Search

In response to the challenges posed by small objects in remote sensing images, such as low resolution, complex backgrounds, and severe occlusions, this paper proposes a lightweight improved model based on YOLOv8n. During the detection of small objects, the feature fusion part of the YOLOv8n algorithm retrieves relatively fewer features of small objects from the backbone network compared to large objects, resulting in low detection accuracy for small objects. To address this issue, firstly, this paper adds a dedicated small object detection layer in the feature fusion network to better integrate the features of small objects into the feature fusion part of the model. Secondly, the SSFF module is introduced to facilitate multi-scale feature fusion, enabling the model to capture more gradient paths and further improve accuracy while reducing model parameters. Finally, the HPANet structure is proposed, replacing the Path Aggregation Network with HPANet. Compared to the original YOLOv8n algorithm, the recognition accuracy of mAP@0.5 on the VisDrone data set and the AI-TOD data set has increased by 14.3% and 17.9%, respectively, while the recognition accuracy of mAP@0.5:0.95 has increased by 17.1% and 19.8%, respectively. The proposed method reduces the parameter count by 33% and the model size by 31.7% compared to the original model. Experimental results demonstrate that the proposed method can quickly and accurately identify small objects in complex backgrounds. [ABSTRACT FROM AUTHOR]

Aiming at the characteristics of remote sensing images such as a complex background, a large number of small targets, and various target scales, this paper presents a remote sensing image target detection algorithm based on improved YOLOv8. First, in order to extract more information about small targets in images, we add an extra detection layer for small targets in the backbone network; second, we propose a C2f-E structure based on the Efficient Multi-Scale Attention Module (EMA) to enhance the network's ability to detect targets of different sizes; and lastly, Wise-IoU is used to replace the CIoU loss function in the original algorithm to improve the robustness of the model. Using our improved algorithm for the detection of multiple target categories in the DOTAv1.0 dataset, the mAP@0.5 value is 82.7%, which is 1.3% higher than that of the original YOLOv8 algorithm. It is proven that the algorithm proposed in this paper can effectively improve target detection accuracy in remote sensing images. [ABSTRACT FROM AUTHOR]

With satellite quantity and quality development in recent years, remote sensing products in vast areas are becoming widely used in more and more fields. The acquisition of large regional images requires the scientific and efficient utilization of satellite resources through imaging satellite task planning technology. However, for imaging satellite task planning in a vast area, a large number of decision variables are introduced into the imaging satellite task planning model, making it difficult for existing optimization algorithms to obtain reliable solutions. This is because the search space of the solution increases the exponential growth with the increase in the number of decision variables, which causes the search performance of optimization algorithms to decrease significantly. This paper proposes a large-scale multi-objective optimization algorithm based on efficient competition learning and improved non-dominated sorting (ECL-INS-LMOA) to efficiently obtain satellite imaging schemes for large areas. ECL-INS-LMOA adopted the idea of two-stage evolution to meet the different needs in different evolutionary stages. In the early stage, the proposed efficient competitive learning particle update strategy (ECLUS) and the improved NSGA-II were run alternately. In the later stage, only the improved NSGA-II was run. The proposed ECLUS guarantees the rapid convergence of ECL-INS-LMOA in the early evolution by accelerating particle update, introducing flight time, and proposing a binary competitive swarm optimizer BCSO. The results of the simulation imaging experiments on five large areas with different scales of decision variables show that ECL-INS-LMOA can always obtain the imaging satellite mission planning scheme with the highest regional coverage and the lowest satellite resource consumption within the limited evaluation times. The experiments verify the excellent performance of ECL-INS-LMOA in solving vast area mapping planning problems. [ABSTRACT FROM AUTHOR]

Remote sensing (RS) scene classification is important for RS imagery semantic interpretation. Although tremendous strides have been made in RS scene classification, one of the remaining open challenges is recognizing RS scenes in low quality variance (e.g., various scales and noises). This paper proposes a deep salient feature based anti-noise transfer network (DSFATN) method that effectively enhances and explores the high-level features for RS scene classification in different scales and noise conditions. In DSFATN, a novel discriminative deep salient feature (DSF) is introduced by saliency-guided DSF extraction, which conducts a patch-based visual saliency (PBVS) algorithm using "visual attention" mechanisms to guide pre-trained CNNs for producing the discriminative high-level features. Then, an anti-noise network is proposed to learn and enhance the robust and anti-noise structure information of RS scene by directly propagating the label information to fully-connected layers. A joint loss is used to minimize the anti-noise network by integrating anti-noise constraint and a softmax classification loss. The proposed network architecture can be easily trained with a limited amount of training data. The experiments conducted on three different scale RS scene datasets show that the DSFATN method has achieved excellent performance and great robustness in different scales and noise conditions. It obtains classification accuracy of 98.25%, 98.46%, and 98.80%, respectively, on the UC Merced Land Use Dataset (UCM), the Google image dataset of SIRI-WHU, and the SAT-6 dataset, advancing the state-of-the-art substantially. [ABSTRACT FROM AUTHOR]

