Search

The overlap between edge computing and unmanned aerial systems enables Unmanned Aerial Vehicles (UAV) to quickly offload image processing tasks onto edge devices, avoiding the transmission of images over long distances. To improve the speed and efficiency of UAV image stitching in an edge computing environment, this paper proposes an adaptive UAV image parallel stitching algorithm in an edge computing environment. The algorithm incorporates both route-based parallel processing and inverted binary tree-based parallel processing, dividing the image stitching task into multiple processes and allocating them to different cores based on the CPU core count, number of flight routes, and number of images, thereby enhancing computational efficiency in edge scenarios. The experimental results indicate that, when the number of flight routes is greater than or equal to the number of CPUs, the adaptive algorithm will employ the more efficient route parallelism. Conversely, when the number of flight routes is less than the number of CPUs, the efficiency of inverted binary tree parallelism is higher. In the same experimental environment and dataset, the adaptive image stitching algorithm demonstrates an efficiency improvement of approximately 2–10 times compared to other algorithms, with no significant degradation in image quality. This demonstrates that in edge environments, the utilization of multi-threaded adaptive route and inverted binary tree-based parallel approaches can effectively harness the computing resources of edge devices, significantly improving the stitching speed of UAV images and providing technical support for rapid real-time monitoring by UAV. [ABSTRACT FROM AUTHOR]

One of the limitations of remote sensing is the low spatial resolution of the open-access multispectral sensors, generating a mixture of spatial information. The mixed pixels can be modelled as the linear combination of fundamental components, called endmember, with a weighted contribution or abundance. The development of linear unmixing algorithms considering spatial and spectral information has recently increased. Some unmixing methods have relied on segmentation to integrate spatial data, and one of the most used is superpixel-based segmentation. However, previous work in superpixel-based unmixing focuses on using superpixels as uniform regions. Commonly, linear unmixing is used on hyperspectral imagery, and limited literature is found with multispectral images. This paper aims to propose a new preprocessing approach for multispectral linear unmixing called Superpixel Linear Independent Preprocessing. The proposed approach generates a set of candidates to endmembers based on spatial-spectral information; these are the input of traditional endmember extraction methods for multispectral unmixing. Experimental results show that the proposed preprocessing improves the performance of endmember extraction. [ABSTRACT FROM AUTHOR]

Many square ancient sites exist in the Mongolian plateau region, and locating them is of great importance for archaeological research. In recent years, object detection in Google Earth (GE) high-resolution remote sensing (RS) images based on deep learning has driven archaeologists' research of ancient site detection. Deep learning techniques significantly improve the accuracy of site detection in RS images when compared with traditional detection methods while reducing design and computation time. Based on the characteristics of the research objectives, this paper proposes an improved Faster R-CNN algorithm for the detection of square ancient sites in GE high-resolution RS images, which employs Swin-Transformer, VGG16, Atrous Spatial Pyramid Pooling (ASPP), Squeeze-and-Excitation Networks (SENet) to form an improved backbone network, and three methods to optimize the Region Proposal Network (RPN). In addition, a dataset of known square ancient sites containing four typical regions of the Mongolian plateau is built using GE high-resolution RS images for training and evaluating the algorithm model. The experimental results show that the Precision, Recall, F1, IoU, and Average Precision (AP) of the proposed improved Faster R-CNN are 91.38%, 91.16%, 91.27%, 83.49%, and 93.57%, respectively, which are 34.89%, 2.70%, 22.29%, 31.46%, and 7.32% higher than those of the original Faster R-CNN. The algorithm also has high evaluation metrics for object detection in four typical regions: hills, Gobi, cropland, and grassland. Finally, the proposed algorithm is applied to detect square ancient sites in six selected typical regions, and numerous new ones are discovered. Overall, the proposed algorithm provides an effective method for archaeological investigations in the study region. Deep learning is applied to Google Earth high-resolution RS images of the Mongolian Plateau for archaeological detection. A dataset of square ancient sites on typical regions of the Mongolian Plateau has been created. An improved Faster R-CNN algorithm is proposed by modifying the backbone network and the region proposal network. The proposed algorithm is used to detect square ancient sites in typical regions of the Mongolian plateau with good effects. [ABSTRACT FROM AUTHOR]

Sparse unmixing has made great progress in hyperspectral unmixing recently. To improve the unmixing accuracy, spatial information has been widely added to the unmixing model. However, due to the complexity of ground material mixing, the performance of the same model in different situations is unsatisfying. Dataset with a uniform blocky area and sharp boundaries, superpixel-based unmixing methods cluster similar pixels together and effectively exploit spatial correlation and work well, and the same to homogeneous mixed pixels, which usually have the same endmembers and abundance usually. However, if the dataset is mixed randomly and irregularly, the above idea failed. To deal with different mixed situations comprehensively and efficiently, a new method, named spectral-spatial-sparse unmixing with superpixel-oriented graph Laplacian (SGLapS3U), is proposed in this paper. For datasets with patched uniform distribution, the superpixel-oriented graph Laplacian can better investigate the spatial correlation of pixels within each patch. For datasets with irregular mixing situation, a spectral-spatial weighting factor is utilized to explore the spatial continuity of the images, while also guaranteeing the sparsity of the results. The experimental results on different datasets demonstrate the superiority of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Leaf area index (LAI), officially listed as one of essential climate variables, quantifies the structure and amount of vegetation and characterizes the interaction between vegetation and climate. The advanced MEdium Resolution Spectral Imager (MERSI-II) onboard FengYun-3D (FY-3D) can provide twice-daily global observations of earth at a spatial resolution of 250 m. Therefore, it has great potential for promoting the improvement of global LAI products and boosting the development of earth system modelling. However, the existing methods are mostly sensor-specific, they can not be directly applied to MERSI-II data for LAI generation. In this paper, we proposed a sensor-adaptive approach for LAI estimation based on MERSI-II observations. This method is composed of an LAI retrieval look-up table based on radiative transfer theory, which was calibrated by a global optimizing algorithm to adapt MERSI-II characteristics, and a backup algorithm training neural networks with MERSI-II Normalized Difference Vegetation Index (NDVI) and Moderate Resolution Imaging Spectroradiometer (MODIS) LAI. We evaluated the MERSI-II LAI retrievals by intercomparison to MODIS products over mainland China and direct validation using ground-based upscaled LAI reference maps. The assessments demonstrate that (1) the derived MERSI-II LAI products agree well with the MODIS benchmarks in both spatial and temporal respects; (2) compared to the MODIS LAI, the MERSI-II LAI retrievals with less gaps show great potential in improving spatiotemporal continuity; (3) validation versus in-situ measurements reveals acceptable accuracy of the MERSI-II LAI products with a R2 of 0.85 and RMSE of 0.82; (4) the proposed parametric optimization strategy could successfully transplant MODIS LAI algorithm to MERSI-II data. [ABSTRACT FROM AUTHOR]

Himawari-8, a geostationary satellite, is equipped with the Advanced Himawari Imager (AHI) sensor, which offers significant advantages for forest fire monitoring. This study proposes a weighted contextual fire detection algorithm (AHI_WFDA) that can apply to the AHI sensor as a global fire detection algorithm. Unlike the traditional pass-by screening algorithms, the algorithm takes into account the characteristics of different bands and assigns different weights and corresponding thresholds to the test conditions based on the bands' sensitivity to fire. To validate the algorithm's performance, we tested it on fires in five target areas. We regard MODIS data as the ground truth data and it was used as the benchmark for comparison with the AHI_WFDA , the Himawari-8 official product WLF, and the traditional spatial contextual algorithm (the reproduced SEVIRI algorithm). The results show that the AHI_WFDA significantly reduces the commission error rate compared to the WLF product. While our algorithm's accuracy rate is not superior to the SEVIRI algorithm, it detects more fire incidents correctly. Compared with the MODIS active fire product, the AHI_WFDA's omission error rate is about 63%. In contrast, the relative commission error rate is about 12%, which is in line with the results of some previous studies. In addition, we conducted detailed verification of our algorithm's results with the support of the Landsat series and Sentinel-2 data. The results show that the algorithm in this paper can effectively exploit the fire detection capability of AHI sensors and provide a new idea for the subsequent algorithms. [ABSTRACT FROM AUTHOR]

