Search

Recently, there has been a notable surge of interest in scientific research regarding spectral images. The potential of these images to revolutionize the digital photography industry, like aerial photography through Unmanned Aerial Vehicles (UAVs), has captured considerable attention. One encouraging aspect is their combination with machine learning and deep learning algorithms, which have demonstrated remarkable outcomes in image classification. As a result of this powerful amalgamation, the adoption of spectral images has experienced exponential growth across various domains, with agriculture being one of the prominent beneficiaries. This paper presents an extensive survey encompassing multispectral and hyperspectral images, focusing on their applications for classification challenges in diverse agricultural areas, including plants, grains, fruits, and vegetables. By meticulously examining primary studies, we delve into the specific agricultural domains where multispectral and hyperspectral images have found practical use. Additionally, our attention is directed towards utilizing machine learning techniques for effectively classifying hyperspectral images within the agricultural context. The findings of our investigation reveal that deep learning and support vector machines have emerged as widely employed methods for hyperspectral image classification in agriculture. Nevertheless, we also shed light on the various issues and limitations of working with spectral images. This comprehensive analysis aims to provide valuable insights into the current state of spectral imaging in agriculture and its potential for future advancements. [ABSTRACT FROM AUTHOR]

The use of artificial intelligence has led to an increase in road extraction projects from satellite images through deep learning. However, multi-spectral images (MSI) have been largely overlooked in road extraction algorithms due to their lower resolution compared to panchromatic or fused images. Additionally, deep learning faces the challenge of image content reasoning from distant contexts in data rule mining. To address these issues, we propose a new method for road extraction called the MSI-guided Segmentation Network, which utilizes all the data from the GF2 satellite to achieve optimal results. This study highlights the advantages of using MSI with low-resolution for obtaining deeper semantic information in a faster manner, while high-resolution fused images are better suited for extracting precise characteristics. The proposed method includes two sections: (1) a local symmetry feature fusion to enhance the network's local context-awareness for shallow details, and (2) a global asymmetric semantic fusion to improve the network's capability to comprehend the whole scene for deep semantic information. Moreover, to evaluate the robustness and generalization of this method, we have provided a GF2 Full-band China Road Dataset. The codes and datasets will be made public on https://github.com/Dudujia160918/MSNet. [ABSTRACT FROM AUTHOR]

To extract accurately and quickly the fractional vegetation coverage (FVC) for the case of soybean crops in alpine black-soil regions during flowering-podding and seed-filling growth stages, we use unmanned aerial vehicles (UAVs) to collect multi-spectral images of the soybean crops. Different vegetation indices for the multi-spectral bands are analyzed and compared. These are a vegetative index (VEG), a colour index of vegetation extraction (CIVE), an excessive green-feature index (EXG), an excessive green-and-red difference index (EXGR), a combined vegetation index (CVI), a normalized green-blue difference index (NGBDI), a normalized vegetation index (NDVI), a soil-adjusted vegetation index (SAVI), and a modified soil-adjusted vegetation index (MSAVI). A supervised classification method is combined with a threshold method based on statistical histograms of the vegetation indices. This offers an efficient technique for extracting the soybean coverage in the alpine black soils. We divide our experimental field into soil pixels and soybean pixels, while the UAVbased remote-sensing data is divided into the categories of soil and soybean vegetation, using a supervised classification method. Then intersects of the histograms of the vegetation-indices distributions derived with the UAV data are taken as thresholds for the soil and soybeanvegetation pixels. The soybean FVC extracted from synchronously collected high-resolution visible-light images with the ground resolution 0.036 m is used as a reference value for the comparative analysis of the accuracies. Our study reveals the following: (1) the FVCextraction accuracy becomes higher than 90% if the thresholds of the vegetation indices are determined by the statistical histograms and the images obtained with the UAVs are classified in order to extract the FVC, (2) one obtains too high a coverage with the NGBDI index; the corresponding errors are equal to 6.14% and 2.18% respectively for the flowering-podding and seed-filling stages, (3) the COM, VEG, EXG, SAVI and MSAVI indices demonstrate a sufficient accuracy and reliability, and (4) the EXG index provides the highest precision at the podding stage, while the COM index is the best for the period of soybean-kernel filling. Our results represent an important reference for future high-precision extraction of the soybean-vegetation coverage at different growth stages. [ABSTRACT FROM AUTHOR]