Recent years have witnessed an increased interest towards compression-based methods and their applications to remote sensing, as these have a data-driven and parameter-free approach and can be thus succesfully employed in several applications, especially in image information mining. This paper expands the algorithmic information theory frame, on which these methods are based. On the one hand, algorithms originally defined in the pattern matching domain are reformulated, allowing a better understanding of the available compression-based tools for remote sensing applications. On the other hand, the use of existing compression algorithms is proposed to store satellite images with added semantic value. [ABSTRACT FROM AUTHOR]

Urban functional area (UFA) recognition is one of the most important strategies for achieving sustainable city development. As remote-sensing and social-sensing data sources have increasingly become available, UFA recognition has received a significant amount of attention. Research on UFA recognition that uses a single dataset suffers from a low update frequency or low spatial resolution, while data fusion-based methods are limited in efficiency and accuracy. This paper proposes an integrated model to identify UFA using satellite images and taxi global positioning system (GPS) trajectories in four steps. First, blocks were generated as spatial units in the study area, and the spatiotemporal information entropy of the taxi GPS trajectory (STET) for each block was calculated. Second, a 24-hour time-frequency series was formed based on the pick-up and drop-off points extracted from taxi trajectories and used as the interpretation indicator of the blocks. The K-Means++ and k-Nearest Neighbor (kNN) algorithm were used to identify their social functions. Third, a multilabel classification method based on the residual neural network (MLC-ResNets) and "You Only Look Once" (YOLO) target detection algorithms were used to identify the features of the typical and atypical spatial textures, respectively, of the satellite images in the blocks. The confidence scores of the features of the blocks were categorized by the decision tree algorithm. Fourth, to find the best way to integrate the two sub-models for UFA identification, the 10-fold cross-validation method based on stratified random sampling was applied to determine the most optimal STET thresholds. The results showed that the average accuracy reached 82.0%, with an average kappa of 73.5%—significant improvements over most existing studies. This paper provides new insights into how the advantages of satellite images and taxi trajectories in UFA identification can be fully exploited to support sustainable city management. [ABSTRACT FROM AUTHOR]

Image segmentation plays a significant role in remote sensing image processing. Among numerous segmentation algorithms, the region-merging segmentation algorithm is widely used due to its well-organized structure and outstanding results. Many merging criteria (MC) were designed to improve the accuracy of region-merging segmentation, but each MC has its own shortcomings, which can cause segmentation errors. Segmentation accuracy can be improved by referring to the segmentation results. To achieve this, an approach for detecting and correcting region-merging image segmentation errors is proposed, and then an iterative optimization model is established. The main contributions of this paper are as follows: (1) The conflict types of matching segment pairs are divided into scale-expression conflict (SEC) and region-ownership conflict (ROC), and ROC is more suitable for optimization. (2) An equal-scale local evaluation method was designed to quantify the optimization potential of ROC. (3) A regional anchoring strategy is proposed to preserve the results of the previous iteration optimization. Three QuickBird satellite images of different land-cover types were used for validating the proposed approach. Both unsupervised and supervised evaluation results prove that the proposed approach can effectively improve segmentation accuracy. All explicit and implicit optimization modes are concluded, which further illustrate the stability of the proposed approach. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new approach for sub-pixel co-registration based on Fourier phase correlation combined with the Harris detector. Due to the limitation of the standard phase correlation method to achieve only pixel-level accuracy, another approach is required to reach sub-pixel matching precision. We first applied the Harris corner detector to extract corners from both references and sensed images. Then, we identified their corresponding points using phase correlation between the image pairs. To achieve sub-pixel registration accuracy, two optimization algorithms were used. The effectiveness of the proposed method was tested with very high-resolution (VHR) remote sensing images, including Pleiades satellite images and aerial imagery. Compared with the speeded-up robust features (SURF)-based method, phase correlation with the Blackman window function produced 91% more matches with high reliability. Moreover, the results of the optimization analysis have revealed that Nelder–Mead algorithm performs better than the two-point step size gradient algorithm regarding localization accuracy and computation time. The proposed approach achieves better accuracy than 0.5 pixels and outperforms the speeded-up robust features (SURF)-based method. It can achieve sub-pixel accuracy in the presence of noise and produces large numbers of correct matching points. [ABSTRACT FROM AUTHOR]