Compressed sensing (CS) algorithms mostly achieve linear array synthetic aperture radar (LASAR) 3D sparse imaging under the On-Grid strategy, they suffer from the mismatch measurement matrix and decreased imaging quality due to the position-errors among targets and preset scattering units. Aimed at this problem, based on the Off-Grid strategy, a sparse recovery algorithm via adaptive grids (SRAG) is proposed in this paper. First, the proposed algorithm extracts the target scattering units in the imaging scene under the On-Grid strategy. Second, the target scattering units with position-errors are extracted under the non-zero adjacent scattering coefficient criterion, and they are defined as the unfocused scattering units. Third, according to whether the unfocused scattering units' distance is smaller than the scattering unit spacing, their search-areas of targets' real positions are set, respectively, and differently. Finally, based on the minimum scattering coefficient residual criterion, we adaptively compensate the unfocused scattering units' position-errors and re-estimate their scattering coefficients. Both simulation and experimental results indicate that the SRAG algorithm decreases the position-errors effectively, it improves the imaging quality, estimation accuracy of targets' positions, and scattering coefficients than traditional On-Grid CS algorithms. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar systems are capable of acquiring high-resolution images by modulating and transmitting waves in high frequency levels towards the ground. Synthetic Aperture Radar (SAR) images are generated by demodulating and processing the backscattered waves by the targets. New SAR systems produce high-resolution images by raising the modulation frequency. The sampling time becomes shorter and a large number of samples are generated, which costs for processing and storage. Compressed Sensing (CS) is a compression technique capable of reconstructing a sparse signal from a small number of samples inferior to the conventional sampling. The representation basis, that projects a signal to a sparse form is the key of the application of CS. CS becomes unusable in the acquisition of heterogeneous scenes that present many scatterings types because the representation matrices are unknown and require intensive computing to generate them. In the literature, most proposed researches in the CS field apply CS on simulated sparse scenes, where only a few number of strong scatters are present to avoid the representation matrix computing. The purpose of this paper is to apply CS on non-sparse images and to avoid heavy computation to generate a representation matrix at the same time by combining the CS with the Gaussian Process regression (GPR). A small number of backscattered signals are acquired and sampled with respect to the Nyquist theory, sparsified and used as a feature vector for the training of the GPR model. The remaining signals are processed by the CS theory. After reconstruction, the zero values of the image are predicted using the model generated by the GPR algorithm. Five strategies are proposed in this paper and several evaluations are performed. These methods reconstruct an exploitable image from 40 % of samples. [ABSTRACT FROM AUTHOR]

Estimating the velocity of electromagnetic waves in the medium is essential for ground penetrating radar (GPR) to reconstruct target scenes. However, the existing velocity estimation methods based on imaging algorithms, e.g. the back-projection (BP)- and the Stolt migration-based methods, are susceptible to clutter and cannot strike a balance between depth independence and computational efficiency. Therefore, a velocity estimation method is proposed based on the vertex extraction-guided local BP algorithm. Initially, the high-order moment (HOM) is introduced into GPR data by analysing the distributions of target hyperbolas and clutter. Designed to avoid clutter, the proposed HOM sliding window extracts the hyperbola vertex at a high signal-to-clutter ratio region. By virtue of the extracted vertex, the local hyperbola region is subsequently extracted to reduce computation. Additionally, this paper adopts the depth-independent BP algorithm and further develops a local BP algorithm utilizing its imaging flexibility. Guided by the extracted vertex, the proposed local BP algorithm is iteratively performed on the local hyperbola region to estimate the velocity by a focus metric. Comprehensive experiments demonstrate the effectiveness and robustness of the proposed velocity estimation method. The proposed method outperforms the existing methods in clutter robustness, computational efficiency, and depth independence. [ABSTRACT FROM AUTHOR]

Common image fusion methods used to merge remotely sensed data of varying spatial and spectral information as provided by different air-, and space-borne sensors often do not provide the optimal reachable information. This paper proposes a novel fusion method for pansharpening using a multi-resolution analysis (MRA) based on Chinese Gaofen (GF-1/2) satellite data and corresponding drone data as an example. The novel fusion method is named droesharpening fusion method, which addresses common poor spatial and spectral feature issues of fusion results. The droesharpening fusion method designed several separate computing steps based on wavelets and a pulse-coupled neural network (PCNN) to calculate low-resolution drone (LDRO) images and an injection weight (gk) for significantly improved results. The droesharpening fusion method includes a new algorithm for reducing the MDRO image dimensions (RDA). The proposed new algorithm calculated image feature (IFA), and the proposed algorithm of calculating the gk (IWA). ARD is used to reduce the dimensionalities of a drone (MDRO) image to a new single-band drone (SDRO) image. Then, we applied an improved 'à trous' Wavelet Transform (ATWT) to SDRO images to extract LDRO images and an improved PCNN for the multispectral (MS) images. Additionally, edge processing is deployed to the PCNN segmented images. The IFA is then used to calculate the spatial characteristics of the SDRO images based on the ATWT decomposed image and the spectral features of the MS images based on the PCNN segmented images. In the next step, the IMA calculates the gk based on the spatial and spectral characteristics. The detailed spatial information of the MDRO images is then injected into the MS images by using the gk to obtain the fused drone/multispectral satellite imagery. Additional experimental results using several drone/multispectral satellite images proved that the proposed method achieves high spectral fidelity and simultaneously improves the spatial resolution of fused images. [ABSTRACT FROM AUTHOR]

Hyperspectral image clustering is usually used for unsupervised learning in different applications. However, the traditional clustering methods have not been considered the complex relationships among neighbouring pixels. The Albedo and Shading elements can define pixel values in the HyperSpectral Images (HSIs). In HSIs, features are different from each other because of their natural physical characteristics and the physical nature of different image features can be described by the Albedo element. Therefore, in this paper, we generate the natural Albedo feature of the HSIs by applying Albedo recovery step to exploit main information from HSIs. Then, we utilized the Fuzzy C-means clustering method to cluster the natural Albedo dataset. In this paper, we propose a novel accurate Albedo Recovery based Fuzzy C-Means (ARFCM) method to cluster HSIs. In the dataset, each feature vector is processed by the Albedo recovery step to create a new feature vector. This new feature vector can describe the dataset better than the original one. Comparing clustering methods as one of the powerful clustering algorithms are widely used in the remote sensing fields of studying. The experiments conducted on several benchmark datasets demonstrated that the proposed clustering method achieves higher performance than other methods and present the efficiency and effectiveness of the proposed method. The results of experiments over different HSI datasets indicated that the proposed method could produce reliable and suitable results compared to the other methods. This shows the robustness of the proposed ARFCM algorithm over the various HSI datasets. Other methods may provide a good response in a given dataset and do not perform well in the other data. Consequently, the ARFCM method, regardless of the study area characteristics and the sensor features, always renders remarkable clustering accuracy. [ABSTRACT FROM AUTHOR]