This study delves into the problem of moving object detection in infrared and visible images. While existing approaches primarily focus on single-task detection using single-spectral image data, such as thermal infrared or visible images, they often ignore the differences between different spectral images and the interconnectedness of related tasks such as image fusion and segmentation. To tackle these problems, we present a novel multi-spectral image fusion network with quality and semantic awareness for moving object detection (MOD), particularly in scenarios where ground truth labels for both infrared and visible images are unavailable. Our approach fuses multi-spectral images, incorporating additional subtasks in the image fusion to obtain content and quality perception of infrared and visible images. In addition, we design a novel residual global perception module (RGPM) and multi-spectral fusion loss, which can capture more hidden features and contextual information across various scales. This enhanced capability leads to more precise detection and tracking of moving objects, particularly in challenging situations involving occlusions and dynamic backgrounds. Compared with single-spectral moving object detection optimization, the hurdles of utilizing deep learning for multi-spectral image fusion, e.g., without ground truth labels and harmful noise, are significantly mitigated. Extensive quantitative and qualitative comparative experiments demonstrate its effectiveness, robustness, and superior performance compared to contemporary methods. Concisely, the proposed fusion representation learning has gained 44. 2 % , 31. 2 % , 36. 3 % , 41. 6 % , 5. 3 % , 31. 2 % , 76. 2 % on EI, SF, DF, AG, MI, SD and Nabf metrics compared with the best competitors. • We present a novel multi-spectral image fusion method with quality and semantic awareness. • We propose a global perception model (GPM) to capture multiscale features of source images. • We develop an image fusion network for moving object detection. • We conduct extensive experiments on the publication datasets. [ABSTRACT FROM AUTHOR]

There have been various plant image-based studies for segmentation, deblurring, super-resolution reconstruction, and classification. However, nonlinear motion blur in thermal images was not considered in the existing studies on plant classification. Nonlinear motion blur occurs in images due to camera or plant movements, and it causes the degradation of plant classification accuracy. Moreover, nonlinear motion blur in images gets worse when both camera and plant movements occur simultaneously. In this case, it becomes difficult to recognize plants, and the performance of plant image classification becomes very low. Therefore, to reduce the nonlinear motion blur, a thermal and visible light plant images-based deblurring network (TVPD-Net) is proposed in this study. In addition, a thermal and visible light plant images-based classification network (TVPC-Net) is also proposed to improve the plant classification performance on deblurred images. Experimental results revealed that the proposed TVPD-Net achieved 21.21 and 22.53 of the peak signal-to-noise ratio (PSNR), and 0.726 and 0.737 of the structural similarity index measure (SSIM) on both visible light and thermal plant image datasets which were self-collected, respectively. Moreover, the proposed TVPC-Net with deblurred images by TVPD-Net achieved 92.52 % (top-1 accuracy) and 87.73 % (harmonic mean of precision and recall (F1-score)). In addition, the experimental results on an open dataset named Hyperspectral Flower Dataset (HFD100) revealed that the proposed plant classification method achieved 90.94 % of top-1 accuracy and 86.21 % of F1-score. The accuracies of the proposed methods are greater than those of the state-of-the-art methods. • This is the first study for plant thermal image-based deblurring. • This is the first study of plant thermal and visible images-based classification with motion blur. • We propose TVPD-Net including 10 residual blocks for plant image deblurring. • We propose TVPC-Net including 4 groups of layers for plant image classification. • Proposed TVPD-Net and TVPC-Net with self-collected database are made open via Github site. [ABSTRACT FROM AUTHOR]

The pansharpening is a combination of multispectral (MS) and panchromatic (PAN) images that produce a high-spatial-spectral-resolution MS images. In multiresolution analysis-based pansharpening schemes, some spatial and spectral distortions are found. It can be reduced by adding spatial detail images of the PAN image into MS images. In the convolution neural network- (CNN) based method, the lowpass filter image extracted by the CNN model when MS and PAN images are directly applied into the input. The feature values are very high and reduce the conversion efficiency. In the proposed scheme, bi-dimensional empirical mode decomposition is used to extract the spatial detail information of the PAN image to reduce the feature values of the input. This extracted PAN image information is applied to the CNN to produce the non-linear changes in the image pixels and transformed into the perfect spatial detail image. It identifies the spatial and spectral detail quantity for the proposed scheme and it also varies with the different datasets automatically of the same satellite images. Simulation results in the context of qualitative and quantitative analysis demonstrate the effectiveness of proposed scheme applied on datasets collected by different satellites. [ABSTRACT FROM AUTHOR]