Objects in satellite remote sensing image sequences often have large deformations, and the stereo matching of this kind of image is so difficult that the matching rate generally drops. A disparity refinement method is needed to correct and fill the disparity. A method for disparity refinement based on the results of plane segmentation is proposed in this paper. The plane segmentation algorithm includes two steps: Initial segmentation based on mean-shift and alpha-expansion-based energy minimization. According to the results of plane segmentation and fitting, the disparity is refined by filling missed matching regions and removing outliers. The experimental results showed that the proposed plane segmentation method could not only accurately fit the plane in the presence of noise but also approximate the surface by plane combination. After the proposed plane segmentation method was applied to the disparity refinement of remote sensing images, many missed matches were filled, and the elevation errors were reduced. This proved that the proposed algorithm was effective. For difficult evaluations resulting from significant variations in remote sensing images of different satellites, the edge matching rate and the edge matching map are proposed as new stereo matching evaluation and analysis tools. Experiment results showed that they were easy to use, intuitive, and effective. [ABSTRACT FROM AUTHOR]

The use of the spatiotemporal data fusion method as an effective data interpolation method has received extensive attention in remote sensing (RS) academia. The enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM) is one of the most famous spatiotemporal data fusion methods, as it is widely used to generate synthetic data. However, the ESTARFM algorithm uses moving windows with a fixed size to get the information around the central pixel, which hampers the efficiency and precision of spatiotemporal data fusion. In this paper, a modified ESTARFM data fusion algorithm that integrated the surface spatial information via a statistical method was developed. In the modified algorithm, the local variance of pixels around the central one was used as an index to adaptively determine the window size. Satellite images from two regions were acquired by employing the ESTARFM and modified algorithm. Results showed that the images predicted using the modified algorithm obtained more details than ESTARFM, as the frequency of pixels with the absolute difference of mean value of six bands' reflectance between true observed image and predicted between 0 and 0.04 were 78% by ESTARFM and 85% by modified algorithm, respectively. In addition, the efficiency of the modified algorithm improved and the verification test showed the robustness of the modified algorithm. These promising results demonstrated the superiority of the modified algorithm to provide synthetic images compared with ESTARFM. Our research enriches the spatiotemporal data fusion method, and the automatic selection of moving window strategy lays the foundation of automatic processing of spatiotemporal data fusion on a large scale. [ABSTRACT FROM AUTHOR]

Compositing is a fundamental pre-processing for remote sensing images. Landsat series optical satellite images are influenced by cloud coverage, acquisition time, sensor types, and seasons, which make it difficult to obtain continuous cloud-free observations. It limits the potential use and analysis of time series images. Therefore, global change researchers urgently need to 'composite' multi-sensor and multi-temporal images. Many previous studies have used isolated pixel-based algorithms to composite Landsat images; however, this study is different and develops a batch pixel-based algorithm for composing continuous cloud-free Landsat images. The algorithm chooses the best scene as the reference image using the user-specified image ID or related parameters. Further, it accepts all valid pixels in the reference image as the main part of the result and develops a priority coefficient model. Development of this model is based on the criteria of five factors including cloud coverage, acquisition time, acquisition year, observation seasons, and sensor types to select substitutions for the missing pixels in batches and to merge them into the final composition. This proposed batch pixel-based algorithm may provide reasonable compositing results on the basis of the experimental test results of all Landsat 8 images in 2019 and the visualization results of 12 locations in 2020. In comparison with the isolated pixel-based algorithms, our algorithm eliminates band dispersion, requires fewer images, and enhances the composition's pixel concentration considerably. The algorithm provides a complete and practical framework for time series image processing for Landsat series satellites, and has the potential to be applied to other optical satellite images as well. [ABSTRACT FROM AUTHOR]