The high accuracy of infrared dim and small target detection in complex backgrounds is of great relevance for infrared identification and tracking systems. Traditional infrared dim and small target detection methods suit scenes with a single and homogeneous continuous background. However, human vision system methods suffer from an undetectable or high false alarm rate in complex scenes with dim small targets. To address this shortcoming, this paper proposes an infrared dim and small target detection algorithm based on frequency domain differencing (FDD). The proposed algorithm consists of a spectrum residual module and a Gaussian greyscale difference module. Firstly, the target enhancement image is constructed by using the spectrum residual module to highlight small targets and suppress background noise. Secondly, the local contrast of the image is enhanced by the Gaussian grayscale difference module, which accurately depicts the edge information of small targets and locates them. Finally, the target enhancement image and Gaussian grayscale difference image are fused to detect infrared dim and small targets. Experimental results show that the proposed algorithm has higher accuracy under the evaluation metrics of local signal-to-noise ratio gain (LSNRG), signal-to-clutter ratio gain (SCRG) and background suppression factor (BSF). At the same time, compared with other algorithms, the detection rate of the proposed algorithm is higher for infrared dim and small targets in complex scenes. Code is available at . [ABSTRACT FROM AUTHOR]

Pushbroom time delay integration charge-coupled device imaging is the primary imaging mode of high-resolution satellites. This imaging mode requires an inverse transformation to determine image coordinates from ground coordinates relying on an iterative algorithm. This process is complicated and time-consuming, and convergence may fail. With the improvement of the agility and mobility of optical satellites, curve scanning imaging becomes possible, which will be the dominant imaging mode to greatly improve the observation efficiency of satellite in the future. However, the traditional inverse transformation algorithm is no longer applicable to curve imaging mode. Based on the essential characteristics of pushbroom time delay integration charge-coupled device imaging, we propose a novel inverse transformation algorithm with approximate perpendicularity constraint between CCD array and image motion trajectory. This algorithm can not only be applied to both traditional push-scan mode and curve imaging mode, but also improve the computational efficiency of inverse transformation. In this paper, the simulation data of curve imaging mode and traditional push-scan imaging data of JiLin-01, GaoFen26A and GaoFen26B are used to carry out experiments. Compared with the existing inverse transformation algorithm, the proposed method can be well applied to the curve imaging mode. Moreover, the inverse transformation accuracy can reach 0.0002–0.0006 pixels and the computational efficiency is improved by 550% compared with affine model and 35.6% compared with scanning plane model for traditional push-scan imaging, which verifies the correctness and feasibility of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Morphological processing has found several applications in image analysis and pattern recognition. Some of these techniques, known as morphological reconstruction algorithms, have been employed for land cover classification in remote sensing data. In this paper, we analyse the mathematical foundations, applications, and limitations of reconstruction by dilation and by erosion oriented to urban extraction, using Sentinel-2 satellite data. Different techniques oriented to the proper determination of the marker and mask images, the basis for reconstruction, are proposed in this manuscript. In addition, in order to diminish the long computation time required for reconstruction, two parallel implementations using Multi-core and GPU, are proposed. According to our research, these algorithms can be considered as effective and non-supervised solutions for urban extraction applications based on multispectral satellite imagery. [ABSTRACT FROM AUTHOR]

Image matching is critical for photorealistic 3D reconstruction based on oblique images. An efficient match pair selection methodology for matching large-scale oblique UAV images is proposed in this paper. The proposed methodology effectively uses existing geospatial data and prior knowledge about data acquisition to generate precise match pairs. First, the principal point of each image is directly georeferenced. The direct georeferencing is based on a novel new DEM-aided direct georeferencing algorithm which employs an iterative binary search in the elevation domain. Second, a terrain-adaptive search radius is calculated for each image based on the calculated ground points, POS data, and prior knowledge. Finally, initial match pairs are generated based on a camera-oriented approach. The camera-oriented approach generates match pairs using k nearest neighbours (knn) search and prior knowledge. False connections in the initial match pairs are filtered using geometrical constraints. A limited number of match pairs are kept to reduce the redundancy of the generated match graph. The proposed methodology is tested on a dataset containing 28,560 images. The experimental results show that the precision of the generated match pairs is 99.99%. An incremental 3D reconstruction of the scene is conducted based on the robustly matched images. More than 99.8% of all the images are successfully oriented. The profiling analysis shows that the proposed methodology generates all the match pairs in 7.719 seconds. The precision, efficiency, and robustness of the proposed methodology are comprehensively analysed. The experimental and simulation results show that the proposed methodology is efficient and precise for large-scale UAV photogrammetry. [ABSTRACT FROM AUTHOR]

Imaging Satellites acquire multispectral images, MIs, in low resolution, LR, and panchromatic images, PANs, in high resolution, HR, due to some advantages provided in satellite design. The pansharpening, PS, is a super resolution image synthesis method that is used to generate the pansharpened image, PI, by fusion of PAN and MI. The use of PS process is unavoidable in applications such as efficient use of communication-bandwidth of imaging satellites and fusion of images derived from various image sensors. The PS process is a multi-step process consisting of various complex image processing stages, such as registration, resampling, synthesis, and fusion. The Weighted Differential Evolution Algorithm-based PS method, WDEPS, has been proposed in this paper. The WDEPS uses WDE to synthesize the intensity image, which is the blended-image of MI -bands. WDE has been used to compute the relevant image-blending weights, efficiently. In the experiments, several satellite images (QuickBird-2, Ikonos-2, and GeoEye-1) with different spatial resolutions were used. The WDEPS's experimental results have been compared with 17 well-known PS methods by using 9 full-reference and 3 blind image quality assessment metrics. The experimental results exposed that WDEPS generates high-quality PIs than traditional PS methods used in the experimental aspect of qualitative and quantitative assessment. [ABSTRACT FROM AUTHOR]

Feature matching in optical remote sensing images usually suffers from significant intensity differences and background variations. In this paper, an effective image matching approach is proposed to match salient structures in optical remote sensing images. The proposed method consists of three main steps. In the first step, EDLines algorithm is implemented to extract straight lines from two corresponding images, and these lines are further processed and divided into line segments for feature matching. In the second step, a robust descriptor namely line segment context (LSC) descriptor is computed for each line segment. An iterative procedure that combines line segment description and feature matching is presented for accurate matching. Finally, the consistency check is implemented to further refine the matching results. We conduct the experiments on pairs of optical remote sensing images, and experimental results show that the proposed method can automatically and robustly generate line segment features and achieve favourable performance compared to existing image matching approaches. [ABSTRACT FROM AUTHOR]

The geolocation quality of satellite observation datasets is causally related to the credibility of operational products. The twice-daily global Earth observations provided by FY-3D/MERSI-2 (FengYun-3D/MEdium Resolution Spectral Imager II) have been used to generate various remote sensing application products, but their geolocation performance has not yet been documented, while the comprehensive analysis of geometric accuracy provides important guidance for improving geolocation accuracy and data application in the future. In this paper, a combination of phase-only correlation and anomaly isolation techniques was used to design a robust algorithm of sub-pixel geolocation displacement detection for MERSI-2 data with 1 km spatial resolution. Utilizing MERSI-2 data from three typical regions and monthly Landsat 8 OLI (Operational Land Imager) data synthesized by Google Earth Engine (GEE), an exhaustive presentation of how the developed method quantifies the geometric displacements of the Level 1 dataset to along-track and cross-track directions is described, ultimately revealing the deterioration of MERSI-2 on-orbit geolocation performance. During the 17 months of official operational products, the geolocation error increases by a factor of 1.13 in along-track direction and 1.56 in cross-track direction. But approximately 70% of the geometric displacements remain within ±300 m in both along-track and cross-track directions, while about 92% are within ±500 m. This method reliably ascertains that the geolocation accuracy of MERSI-2 matches within 1/2 Instantaneous Field of View (IFOV). [ABSTRACT FROM AUTHOR]