Documenting the inter-annual variability and the long-term trend of the glacier snow line altitude is highly relevant to document the evolution of glacier mass changes. Automatically identifying the snow line on glaciers is challenging; recent developments in machine learning approaches show promise to tackle this issue. This manuscript presents a proof of concept of machine learning approaches applied to multi-spectral images to detect the snow line and quantify its average altitude. The tested approaches include the combination of different image processing and classification methods, and takes into account cast shadows. The efficiency of these approaches is evaluated on mountain glaciers in the European Alps by comparing the results with manually annotated data. Solutions provided by the different approaches are robust when compared to the ground truth's snow lines, with a Pearson's correlation ranging from 79% to 96% depending on the method. However, the tested approaches may fail when snow lines are not continuous or exhibit a strong change of elevation. The major advantage over the state of the art is that the proposed approach does not require one calibration per glacier. [ABSTRACT FROM AUTHOR]

Multi-spectral semantic segmentation has shown great advantages under poor illumination conditions, especially for remote scene understanding of autonomous vehicles, since the thermal image can provide complementary information for RGB image. However, methods to fuse the information from RGB image and thermal image are still under-explored. In this paper, we propose a simple but effective module, add–multiply fusion (AMFuse) for RGB and thermal information fusion, consisting of two simple math operations—addition and multiplication. The addition operation focuses on extracting cross-modal complementary features, while the multiplication operation concentrates on the cross-modal common features. Moreover, the attention module and atrous spatial pyramid pooling (ASPP) modules are also incorporated into our proposed AMFuse modules, to enhance the multi-scale context information. Finally, in the UNet-style encoder–decoder framework, the ResNet model is adopted as the encoder. As for the decoder part, the multi-scale information obtained from our proposed AMFuse modules is hierarchically merged layer-by-layer to restore the feature map resolution for semantic segmentation. The experiments of RGBT multi-spectral semantic segmentation and salient object detection demonstrate the effectiveness of our proposed AMFuse module for fusing the RGB and thermal information. [ABSTRACT FROM AUTHOR]

The development of new sensory and robotic technologies in recent years and the increase in the consumption of organic vegetables have allowed the generation of specific applications around precision agriculture seeking to satisfy market demand. This article analyzes the use and advantages of specific optical sensory systems for data acquisition and processing in precision agriculture for Robotic Fertilization process. The SUREVEG project evaluates the benefits of growing vegetables in rows, using different technological tools like sensors, embedded systems, and robots, for this purpose. A robotic platform has been developed consisting of Laser Sick AG LMS100 × 3, Multispectral, RGB sensors, and a robotic arm equipped with a fertilization system. Tests have been developed with the robotic platform in cabbage and red cabbage crops, information captured with the different sensors, allowed to reconstruct rows crops and extract information for fertilization with the robotic arm. The main advantages of each sensory have been analyzed with an quantitative comparison, based on information provided by each one; such as Normalized Difference Vegetation Index index, RGB Histograms, Point Cloud Clusters). Robot Operating System processes this information to generate trajectory planning with the robotic arm and apply the individual treatment in plants. Main results show that the vegetable characterization has been carried out with an efficiency of 93.1% using Point Cloud processing, while the vegetable detection has obtained an error of 4.6% through RGB images.

Precisely localising solar Active Regions (AR) from multi-spectral images is a challenging but important task in understanding solar activity and its influence on space weather. A main challenge comes from each modality capturing a different location of the 3D objects, as opposed to typical multi-spectral imaging scenarios where all image bands observe the same scene. Thus, we refer to this special multi-spectral scenario as multi-layer. We present a multi-task deep learning framework that exploits the dependencies between image bands to produce 3D AR localisation (segmentation and detection) where different image bands (and physical locations) have their own set of results. Furthermore, to address the difficulty of producing dense AR annotations for training supervised machine learning (ML) algorithms, we adapt a training strategy based on weak labels (i.e. bounding boxes) in a recursive manner. We compare our detection and segmentation stages against baseline approaches for solar image analysis (multi-channel coronal hole detection, SPOCA for ARs) and state-of-the-art deep learning methods (Faster RCNN, U-Net). Additionally, both detection and segmentation stages are quantitatively validated on artificially created data of similar spatial configurations made from annotated multi-modal magnetic resonance images. Our framework achieves an average of 0.72 IoU (segmentation) and 0.90 F1 score (detection) across all modalities, comparing to the best performing baseline methods with scores of 0.53 and 0.58, respectively, on the artificial dataset, and 0.84 F1 score in the AR detection task comparing to baseline of 0.82 F1 score. Our segmentation results are qualitatively validated by an expert on real ARs. [ABSTRACT FROM AUTHOR]