Atmospheric correction of remote sensing imagery over optically complex waters is still a challenging task. Even algorithms showing a good accuracy for moderate and extremely turbid waters need to be tested when being used for eutrophic inland basins. Such a test was carried out in this study on the example of a Sentinel-3/OLCI image of the productive waters of the Gorky Reservoir during the period of intense blue-green algal bloom using data on the concentration of chlorophyll a and remote sensing reflectance measured from the motorboat at many points of the reservoir. The accuracy of four common atmospheric correction (AC) algorithms was examined. All of them showed unsatisfactory accuracy due to incorrect determination of atmospheric aerosol parameters and aerosol radiance. The calculated aerosol optical depth (AOD) spectra varied widely (AOD(865) = 0.005 − 0.692) even over a small area (up to 10 × 10 km) and correlated with the measured chlorophyll a. As a result, a part of the high water-leaving signal caused by phytoplankton bloom was taken as an atmosphere signal. A significant overestimation of atmospheric aerosol parameters, as a consequence, led to a strong underestimation of the remote sensing reflectance and low accuracy of the considered AC algorithms. To solve this problem, an algorithm with a fixed AOD was proposed. The fixed AOD spectrum was determined in the area with relatively "clean" water as 5 percentiles of AOD in all water pixels. The proposed algorithm made it possible to obtain the remote sensing reflectance with high accuracy. The slopes of linear regression are close to 1 and the intercepts tend to zero in almost all spectral bands. The determination coefficients are more than 0.9; the bias, mean absolute percentage error, and root-mean-square error are notably lower than for other AC algorithms. [ABSTRACT FROM AUTHOR]

An efficient satellite image segmentation method based on a hybrid grasshopper optimization algorithm (GOA) and minimum cross entropy (MCE) is proposed in this paper. The proposal is known as GOA–jDE, and it merges GOA with self-adaptive differential evolution (jDE) to improve the search efficiency, preserving the population diversity especially in the later iterations. A series of experiments is conducted on various satellite images for evaluating the performance of the algorithm. Both low and high levels of the segmentation are taken into account, increasing the dimensionality of the problem. The proposed approach is compared with the standard color image thresholding methods, as well as the advanced satellite image thresholding techniques based on different criteria. Friedman test and Wilcoxon's rank sum test are performed to assess the significant difference between the algorithms. The superiority of the proposed method is illustrated from different aspects, such as average fitness function value, peak signal to noise ratio (PSNR), structural similarity index (SSIM), feature similarity index (FSIM), standard deviation (STD), convergence performance, and computation time. Furthermore, natural images from the Berkeley segmentation dataset are also used to validate the strong robustness of the proposed method. [ABSTRACT FROM AUTHOR]

Automatic building extraction using a single data type, either 2D remotely-sensed images or light detection and ranging 3D point clouds, remains insufficient to accurately delineate building outlines for automatic mapping, despite active research in this area and the significant progress which has been achieved in the past decade. This paper presents an effective approach to extracting buildings from Unmanned Aerial Vehicle (UAV) images through the incorporation of superpixel segmentation and semantic recognition. A framework for building extraction is constructed by jointly using an improved Simple Linear Iterative Clustering (SLIC) algorithm and Multiscale Siamese Convolutional Networks (MSCNs). The SLIC algorithm, improved by additionally imposing a digital surface model for superpixel segmentation, namely 6D-SLIC, is suited for building boundary detection under building and image backgrounds with similar radiometric signatures. The proposed MSCNs, including a feature learning network and a binary decision network, are used to automatically learn a multiscale hierarchical feature representation and detect building objects under various complex backgrounds. In addition, a gamma-transform green leaf index is proposed to truncate vegetation superpixels for further processing to improve the robustness and efficiency of building detection, the Douglas–Peucker algorithm and iterative optimization are used to eliminate jagged details generated from small structures as a result of superpixel segmentation. In the experiments, the UAV datasets, including many buildings in urban and rural areas with irregular shapes and different heights and that are obscured by trees, are collected to evaluate the proposed method. The experimental results based on the qualitative and quantitative measures confirm the effectiveness and high accuracy of the proposed framework relative to the digitized results. The proposed framework performs better than state-of-the-art building extraction methods, given its higher values of recall, precision, and intersection over Union (IoU). [ABSTRACT FROM AUTHOR]

Road network extraction from remote sensing images has played an important role in various areas. However, due to complex imaging conditions and terrain factors, such as occlusion and shades, it is very challenging to extract road networks with complete topology structures. In this paper, we propose a learning-based road network extraction framework via a Multi-supervised Generative Adversarial Network (MsGAN), which is jointly trained by the spectral and topology features of the road network. Such a design makes the network capable of learning how to "guess" the aberrant road cases, which is caused by occlusion and shadow, based on the relationship between the road region and centerline; thus, it is able to provide a road network with integrated topology. Additionally, we also present a sample quality measurement to efficiently generate a large number of training samples with a little human interaction. Through the experiments on images from various satellites and the comprehensive comparisons to state-of-the-art approaches on the public datasets, it is demonstrated that the proposed method is able to provide high-quality results, especially for the completeness of the road network. [ABSTRACT FROM AUTHOR]