Reliable labelled samples have always played a vital role in the supervised paradigm of hyperspectral imagery (HSI) classification due to the fact that the inclusion of incorrect label information in the training set can seriously degrade the performance of classification methods. Recently, although some inter-class difference-based detection algorithms have been developed to remove mislabelled samples (i.e. noisy labels) in training set, the benefit of contextual information for each sample has not been fully explored yet. In this paper, a training redefinition with entropy-based structure set density (ESSD) method is designed, which consists of following main steps. First, the proposed ESSD method employs an over-segmentation technique to cluster the HSI into many shape-adaptive regions that correspond to sample sets. Then, each sample set is represented with an affine hull (AH) model, which exploits both the similarity and variance of samples within each sample set to adaptively characterize the set. Specifically, considering spectral and spatial weak assumptions among samples in each sample set, the idea of entropy trick-based k -nearest neighbour is introduced into each sample set to redefine its structure by removing different class from the sample set. Next, the distance among AH corresponding to each training sample is calculated based on the AH model. Meanwhile, the set-to-set distance is fed to the density peak algorithm to obtain the density of training samples. Finally, a decision-making value is applied to the density of each training sample to cleanse mislabelled samples within noisy training set. Experimental results on real HSI date sets demonstrate the superiority of the proposed method over several well-known training redefinition methods in terms of detection accuracy. [ABSTRACT FROM AUTHOR]

In hyperspectral remote sensing, the classification of hyperspectral imagery is an important issue of concern. However, obtaining sufficient labelled samples for the classification is hard work and consumes enormous labour and material resources. To solve this problem, many scholars make their efforts to the semi-supervised learning method. The self-training model is a popular semi-supervised learning method, which trains a classifier using a few labelled samples and many unlabelled samples in an iterative manner. Nevertheless, the self-training model may provide misclassification as adding incorrect unlabelled samples. This paper proposes a novel semi-supervised learning method, which attempts to introduce the affinity propagation and spatial constraint to self-training model. In the proposed algorithm, a self-training model is employed to expand the labelled sample set. The affinity propagation is applied to select a group of reliable unlabelled samples. To further protect the reliability of unlabelled samples, the selection process of self-training model is constrained in the spatial local area of the labelled samples. In the iteration, the reliable unlabelled samples are selected and added to the labelled sample set. After that, the classifier is trained by the updated labelled samples. The algorithm finishes as the iterations exceed the predetermined value or the labelled sample set is unchanged. Different from the traditional self-training-based semi-supervised learning method, there are mainly three improvements. First, the selection of reliable unlabelled samples is conducted by the affinity propagation, which can effectively improve the reliability of the unlabelled samples. Second, the spatial constraint is introduced to restrict the selection process of self-training model, which can protect the reliability of unlabelled samples and alleviate the computational complexity. Finally, the spectral correlation angle is applied to construct the similarity matrix of affinity propagation, so that the algorithm is more suitable for hyperspectral imagery. A comparative analysis was conducted with classical self-training semi-supervised algorithms to test the effectiveness of the method. It was found that the proposed method provided higher overall accuracy, average accuracy and kappa coefficient (κ) than the competitors. [ABSTRACT FROM AUTHOR]

The Wide Field of View (WFV) imaging system equipped on the GaoFen-6 (GF-6) optical remote sensing satellite can acquire an image with a swath width 800 km and a resolution of 16 m, which is the largest Earth observation swath width among similar satellites in the world. With the advantages of the high spatial resolution and the wide field of view, GF-6 WFV images are widely used in agricultural resources monitoring, forestry resources investigation, and disaster relief. However, the existence of clouds is inevitable problem in GF-6 WFV images, which influences their availability. To quickly and accurately detect cloud areas in GF-6 WFV images, a cloud detection method for GF-6 WFV images based on the spectrum and variance of superpixels is proposed in the paper. First, the GF-6 WFV image is down-sampled. The simple linear iterative clustering algorithm is used to segment down-sampled images to obtain superpixels. The initial cloud detection result is obtained based on the spectrum of superpixels. Second, the initial cloud detection result is refined based on the variance of superpixels to eliminate the influence of cloud-like ground objects. Finally, the refined cloud detection result is post-processed using the region growing algorithm and expansion algorithm. The post-processed cloud detection result is up-sampled to obtain cloud detection result of the GF-6 WFV image. The experimental results show that the recall and precision of the proposed method are 84.61% and 88.46%, respectively, providing good cloud detection results for GF-6 WFV images. [ABSTRACT FROM AUTHOR]

Relative radiometric normalization (RRN) is a critical preprocessing step that is widely applied to remote sensing data. Essential to RRN are the pseudo-invariant features (PIFs) – ground objects with invariant reflectance across the acquisition dates of multiple images. To meet the requirements of RRN for change detection in multi-temporal images, this paper proposed a novel automatic method for PIF extraction: first, we calculated spectral, spatial, and visual features for the images. Next, a set of change vectors were generated to quantify the features' differences. Then, the initial PIF was obtained by synthesizing similar pixels from each change vector. Finally, an iterative linear regression was performed to generate the final PIFs. Furthermore, we employed the random sample consensus (RANSAC) algorithm to establish the RRN model for normalizing the target image. The methods and workflow of PIF extraction and the RRN model establishment were validated with two TripleSat-2 multi-spectral images with a spatial resolution of 3.2 metres. The applicability of the proposed PIF extraction method was further validated by Landsat-8 OLI, GF-1 WFV, Sentinel-2 MSI, and WorldView-2 images. The results showed that: (1) The proposed PIF extraction method can automatically obtain the PIFs with high precision. Based on the extracted PIFs, the RANSAC algorithm is capable of building the RRN model with a significant linear relationship. (2) The PIF extraction method is applicable to multi-spectral images with different spatial resolutions. (3) Compared with the multivariate alteration detection (MAD) and the iteratively reweighted MAD (IR-MAD), the proposed PIF extraction method achieved a better performance in selecting the pixels with smaller radiometric differences, which is helpful to reach a higher accuracy of the RRN model. (4) Differences in image brightness, spectral domain, and spatial domain are considered in the PIF extraction method with fewer parameters and high portability. (5) Spectral features are dominant to obtain ideal PIFs, and feature combinations can get the advantages to enhance the effectiveness of the PIFs. [ABSTRACT FROM AUTHOR]

The characterization of ground targets from a remotely sensed Synthetic Aperture Radar (SAR) image is addressed by polarimetric decomposition. The polarimetric SAR (PolSAR) decomposition measures the contribution of total backscatter from different scattering mechanisms using SAR images. The ambiguities present in the retrieval of scattering are the major problems associated with the model-based decomposition which could be reduced with a combination of interferometric coherence and PolSAR backscatter. The objective of this study is to improve the polarimetric decomposition model for identifying the scattering mechanisms based on the Polarimetric SAR Interferometry (PolInSAR) coherence for natural and manmade features. In this paper, we have proposed a model-based polarimetric decomposition using PolInSAR decorrelation. The PolInSAR decorrelation is exploited here to distinguish the time-varying and invariant scatterers present in the ground. The volume scattering power was calculated using the proposed decorrelation parameter which is the combination of PolInSAR coherence and decorrelation. The proposed algorithm has been tested on spaceborne multifrequency SAR datasets consisting of X-band TerraSAR-X and TerraSAR-X add-on for Digital Elevation Measurement (TanDEM-X), C-band Radarsat-2, and phased array L-band synthetic aperture radar-2 (PALSAR-2) data of advanced land observing satellite-2 (ALOS-2) PolInSAR data for the Dehradun region, India. The results show that there is a remarkable reduction in the ambiguities present in the identification of the scattering mechanism from the SAR image by using the proposed decorrelation-based decomposition model. Moreover, the algorithm is tested on X-band TerraSAR-X and TanDEM-X data of the Haridwar area and Rudrapur area, Uttarakhand, India to analyse the potential of the proposed decomposition technique in representing different manmade and natural features. [ABSTRACT FROM AUTHOR]