Multi-spectral imaging (MSI) is a novel non-invasive tool for visualizing the entire span of the eye, from the internal limiting membrane to the choroid. However, spatial misalignments can be frequently observed in sequential MSI images because the eye saccade movement is usually faster than the MSI image acquisition speed. Therefore, registering MSI images is necessary for computer-based analysis of retinal degeneration via MSI. In this paper, we propose an early deep learning framework for achieving an accurate registration of MSI images in a group-wise fashion. The framework contains three parts: a template construction based on principal component analysis, a deformation field calculation, and a spatial transformation. The framework is uniquely capable of resolving two key challenges, i.e., the “multi-modal” characteristics in MSI images for the acquisition with different spectra and the requirement of joint registration of the sequential images. Our experimental results demonstrate the superior performance of our framework compared to several representative state-of-the-art techniques in both speed and accuracy.

Documenting the inter-annual variability and the long-term trend of the glacier snow line altitude is highly relevant to document the evolution of glacier mass changes. Automatically identifying the snow line on glaciers is challenging; recent developments in machine learning approaches show promise to tackle this issue. This manuscript presents a proof of concept of machine learning approaches applied to multi-spectral images to detect the snow line and quantify its average altitude. The tested approaches include the combination of different image processing and classification methods, and takes into account cast shadows. The efficiency of these approaches is evaluated on mountain glaciers in the European Alps by comparing the results with manually annotated data. Solutions provided by the different approaches are robust when compared to the ground truth’s snow lines, with a Pearson’s correlation ranging from 79% to 96% depending on the method. However, the tested approaches may fail when snow lines are not continuous or exhibit a strong change of elevation. The major advantage over the state of the art is that the proposed approach does not require one calibration per glacier.

Multi-spectral semantic segmentation has shown great advantages under poor illumination conditions, especially for remote scene understanding of autonomous vehicles, since the thermal image can provide complementary information for RGB image. However, methods to fuse the information from RGB image and thermal image are still under-explored. In this paper, we propose a simple but effective module, add–multiply fusion (AMFuse) for RGB and thermal information fusion, consisting of two simple math operations—addition and multiplication. The addition operation focuses on extracting cross-modal complementary features, while the multiplication operation concentrates on the cross-modal common features. Moreover, the attention module and atrous spatial pyramid pooling (ASPP) modules are also incorporated into our proposed AMFuse modules, to enhance the multi-scale context information. Finally, in the UNet-style encoder–decoder framework, the ResNet model is adopted as the encoder. As for the decoder part, the multi-scale information obtained from our proposed AMFuse modules is hierarchically merged layer-by-layer to restore the feature map resolution for semantic segmentation. The experiments of RGBT multi-spectral semantic segmentation and salient object detection demonstrate the effectiveness of our proposed AMFuse module for fusing the RGB and thermal information.

Multi-spectralimages suffers from out-of-focusblur due to well focused camera at the reference imaging channel. A framework for out-of-focus images de-blurring using texture extraction and modified Fourier transform is proposed. The texture is extracted from the blurred image using region covariance. Fourier transform is modified by modification of guided image (as prior) using L0 gradient projection followed by detail amplification which is used as an input for Fourier transform. For further enhancement, the multi-spectral de-blurred images are smooth, and ringing artifacts are minimized by combining with the textures extracted to ensure maximum edge preservation. Comparison of proposed and existing schemes on different multi-spectral images explains the advantage of the proposed scheme for de-blurring in terms of edge preservation, noise and artifacts removal. [ABSTRACT FROM AUTHOR]