Multispectral remote sensing data may contain component images that are heavily corrupted by noise and the pre-filtering (denoising) procedure is often applied to enhance these component images. To do this, one can use reference images—component images having relatively high quality and that are similar to the image subject to pre-filtering. Here, we study the following problems: how to select component images that can be used as references (e.g., for the Sentinel multispectral remote sensing data) and how to perform the actual denoising. We demonstrate that component images of the same resolution as well as component images of a better resolution can be used as references. To provide high efficiency of denoising, reference images have to be transformed using linear or nonlinear transformations. This paper proposes a practical approach to doing this. Examples of denoising tests and real-life images demonstrate high efficiency of the proposed approach. [ABSTRACT FROM AUTHOR]

The traditional mine remote sensing information pre-survey is mainly based on manual interpretation, and interpreters delineate the mine boundary shape. This work is difficult and susceptible to subjective judgment due to the large differences in the characteristics of mining complex within individuals and small differences between individuals. CondInst-VoV and BlendMask-VoV, based on VoVNet-v2, are two improved instance segmentation models proposed to improve the efficiency of mine remote sensing pre-survey and minimize labor expenses. In Hubei Province, China, Gaofen satellite fusion images, true-color satellite images, false-color satellite images, and Tianditu images are gathered to create a Key Open-pit Mine Acquisition Areas (KOMMA) dataset to assess the efficacy of mine detection models. In addition, regional detection was carried out in Daye Town. The result shows that the performance of improved models on the KOMMA dataset exceeds the baseline as well as the verification accuracy of manual interpretation in regional mine detection tasks. In addition, CondInst-VoV has the best performance on Tianditu image, reaching 88.816% in positioning recall and 98.038% in segmentation accuracy. [ABSTRACT FROM AUTHOR]

Scene classification, aiming to identify the land-cover categories of remotely sensed image patches, is now a fundamental task in the remote sensing image analysis field. Deep-learning-model-based algorithms are widely applied in scene classification and achieve remarkable performance, but these high-level methods are computationally expensive and time-consuming. Consequently in this paper, we introduce a knowledge distillation framework, currently a mainstream model compression method, into remote sensing scene classification to improve the performance of smaller and shallower network models. Our knowledge distillation training method makes the high-temperature softmax output of a small and shallow student model match the large and deep teacher model. In our experiments, we evaluate knowledge distillation training method for remote sensing scene classification on four public datasets: AID dataset, UCMerced dataset, NWPU-RESISC dataset, and EuroSAT dataset. Results show that our proposed training method was effective and increased overall accuracy (3% in AID experiments, 5% in UCMerced experiments, 1% in NWPU-RESISC and EuroSAT experiments) for small and shallow models. We further explored the performance of the student model on small and unbalanced datasets. Our findings indicate that knowledge distillation can improve the performance of small network models on datasets with lower spatial resolution images, numerous categories, as well as fewer training samples. [ABSTRACT FROM AUTHOR]

As speckle seriously restricts the applications of remote sensing images in many fields, the ability to efficiently and effectively suppress speckle in a coherent imaging system is indispensable. In order to overcome the over-smoothing problem caused by the speckle suppression algorithm based on classical sparse representation, we propose a non-local speckle suppression algorithm that combines the non-local prior knowledge of the image into the sparse representation. The proposed algorithm first applies shearlet to sparsely represent the input image. We then incorporate the non-local priors as constraints into the image sparse representation de-noising problem. The denoised image is obtained by utilizing an alternating minimization algorithm to solve the corresponding constrained de-noising problem. The experimental results show that the proposed algorithm can not only significantly remove speckle noise, but also improve the visual effect and retain the texture information of the image better. [ABSTRACT FROM AUTHOR]