This study attempts to exploit 'Satellite with Advanced Research and Global Observation Satellite (Argos) and Ka-band Altimeter (ALtiKa)' (SARAL/AltiKa) and Passive Microwave Radiometer (PMR) measurements for the retrieval of precipitation and rain rate (RRain) over the global oceans. The altimetric measurements are affected by the presence of rain and these measurements are thus required to be identified. In this research, the concurrent SARAL and Tropical Rainfall Measuring Mission – Precipitation Radar (TRMM-PR) measurements are used to show the rain sensitivity of some of the altimeter derived parameters and PMR-derived Brightness Temperature (T B ). Based on the probability distribution of rain-sensitive parameters, a probabilistic rain identification algorithm is proposed, which is optimized to reduce the false-alarm cases for rain estimation. In the second step, a Genetic Algorithm (GA)-based rain measurement algorithm is developed. The algorithm is applied to a full year (2016) of independent SARAL measurements, compared with collocated Global Precipitation Measurement (GPM) Mission Microwave Imager (GMI) and Special Sensor Microwave Imager Sounder (SSMIS) measurements. Within TRMM latitudinal coverage area (i.e. < ± 40° latitudes), the comparison with GMI and SSMIS shows correlation coefficient (r) of 0.78 and 0.76 and root mean square difference (RMSD) of 0.48 and 0.43 (mm h−1), respectively. The comparison, beyond latitudinal coverage of TRMM-PR (i.e. outside ± 40° latitudes), with GMI and SSMIS, shows r of 0.63 and 0.60 and RMSD of 0.59 and 0.55 (mm h−1), respectively. The algorithm is further applied to measure rain associated with a tropical cyclone. These rain measurements are then compared with near-concurrent rain measurements from SSMIS, and comparison results are presented in the paper. [ABSTRACT FROM AUTHOR]

Maintaining an up-to-date repository of horizontal curve attributes is extremely important due to the role curves play in the safe operation of highways. Such attributes are typically collected using traditional surveying techniques which have been shown to be time-consuming, traffic disruptive, and potentially unsafe methods. This burden is further aggravated when the data collection is required on a large highway network across North America. To overcome this burden, this paper proposes a framework for network-level detection and extraction of horizontal curve elements from Light Detection and Ranging (LiDAR) data in a fully automated manner. The proposed technique was validated and then tested on LiDAR data collected on 242 km of highways in Alberta, Canada. The algorithm was successful in detecting all curves on the test highways and estimated their attributes with accuracies ranging from 96% to 100% demonstrating the robustness of the extraction method and the feasibility of performing the extraction on such a large scale. The proposed method is an alternative approach that could help transportation agencies maintain an updated inventory of horizontal alignment information on a large-scale. [ABSTRACT FROM AUTHOR]

Building extraction from very high-resolution (VHR) remotely sensed imagery has been an area of increased interest. One of the main purposes of building extraction is to generate polygonal representations of buildings and identify additional engineering applications. However, the complex backgrounds and defects of target images result in incomplete and false edge extraction, which severely reduces the extraction accuracy. To solve these problems, this paper proposes a refined building extraction method based on the semantic edge-assisted approach from VHR remotely sensed imagery. Object and edge detection models are trained to obtain bounding boxes and the edge strength map, respectively, and then the object detection results are used as constraints to refine the edge strength map and repair any unclosed boundaries. To this end, we propose an incomplete boundary repair algorithm for repairing unclosed boundaries. The Douglas–Peucker (D-P) algorithm is applied to simplify boundaries as a series of points and then further simplifies these points to regularize building boundaries and finally determines the repair lines that conform to the rule of boundary variation. The experimental results indicate that the proposed building extraction method and algorithm can obtain a complete and refined polygon boundary of the target building, which makes the approach very convenient in practical applications. [ABSTRACT FROM AUTHOR]

The increasing availability of highly detailed and accurate three-dimensional (3D) geospatial data are currently pushing the 3D change detection analysis towards a new 3D mapping frame. In this paper, medium-term changes (8 years) at a coastal rocky cliff are quantified using and comparing 2.5D and 3D methods to estimate the volume of rockfalls and three datasets: one Terrestrial Laser Scanner (TLS) acquired in 2010 and two coincident Unmanned Aerial Vehicles (UAV: multirotor and fixed-wing) datasets acquired in 2018. Advantages and limitations of these techniques, platforms and methods are discussed and the role of Ground Control Points (GCPs) distribution was analysed. Maps of 3D changes were produced by means of the Multiscale-Model-to-Model Cloud-Comparison algorithm (M3C2). The volume of the eroded-deposited material was estimated using two 2.5D and one 3D approaches: 1) rasterizing M3C2 distances using a conventional top-view perspective, 2) rasterizing the M3C2 distances rotated and orientated with the z vector normal and, 3) for the largest rockfalls, the volume was estimated using the Poisson Surface Reconstruction (PSR) algorithm (3D). The 3D models produced using both UAV platforms showed cm-level accuracies with Root Mean Square Error (RMSE) of 0.02 and 0.03 m for the multirotor and the fixed-wing, respectively, and faithfully represented cliff geometry. GCP configuration analysis showed that, at least, two stripes of GCPs evenly distributed at different heights are necessary, but three are recommended. The spatial pattern of change between the TLS and the two UAVs datasets was similar. The quantification of the volume of the eroded-accumulated material (using the M3C2 distances and the two UAV datasets) resulted in significant differences as the fixed-wing underestimated the values calculated using the multirotor dataset. The 2.5D strategies used to quantify the volume of change underestimated the eroded volume of the largest rockfalls (compared to the PSR 3D method), which provided the most accurate volume estimates. [ABSTRACT FROM AUTHOR]

Satellite remote sensing may serve as an ideal technique to detect dust storms for high temporal and spatial scales. In this paper, we propose an improved dust identification index (IDII) based on Moderate Resolution Imaging Spectroradiometer (MODIS) imagery. The IDII algorithm was used to monitor 129 dust storm events over the West Asia region from 2016 to 2018. Ground-based observations of synoptic stations, RGB images, and Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP), and Ozone Monitoring Instrument (OMI) were implemented for validating IDII algorithm. In addition, the performance of the proposed algorithm was compared with the Global Dust Detection Index (GDDI). The results show that the accuracy (Ac), Probability Of Correct positive Detection (POCD), and Probability Of False-positive Detection (POFD) for the IDII and GDDI are 82%, 85%, 33%, and 71%, 74%, 27%, respectively. Also over the water as a challenging object, it is clearly seen that the IDII performs much better than GDDI method. Our results suggest that the proposed approach can deal with the common limitations of dust detection algorithms, i.e. dust detection over different surfaces (land and water), seasonal changes, and similarity between dust and other objects like clouds. [ABSTRACT FROM AUTHOR]

Unsupervised feature selection (UFS) is a standard approach to reduce the dimensionality of hyperspectral images (HSIs). The main idea in UFS is to define a similarity metric, and select the features minimizing the metric to reduce the data redundancy. In this paper, we proposed a novel criterion for unsupervised dimensionality reduction based on the representation of spectral reflectance to capture dominant reflectance variations. Since capturing all the spectral information from an entire hyperspectral dataset is a time-consuming process, we proposed a heuristic algorithm named Greedy Search for Spectral Representation (GSSR). This algorithm divides the spectrum into spectral regions with less spectral variations and merges them. GSSR, similar to feature selection techniques, preserves the original data from being distorted or compromised by a transformation. We compared the GSSR algorithm with well-known existing algorithms in different experiments using various datasets. Comparison with the best approximation to represent single spectra as well as entire hyperspectral scene revealed that spectral representation is almost the same. The difference between the best spectral representation and the ones provided by GSSR is less than 0.01%; while on average, GSSR is about 660 times faster to represent single spectra and 37 times faster for a complete hyperspectral scene. Five well-known unsupervised dimensionality reduction methods were also implemented and used for comparison analysis. Based on the image classification accuracy over two hyperspectral datasets, the spectral features identified by the proposed criterion improved the classification accuracy as well. [ABSTRACT FROM AUTHOR]