The accurate monitoring of forest cover and its changes are essential for environmental change research, but current satellite products for forest coverage carry many uncertainties. This study used 30-m Landsat-8 data, and aggregated 1-m GaoFen-2 (GF-2) satellite images to construct the training samples and used multiple machine learning algorithms (MLAs) to estimate the fractional forest cover (FFC) in China's Three North Region (TNR). In this study, multiple MLAs were merged to construct stacked generalization (SG) models based on the idea of SG, and the performances of the MLAs in the FFC estimation were evaluated. The results of the 10-fold cross-validation showed that all non-linear algorithms had a good performance, with an R2 value of greater than 0.8 and a root-mean square error (RMSE) of less than 0.05. In the bagging ensemble, the random forest (RF) (R2 = 0.993, RMSE = 0.020) model performed the best and in the boosting ensemble, the light gradient boosted machine (LGBM) (R2 = 0.992, RMSE = 0.022) performed the best. Although the evaluation index of the RF is slightly better than that of the LGBM, the independent validation results show that the two models have similar performances. The model evaluation results of the independent datasets showed that, in the SG model, the performance of the SG(LGBM) (R2 = 0.991, RMSE = 0.034) was better than that of the single or non-ensemble model. Comparing the FFC estimates of our model with those of existing datasets showed that our model exhibited more forest spatial distribution details and higher accuracy in complex landscapes. Overall, in this study, the method of using high-resolution remote sensing (RS) images to extract samples for FFC estimation is feasible. Our results demonstrate the potential of the ensemble MLAs to map the FFC. The research results also show that among many MALs, the RF algorithm is the most suitable algorithm for estimating FFC, which provides a reference for future research. [ABSTRACT FROM AUTHOR]

The evaluation of remote sensing imagery segmentation results plays an important role in the further image analysis and decision-making. The search for the optimal segmentation method for a particular data set and the suitability of segmentation results for the use in satellite image classification are examples where the proper image segmentation quality assessment can affect the quality of the final result. There is no extensive research related to the assessment of the segmentation effectiveness of the images. The designed objective quality assessment metrics that can be used to assess the quality of the obtained segmentation results usually take into account the subjective features of the human visual system (HVS). A novel approach is used in the article to estimate the effectiveness of satellite image segmentation by relating and determining the correlation between subjective and objective segmentation quality metrics. Pearson's and Spearman's correlation was used for satellite images after applying a k-means++ clustering algorithm based on colour information. Simultaneously, the dataset of the satellite images with ground truth (GT) based on the "DeepGlobe Land Cover Classification Challenge" dataset was constructed for testing three classes of quality metrics for satellite image segmentation. [ABSTRACT FROM AUTHOR]

This study aimed to estimate the discharge in ungauged watersheds. To this end, we herein deviated from the model development methodology of previous studies and used convolution neural network (CNN), a deep training algorithm, and hydrological images. As the CNN model was developed for solving classification issues in general, it is unsuitable for simulating the discharge, which is a continuous variable. Therefore, the fully connected layer of the CNN model was improved. Moreover, images reflecting the hydrological conditions rather than a general photograph were used as input data for the CNN model. Three study areas that have discharge gauged data were set for the model's training and testing. The data from two of the three study areas were used for CNN model training, and the data of the other were used to evaluate model prediction performance. The results of this study demonstrate a moderate predictive success of the discharge of an ungauged watershed using the CNN model and hydrological images. Therefore, it can be suitable as a methodology for the discharge estimation of ungauged watersheds. Simultaneously, it is expected that our methodology can be applied to the field of remote sensing or to the field of real-time discharge simulation using satellite imagery on a global scale or across a wide area. [ABSTRACT FROM AUTHOR]

Accurate and efficient extraction of cultivated land data is of great significance for agricultural resource monitoring and national food security. Deep-learning-based classification of remote-sensing images overcomes the two difficulties of traditional learning methods (e.g., support vector machine (SVM), K-nearest neighbors (KNN), and random forest (RF)) when extracting the cultivated land: (1) the limited performance when extracting the same land-cover type with the high intra-class spectral variation, such as cultivated land with both vegetation and non-vegetation cover, and (2) the limited generalization ability for handling a large dataset to apply the model to different locations. However, the "pooling" process in most deep convolutional networks, which attempts to enlarge the sensing field of the kernel by involving the upscale process, leads to significant detail loss in the output, including the edges, gradients, and image texture details. To solve this problem, in this study we proposed a new end-to-end extraction algorithm, a high-resolution U-Net (HRU-Net), to preserve the image details by improving the skip connection structure and the loss function of the original U-Net. The proposed HRU-Net was tested in Xinjiang Province, China to extract the cultivated land from Landsat Thematic Mapper (TM) images. The result showed that the HRU-Net achieved better performance (Acc: 92.81%; kappa: 0.81; F1-score: 0.90) than the U-Net++ (Acc: 91.74%; kappa: 0.79; F1-score: 0.89), the original U-Net (Acc: 89.83%; kappa: 0.74; F1-score: 0.86), and the Random Forest model (Acc: 76.13%; kappa: 0.48; F1-score: 0.69). The robustness of the proposed model for the intra-class spectral variation and the accuracy of the edge details were also compared, and this showed that the HRU-Net obtained more accurate edge details and had less influence from the intra-class spectral variation. The model proposed in this study can be further applied to other land cover types that have more spectral diversity and require more details of extraction. [ABSTRACT FROM AUTHOR]