Hyperspectral imagery (HSI) creates a lot of applications in target or anomaly detection due to their rich spectral content. Generally, one scene of an HSI contains more than one class. Therefore, the Gaussian distribution assumption of the background fails. Furthermore, the high dimensionality of data makes background modelling more difficult by increasing redundancy and disturbances. In this paper, a segmented-distance based anomaly detection method is proposed for HSI. The proposed method is based on segmentation and takes advantage of the statistical properties of the segmented areas to suppress the false-alarms. In addition to that, nonlinear feature extraction based on convolutional stacked auto-encoder (SAE) neural networks are implemented to extract deep and nonlinear relations from the input data. Both 1-D and 2-D convolutional layers are investigated. The proposed method is tested on the three different datasets. The experimental results show that the integration of segmentation and deep feature extraction generally performs better than other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

A vehicle extraction method is proposed in this paper to extract vehicles in urban areas more accurately from airborne point clouds. First, the ground points are separated from the non-ground points, and a potential vehicle-occupied area (PVOA) is then extracted from the ground point cloud. A PVOA-based non-ground point cloud segmentation method is proposed in this work, and a gap-based method is put forward to re-cluster the segment, which may include multiple vehicles. The non-ground point cloud is clustered into a series of one-vehicle segments and empty segments. Following this, a shape-based vehicle recognition method is presented that can judge whether or not a given segment is a vehicle using a dynamic time warping similarity measurement. In addition to judging whether or not a segment is a vehicle, the category of each vehicle can also be determined. To a significant extent, our PVOA-based non-ground point cloud segmentation method can avoid the difficulties of over- and under-segmentation that arise in current mainstream methods of object-based vehicle extraction, and can also avoid incorrect segmentation in case of vehicles parked close together. Our shape-based vehicle recognition method can exclude non-vehicle objects, especially those with sizes similar to those of vehicles. This method is more effective than current algorithms based on normal geometric features such as area and rectangularity. Using four datasets of typical urban scenarios, the performance of the new algorithm is tested and compared with that of the OBPCA and DT algorithm. The experimental results show that the correctness, completeness, and quality of the new algorithm are 96.7%, 91.1%, and 93.8%, higher than that of the OBPCA and DT algorithm. [ABSTRACT FROM AUTHOR]

Hyperspectral image classification is a challenging problem for machine learning methods due to the small number of labelled samples and high spectral variability. In this paper, to solve this problem, a novel superpixel and multi-classifier fusion (SMCF)-based classification method for hyperspectral images is proposed. This method takes full advantage of the spectral information of superpixels and the spatial information of hyperspectral images and includes the following three steps. First, superpixels are used to increase the number of training samples and their spectral diversity. Second, label propagation (LP) is used to classify the hyperspectral images. Although LP is an efficient semi-supervised classification method, the corresponding performance is poor for certain land cover types with dispersed spatial distributions. Thus, a support vector machine (SVM) classifier is introduced to classify the hyperspectral images. Finally, the results of the SVM and LP classifiers are combined using our new class-specific weighted fusion algorithm. In the experiments, we selected three widely used and real hyperspectral data sets for evaluation. The final classification performance was evaluated based on two common metrics: the overall accuracy (OA) and the Kappa coefficient. The experimental results show that the proposed SMCF method is superior to six well-known classification methods, even when only 1% or less of the labelled samples are used. [ABSTRACT FROM AUTHOR]

An unsupervised feature extraction method could effectively address the phenomenon where using a limited number of labelled samples leads to poor hyperspectral image (HSI) classification. Inspired by this method, we have developed a new method based on fusing dual unsupervised features for HSI classification in this paper. First, we used principal component analysis (PCA) to reduce the dimensions of HSI data and obtain the first set of unsupervised features. Then, we got the second set of unsupervised features by adopting the self-taught learning method, which could learn more discriminatory features by making full use of the information of unlabelled samples in the same HSI. Next, we used the correlation canonical analysis (CCA) algorithm to fuse linearly dual unsupervised learning features. Finally, we proved the effectiveness of the features extracted by the proposed algorithm by applying the extreme learning machine (ELM) classifier to evaluate the purposes. Experiments with three widely used real HSI datasets showed good classification performance when the number of training samples was quite limited. This demonstrates that the proposed feature learning method was indeed an effective method for HSI classification. [ABSTRACT FROM AUTHOR]

Among the Markov random field methods, conditional random fields (CRF) model has shown good results in Synthetic Aperture Radar (SAR) image segmentation. CRF not only directly models the posterior distribution of label field conditioned on images but also allows the interactions between observations. In this paper, we propose a Fast, Weighted CRF (FWCRF) algorithm based on a two-step superpixel generation method. In our method, heterogeneity of intensity in SAR images due to speckle noise and backscattering is considered. The first step is a preprocessing task for suppressing speckle noise which is done by the L0 smoothing algorithm. It is followed by Sobel edge detector to highlight heterogeneous regions and edges. Then SAR image is partitioned into homogeneous and heterogeneous regions by using fast robust fuzzy c-means clustering (FRFCM). Simultaneously, the simple linear iterative clustering (SLIC) algorithm is applied to split the image into superpixels. Next, the superpixels belonging to the same class are merged by using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) method. Finally, the SAR image is labelled using the FWCRF algorithm which consists of weighted pairwise potential based on adaptive features and applying FRFCM as an initial segmentation method. The proposed algorithm is evaluated in comparison with other conditional random field schemes. The results of our proposed method demonstrate accuracy improvement in segmentation. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) has become one of the most important remote sensing techniques for object interpretation by its abundant band information. As the data dimension increases, band selection technique is utilized to achieve the highest possible classification accuracy with fewer bands. Essentially, it is considered as an NP-hard problem, which is a non-deterministic problem within polynomial complexity and difficult to achieve a satisfactory solution using traditional search methods. Sine cosine algorithm (SCA) is a recently developed swarm intelligence algorithm based on the calculation of sine and cosine functions. To determine the parameters setting in SCA, Lévy flight technique is employed to improve the exploitation phase of the algorithm. In the paper, a new band selection method on the basis of SCA with a Lévy flight is proposed, and an alternative distribution is utilized to decrease the band dimension of HSI. In addition, crossover operation is conducted to enhance the optimal bits of each individual, and an evaluation criterion for assessing the performance of band selection is defined, allowing the classification accuracy and selected number of bands to be as balanced as possible. Experimental results demonstrate that the proposed band selection method is superior to other state-of-the-art approaches in terms of band subsets that achieve higher classification accuracy. [ABSTRACT FROM AUTHOR]

Airborne Light Detection And Ranging (LiDAR) point cloud is an important data source for building 3D digital cities and can be used to acquire and update urban buildings, roads and etc. However, it is difficult to extract complete and accurate building boundaries from airborne LiDAR point clouds due to partial occlusion, which is mainly caused by adjacent tall trees, particularly in spring and summer. In this paper, we propose an improved minimum bounding rectangle (IMBR) algorithm to extract complete and accurate regularized building boundaries with and without partial occlusion from aerial LiDAR point clouds. The new algorithm only uses LiDAR point cloud and doesn't need any additional data source. In addition, the algorithm can be applied to buildings with complex shapes. To test the proposed algorithm and compare it with the recursive minimum bounding rectangle (RMBR) algorithm, three datasets with different types of partial occlusions and different shapes were tested. The experimental results show that IMBR can successfully extract the complete and accurate regularized building boundary with or without partial occlusion, and its accuracy is equal to that of RMBR algorithm. [ABSTRACT FROM AUTHOR]