Linear dunes and human fingerprints share many characteristics. Both have ridges, valleys, and defects (minutiae) in the form of bifurcations and termination of ridgeline features. For dunes, determining how defects vary across linear and transverse dunefields is critical to understanding the physics of their formative processes and the physical forcing mechanisms that produce dunefields. Unfortunately, manual extraction of defect locations and higher order characteristics (type, orientation, and quality) from remotely sensed imagery is both time-consuming and inconsistent. This problem is further exacerbated when, in the case of imagery from sensors in orbit around Mars, we are unable to field check interpretations. In this research, we apply a novel technique for extracting defects from multiple imagery sources utilizing a robust and well-documented fingerprint minutiae detection and extraction software (MINDTCT: MINutiae DecTeCTion) developed by the National Institute of Standards and Technology (NIST). We apply our 'fingerprinting' approach to Transverse Aeolian Ridges (TARs), relict aeolian features commonly seen on the surface of Mars, whose depositional and formative processes are poorly understood. Our algorithmic approach demonstrates that automating the rapid extraction of defects from orbitally-derived high-resolution imagery of Mars is feasible and produces maps that allow the quantification and analysis of these features. [ABSTRACT FROM AUTHOR]

Land-cover map production using remote-sensing imagery is governed by data availability. In our case, data sources are two-fold: on one hand, optical data provided regularly by satellites such as Sentinel-2, and on the other hand, reference data which allow calibrating mapping methods or validating the results. The lengthy delays due to reference data collection and cleansing are one of the main issues for applications. In this work, the use of Optimal Transport (OT) is proposed. OT is a Domain Adaptation method that uses past data, both images and reference data, to produce the land-cover map of the current period without updated reference data. Seven years of Formosat-2 image time series and the corresponding reference data are used to evaluate two OT algorithms: conventional EMD transport and regularized transport based on the Sinkhorn distance. The contribution of OT to a classification fusion strategy is also evaluated. The results show that with a 17-class nomenclature the problem is too complex for the Sinkhorn algorithm, which provides maps with an Overall Accuracy (OA) of 30%. In contrast, with the EMD algorithm, an OA close to 70% is obtained. One limitation of OT is the number of classes that can be considered at the same time. Simplification schemes are proposed to reduce the number of classes to be transported. Cases of improvement are shown when the problem is simplified, with an improvement in OA varying from 5% and 20%, producing maps with an OA near 79%. As several years are available, the OT approaches are compared to standard fusion schemes, like majority voting. The gain in voting strategies with OT use is lower than the gain obtained with standard majority voting (around 5%). [ABSTRACT FROM AUTHOR]

This work presents an approach to road network extraction in remote sensing images. In our earlier work, we worked on the extraction of the road network using a multi-agent approach guided by Volunteered Geographic Information (VGI). The limitation of this VGI-only approach is its inability to update the new road developments as it only follows the VGI. In this work, we employ a deep learning approach to update the road network to include new road developments not captured by the existing VGI. The output of the first stage is used to train a Convolutional Neural Network (CNN) in the second stage to generate a general model to classify road pixels. Post-processing is used to correct the undesired artifacts such as buildings, vegetation, occlusions, etc. to generate a final road map. Our proposed method is tested on the satellite images acquired over Abu Dhabi, United Arab Emirates and the aerial images acquired over Massachusetts, United States of America, and is observed to produce accurate results. [ABSTRACT FROM AUTHOR]

Coastal land cover classification is a significant yet challenging task in remote sensing because of the complex and fragmented nature of coastal landscapes. However, availability of multitemporal and multisensor remote sensing data provides opportunities to improve classification accuracy. Meanwhile, rapid development of deep learning has achieved astonishing results in computer vision tasks and has also been a popular topic in the field of remote sensing. Nevertheless, designing an effective and concise deep learning model for coastal land cover classification remains problematic. To tackle this issue, we propose a multibranch convolutional neural network (MBCNN) for the fusion of multitemporal and multisensor Sentinel data to improve coastal land cover classification accuracy. The proposed model leverages a series of deformable convolutional neural networks to extract representative features from a single-source dataset. Extracted features are aggregated through an adaptive feature fusion module to predict final land cover categories. Experimental results indicate that the proposed MBCNN shows good performance, with an overall accuracy of 93.78% and a Kappa coefficient of 0.9297. Inclusion of multitemporal data improves accuracy by an average of 6.85%, while multisensor data contributes to 3.24% of accuracy increase. Additionally, the featured fusion module in this study also increases accuracy by about 2% when compared with the feature-stacking method. Results demonstrate that the proposed method can effectively mine and fuse multitemporal and multisource Sentinel data, which improves coastal land cover classification accuracy. [ABSTRACT FROM AUTHOR]

Studies of land surface dynamics in heterogeneous landscapes often require satellite images with a high resolution, both in time and space. However, the design of satellite sensors often inherently limits the availability of such images. Images with high spatial resolution tend to have relatively low temporal resolution, and vice versa. Therefore, fusion of the two types of images provides a useful way to generate data high in both spatial and temporal resolutions. A Bayesian data fusion framework can produce the target high-resolution image based on a rigorous statistical foundation. However, existing Bayesian data fusion algorithms, such as STBDF (spatio-temporal Bayesian data fusion) -I and -II, do not fully incorporate the mixed information contained in low-spatial-resolution pixels, which in turn might limit their fusion ability in heterogeneous landscapes. To enhance the capability of existing STBDF models in handling heterogeneous areas, this study proposes two improved Bayesian data fusion approaches, coined ISTBDF-I and ISTBDF-II, which incorporate an unmixing-based algorithm into the existing STBDF framework. The performance of the proposed algorithms is visually and quantitatively compared with STBDF-II using simulated data and real satellite images. Experimental results show that the proposed algorithms generate improved spatio-temporal-resolution images over STBDF-II, especially in heterogeneous areas. They shed light on the way to further enhance our fusion capability. [ABSTRACT FROM AUTHOR]

The Andes mountain forests are sparse relict populations of tree species that grow in association with local native shrubland species. The identification of forest conditions for conservation in areas such as these is based on remote sensing techniques and classification methods. However, the classification of Andes mountain forests is difficult because of noise in the reflectance data within land cover classes. The noise is the result of variations in terrain illumination resulting from complex topography and the mixture of different land cover types occurring at the sub-pixel level. Considering these issues, the selection of an optimum classification method to obtain accurate results is very important to support conservation activities. We carried out comparative non-parametric statistical analyses on the performance of several classifiers produced by three supervised machine-learning algorithms: Random Forest (RF), Support Vector Machine (SVM), and k-Nearest Neighbor (kNN). The SVM and RF methods were not significantly different in their ability to separate Andes mountain forest and shrubland land cover classes, and their best classifiers showed a significantly better classification accuracy (AUC values 0.81 and 0.79 respectively) than the one produced by the kNN method (AUC value 0.75) because the latter was more sensitive to noisy training data. [ABSTRACT FROM AUTHOR]

Spatial and temporal variations in colored dissolved organic matter (CDOM) are of great importance to understanding the dynamics of the biogeochemical properties of water bodies. This study proposed a remote sensing approach for estimating CDOM concentrations (CCDOM) based on in situ observations from the Bohai Sea (BS) and the North Yellow Sea (NYS). Cross-validation demonstrated that the accuracy of the CDOM algorithm is R2 = 0.78, APD = 15.9%, RMSE = 0.92 (ppb). The CDOM algorithm was applied to estimate the 14-year (2003–2016) sea surface CCDOM in the BS and NYS areas using Moderate Resolution Imaging Spectroradiometer (MODIS) monthly products. The results showed a significant fluctuation in CDOM variations on a long-term scale. The highest values of CDOM were observed in the BS, the middle values were observed in the Bohai Strait, and the lowest values were observed in the NYS. Seasonal variations were observed with long-lasting high CDOM values from June to August in coastal waters, while relatively low values were observed in the NYS in the summer. In the spring and fall, a distinct increase appeared in the NYS. High CDOM values in the nearshore coastal waters were mostly related to terrestrial inputs, while CDOM in the offshore regions was mainly due to autochthonous production. Furthermore, ocean currents played an important role in the variations in CDOM in the BS and NYS areas, especially for variations in CDOM in the Bohai Strait. [ABSTRACT FROM AUTHOR]