Striping noise is intrinsic to the process of image acquisition via scanning systems. Although it can be mitigated by radiometric calibration, the residual noise can jeopardize the quantitative analysis of the images and the extraction of physical parameters. This paper presents a new approach for evaluating destriping algorithms by means of a synergic use of: (1) distortion measurements, (2) quality indexes and relevant benchmark values calculated from simulated data, and (3) evaluation of effects on parameters extraction. The proposed procedure is here used to evaluate the performance of three destriping algorithms: Destriping Algorithm based on Statistics and Filtering (DASF), ENVI® algorithm and Wavelet-Fourier Filtering (WFF), on two different scenarios of hyperspectral push-broom data. The study pointed out the need of an approach based on the analysis of several aspects in order to identify the best performing algorithm. In addition, the results showed a good performance of both DASF and WFF that preserved the original radiometry without introducing spectral distortion. [ABSTRACT FROM AUTHOR]

Phase unwrapping (PU) is one of the key processes in reconstructing the digital elevation model (DEM) of a scene from its corresponding interferometric synthetic aperture radar (InSAR) data. In contrast to traditional single-baseline PU, the multibaseline PU does not require phase continuity, which is useful when reconstructing the DEM in cases where the topography varies sharply. However, the performance of the multibaseline PU is directly related to the noise level, whereas the single-baseline PU algorithm has favourable noise robustness since it is based on the global wrapped phase information, e.g. the PU-max-flow (PUMA) algorithm. To improve the noise robustness of the multibaseline unwrapping process, we extend the single-baseline PUMA algorithm in this paper to a multibaseline domain, referred to as the multibaseline PUMA algorithm, which allows the unwrapping of multibaseline interferograms to generate the DEM. The proposed algorithm is less influenced by the phase continuity assumption by taking advantage of the multibaseline diversity and improves the noise robustness by using the global wrapped information from both single- and multibaseline domains. The performance of the proposed algorithm is tested on both simulated and real InSAR data experiments to demonstrate the effectiveness and noise robustness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

A novel unsupervised image classification algorithm which based on the sparse representation theory for polarimetric synthetic aperture radar (PolSAR) image is introduced in this paper. The algorithm conjunctively uses sparse representation-based classification (SRC) theory, dictionary updating method, and label smoothness constraint to update class labels. The unsupervised H/ /A Wishart classification method is introduced to provide the preliminary classification result, from which the initial dictionary and class labels can be extracted. An energy function is defined, and it contains two terms. The first term is based on the sparse representation theory. It reflects the cost of assigning different class labels to a pixel. The second term is label smoothness constraint. It constrains that class labels of neighbouring pixels in flat regions should be the same. By alternately minimizing the energy function, two unknown variables, dictionary and class labels are updated. Optimized class labels are the outputs to compose the final classification result. Extensive experimental results for three PolSAR datasets are analysed to verify the validity of the proposed method. Comparison with other unsupervised/supervised classification methods indicates its superiority. [ABSTRACT FROM AUTHOR]

The present study introduces distance based change detection (CD) algorithms in polarimetric synthetic aperture radar (PolSAR) data. PolSAR images, due to interactions between electromagnetic waves and target and because of the high spatial resolution, can be used to study changes in the Earth's surface. The purpose of this paper is to use features extracted from the fully-polarimetry imaging radar that involved Yamaguchi four-component and H/A/α decomposition based on the distance between the vectors of features for CD. We first extract features from polarimetric decompositions of multi-looked covariance (or coherency) matrix data. We then use two well-known distance measures namely Canberra and Euclidean distances for measuring the similarity between the vectors of polarimetric decompositions at different times. Assessment of incorporated methods is performed using different criteria, such as overall accuracy, area under the receiver operating characteristic curve, and false alarms rate. The results of the experiments show that Canberra distance has better performance with high overall accuracy and low false alarm rate than Euclidean distance and other compared algorithms to detect changes. [ABSTRACT FROM AUTHOR]

In recent years, object-based segmentation methods and shallow-model classification algorithms have been widely integrated for remote sensing image supervised classification. However, as the image resolution increases, remote sensing images contain increasingly complex characteristics, leading to higher intraclass heterogeneity and interclass homogeneity and thus posing substantial challenges for the application of segmentation methods and shallow-model classification algorithms. As important methods of deep learning technology, convolutional neural networks (CNNs) can hierarchically extract higher-level spatial features from images, providing CNNs with a more powerful recognition ability for target detection and scene classification in high-resolution remote sensing images. However, the input of the traditional CNN is an image patch, the shape of which is scarcely consistent with a given segment. This inconsistency may lead to errors when directly using CNNs in object-based remote sensing classification: jagged errors may appear along the land cover boundaries, and some land cover areas may overexpand or shrink, leading to many obvious classification errors in the resulting image. To address the above problem, this paper proposes an object-based and heterogeneous segment filter convolutional neural network (OHSF-CNN) for high-resolution remote sensing image classification. Before the CNN processes an image patch, the OHSF-CNN includes a heterogeneous segment filter (HSF) to process the input image. For the segments in the image patch that are obviously different from the segment to be classified, the HSF can differentiate them and reduce their negative influence on the CNN training and decision-making processes. Experimental results show that the OHSF-CNN not only can take full advantage of the recognition capabilities of deep learning methods but also can effectively avoid the jagged errors along land cover boundaries and the expansion/shrinkage of land cover areas originating from traditional CNN structures. Moreover, compared with the traditional methods, the proposed OHSF-CNN can achieve higher classification accuracy. Furthermore, the OHSF-CNN algorithm can serve as a bridge between deep learning technology and object-based segmentation algorithms thereby enabling the application of object-based segmentation methods to more complex high-resolution remote sensing images. [ABSTRACT FROM AUTHOR]

Adaptive Neuro-Fuzzy Inference System (ANFIS) is a robust method in solving non-linear classification by employing a human-readable interpretation manner. This paper verified a hybrid model, named WANFIS, where Whale Optimization Algorithm (WOA) was used for feature selection and tuning parameters of the ANFIS for land-cover classification. Hanoi, the capital of Vietnam, was selected as a case study, because of its complex surface morphology. The model was trained and validated with different data sets, which were subsets of the segmented objects from SPOT 7 satellite data (1.5 m in panchromatic and 6 m multiple spectral bands). The image segmentation was carried out by using PCI Geomatics software (evaluation version), and output objects with associated spectral, shape, and metric information were selected as input data to train and validate the proposed model. For accuracy assessment, the performance of the model was compared to several benchmarked classifiers by using standard statistical indicators such as Receiver Operator Characteristics, Area under ROC, Root Mean Square Error, Absolute Mean Error, Kappa index, and Overall accuracy. The results showed that WANFIS outperformed the other in almost all training data sets for both operations. It could be concluded that the examination of the classification model in different training data sizes is significant, and the proper determination of predictor variables and training sizes would improve the quality of classification of remotely sensed data. [ABSTRACT FROM AUTHOR]

In this paper, a high fidelity haze removal algorithm is proposed for optical satellite images by using progressive transmission estimation based on the dark channel prior (DCP). The transmission is estimated adaptively according to the histogram of the dark channel image and the constraint of maximum transmission. Then, the guided filter is used to refine the transmission to obtain a continuous transmission map in which the clean areas are retained as much as possible. The refined transmission is applied to each visual band to obtain the initial de-hazing image. Then, the transmission is re-evaluated for the initial de-hazing image, and a guided filter with a small window size is used to refine the re-evaluated transmission. Furthermore, the transmission is stretched with the power-law transformation (PLT). To ensure fidelity in hazy areas, the optimal stretched transmission is estimated according to the artificially selected samples, from which the final haze removal results can be achieved. Several optical satellite images are collected and tested to validate the effectiveness of the proposed method. The evaluation results demonstrate that the proposed method is superior to the traditional methods and can recover a haze-free image with high fidelity. [ABSTRACT FROM AUTHOR]

In the last 15 years, the frequency, spatial extent, and intensity of dust storms have increased and it is one of the main continuously occurring environmental hazard in the Middle East region. Since dust storms generally cover a large spatial extent and are highly dynamic, satellite Earth Observation (EO) is a key tool for detecting their occurrence, identifying their origin, and monitoring their transport and state. A variety of satellite dust detection algorithms have been developed to identify dust emissions sources and dust plumes once entrained in the atmosphere. This paper evaluates the performance of five widely applied dust detection algorithms: the Brightness Temperature Difference (BTD), D-parameter, Normalized Difference Dust Index (NDDI), Thermal-Infrared Dust Index (TDI) and the Middle East Dust Index (MEDI). These algorithms are applied to Moderate Resolution Imaging Spectroradiometer (MODIS) data to detect dust-contaminated pixels during three significant dust events in 2007 in the Middle East region that originated from sources in Iraq, Syria and Saudi Arabia. The results indicate that all methods have a comparable performance in detecting dust-contaminated pixels during the three dust events with an average detection rate (between all algorithms) of 85%. However, substantial differences exist in their ability to distinguish dust from clouds and the land surface, which resulted in large errors of commission. Direct validation of these algorithms with observations from seven Aerosol Robotic Network (AERONET) stations in the region found an average false detection rate (between all algorithms) of 89.6%. Although the algorithms performed well in detecting the dust-contaminated pixels their high false detection rate means it is challenging to apply these algorithms in operational context. [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing (HU) is an important technique for extracting materials and their abundance in hyperspectral remote sensing imagery. The presence of nonlinear mixing of light on the ground poses a difficult problem when estimating abundance fractions of all pixels. This problem makes the foundation of algorithms that can adapt all types of nonlinear mixing on the ground more complex and challenged. In this paper, a new bionic intelligent algorithm named crossover double particle swarms optimization (CDPSO) has been presented to estimate abundance for hyperspectral remote sensing imagery. The reconstruction error is used as the objective function for HU based on multilinear mixing model, and the nonlinear unmixing is transformed into an optimization problem. By improving the optimization performance of PSO for HU, we embed two types of new strategies, including double particle swarms crossover and swarm re-initialization, respectively. Our experiments, conducted using both synthetic and real hyperspectral data, demonstrate that the proposed CDPSO algorithm can outperform other state-of-the-art unmixing methods. [ABSTRACT FROM AUTHOR]

To meet the high frame rate requirements of correct point correspondences with a sub-pixel precision, this paper first proposes a Field Programmable Gate Array (FPGA) architecture that consists of corner detection, corner matching, outlier rejection, and sub-pixel precision localisation. In the architecture, a combined Features from Accelerated Segment Test (FAST)+ Binary Robust Independent Elementary Features (BRIEF) algorithm is adopted for detection and matching with pixel precision, a combined algorithm of Slope-based Rejection (SR) and Correlation-Coefficient-based Rejection (CCR) is used to reject the outliers, and a gradient centroid-based algorithm is used for sub-pixel precision localisation. The whole FPGA architecture is implemented on a single FPGA platform (Xilinx XC72K325T). Five image datasets with different spatial resolutions, textures, lights, rotate angles, and viewpoints are used to evaluate the performance of the FPGA-based implementation. The experimental results show that (1) the SR and CCR algorithms are effective for outlier rejection; (2) a higher correct matching rate is achieved for the image pairs that cover artificial textures than for those that cover natural textures; (3) the proposed architecture is also suitable for image pairs with small change of lights, rotate angles, and viewpoints; (4) the speed of the FPGA-based implementation can reach 280 Frames Per Second (FPS), which is 35 times faster than the Personal Computer (PC)-based implementation; and (5) the usage of FPGA resources is acceptable for the selected FPGA platform. The speed and usage of the FPGA resources can be improved when the whole FPGA-based implementation is further optimised. [ABSTRACT FROM AUTHOR]

This paper presents a novel adaptive spatially constrained fuzzyc-means (ASCFCM) algorithm for multispectral remotely sensed imagery clustering by incorporating accurate local spatial and grey-level information. In this algorithm, a novel weighted factor is introduced considering spatial distance and membership differences between the centred pixel and its neighbours simultaneously. This factor can adaptively estimate the accurate spatial constrains from neighbouring pixels. To further enhance its robustness to noise and outliers, a novel prior probability function is developed by integrating the mutual dependency information in the neighbourhood to obtain accurate spatial contextual information. The proposed algorithm is free of any experimentally adjusted parameters and totally adaptive to the local image content. Not only the neighbourhood but also the centred pixel terms of the objective function are all accurately estimated. Thus, the ASCFCM enhances the conventional fuzzyc-means (FCM) algorithm by producing homogeneous regions and reducing the edge blurring artefact simultaneously. Experimental results using a series of synthetic and real-world images show that the proposed ASCFCM outperforms the competing methodologies, and hence provides an effective unsupervised method for multispectral remotely sensed imagery clustering. [ABSTRACT FROM PUBLISHER]

Atmospheric correction of ocean colour remote-sensing data is based on the assumption that no water-leaving reflectance occurs in the near-infrared (NIR) area. However, this assumption is not valid for highly productive waters. To solve this problem, this paper describes a modified atmospheric correction scheme for Hyperion data. Based on the assumption that the ratio of water-leaving radiance and aerosol radiance in two NIR bands follows a fixed rule, we moved a rectangular box around the imagery to calculate those two parameters, which were then used to replace the assumption of zero water-leaving radiance in the NIR. We applied the new atmospheric correction algorithm to one Hyperion image. Following comparison of in situ measurements to results of the FLAASH atmospheric correction schema, preliminary findings show that the new algorithm is effective in reducing error in retrieved water-leaving radiance values, to some extent. [ABSTRACT FROM PUBLISHER]

Epipolar rectification aims at resampling stereoscopic images so that conjugate points are located along the same horizontal x-axis. For most stereoscopic digital surface model production algorithms, this rectification is a necessary preprocessing task because it allows reducing the 2D matching to a 1D matching problem. Most epipolar rectification algorithms exist in literature and are mainly for a given type of sensor (frame camera or push-broom sensor). In this paper, we present a generic method for epipolar rectification. This means that the method is applicable for both frame and push-broom cameras. The only difference lies in the projection function used to generate epipolar curves. [ABSTRACT FROM AUTHOR]

This paper proposes a new decision fusion method accounting for conditional dependence (correlation) between land-cover classifications from multi-sensor data. The dependence structure between different classification results is calculated and used as weighting parameters for the subsequent fusion scheme. An algorithm for fusion of correlated probabilities (FCP) is adopted to fuse the prior probability, conditional probability, and obtained weighting parameters to generate a posterior probability for each class. A maximum posterior probability rule is then used to combine the posterior probabilities generated for each class to produce the final fusion result. The proposed FCP-based decision fusion method is assessed in land-cover classification over two study areas. The experimental results demonstrate that the proposed decision fusion method outperformed the existing decision fusion methods that do not take into account the correlation or dependence. The proposed decision fusion method can also be applied to other applications with different sensor data. [ABSTRACT FROM PUBLISHER]