It is of great significance and practical application value to extract land-cover type accurately. However, the input data usually used in classification such as reflectance data or vegetation index are very simple and quantitative remote sensing products are rarely used. In this paper, a multi-spectral land-cover classification method based on deep learning is proposed. Using the excellent detail capture ability of contourlet transform to obtain the potential information to supplement the spectral feature space, combined with deep learning for feature selection and feature extraction, a spectral–texture classification model is constructed. The multi-spectral sensing remote data and field measurement data in Dadukou District of Chongqing, northern Negev, and Changping region of Beijing were used for evaluation. Experiment results show the proposed method can outperform principal component analysis, linear discriminant analysis and neural network, and effectively improve the classification accuracy of multi-spectral images; this method provides a new perspective for land-use classification. [ABSTRACT FROM AUTHOR]

Over the past few years, deep learning algorithms have held immense promise for better multi-spectral (MS) optical remote sensing image (RSI) analysis. Most of the proposed models, based on convolutional neural network (CNN) and fully convolutional network (FCN), have been applied successfully on computer vision images (CVIs). However, there is still a lack of exploration of spectra correlation in MS RSIs. In this study, a deep neural network with a spectrum separable module (DSSM) is proposed for semantic segmentation, which enables the utilization of MS characteristics of RSIs. The experimental results obtained on Zurich and Potsdam datasets prove that the spectrum-separable module (SSM) extracts more informative spectral features, and the proposed approach improves the segmentation accuracy without increasing GPU consumption.

Effectively highlighting multiple changes in the earth surface from multi-temporal remote sensing images is a meaningful but challenging task. In order to reduce costs and ensure the performance, it is advisable to employ a semisupervised strategy to achieve this goal. As a discriminative joint classification task, semisupervised change detection aims to extract useful and discriminative features from a large amount of unlabeled data in addition to limited labeled samples. The discriminator of a well-trained generative adversarial network (GAN) is just right for this. Therefore, in this letter, we proposed a semisupervised GAN-based multiple change detection framework for multi-spectral images. First, the GAN is trained by all data without any prior information. Then, we combine two identical trained discriminators to construct a dual-pipeline joint classifier. Finally, the classifier is fine-tuned by a very small amount of labeled data to detect multiple changes. The superior performance of the proposed model over both real multi-spectral data sets demonstrates its robustness and effectiveness. [ABSTRACT FROM AUTHOR]

Automatic identification of (paved) roads is crucial for applications such as autonomous navigation and urban planning. We use high-resolution aerial images, airborne Lidar, and low-resolution multi-spectral images to perform pixel-wise segmentation of road pixels. We utilize multi-modal data along with binary and multi-class ground truth information to train convolutional neural networks (CNNs) and modify an existing CNN architecture to enable training on the lower resolution multi-spectral images. We propose an ensemble of CNNs, called QuadRoad, which combines the results of four trained CNN models to boost the binary road segmentation accuracy. QuadRoad achieves higher accuracy than existing road segmentation techniques. [ABSTRACT FROM AUTHOR]

Highlights • Tree mortality and liana infestation can be mapped using advanced artificial intelligence techniques. • Deep learning classifiers outperform SVM techniques on final classification accuracies. • Drone base technologies and AI techniques open new doors for remote sensing studies. Abstract Global environmental change leads to the variation in the relative coverage of dead trees, liana-infested and non-liana-infested trees in many tropical forests. Increase in the coverage of lianas had adverse effects on forested ecosystems such as decreasing tree growth rates and increasing tree mortality. This paper proposes a classification framework that integrates unmanned aerial vehicle systems (UAVs)-derived multi-spectral images and a Deep self-encoding network (DSEN) with the goal of monitoring and quantifying the relative coverage of dead trees, liana-infested, and non-liana-infested trees at high spatial scales. Today's UAVs-derived multi-spectral images provide the much necessary high resolution/quality data to monitor ecosystem-level processes at low cost and on demand. On the other hand, DSEN, a state-of-the-art classification approach that uses multiple layers to exploit abstract, invariant features from input data, has been proved to have the ability to acquire excellent results. This new classification framework, implemented at a tropical Dry Forest site in Costa Rica, provided accurate estimations of the relative coverage of dead trees, liana-infested trees, non-liana-infested trees, and non-forests. The approach opens the door to start exploring linkages between a booming UAVS industry and machine learning/Deep learning classifiers. [ABSTRACT FROM AUTHOR]

Abstract The emergence of deep learning applications such as convolutional neural networks (CNNs) have resulted in huge improvements on computer vision applications in a wide variety of fields. However, several works demonstrated that low-quality or noisy data (even including perceptually not visible noises) may have a huge impact on the accuracy of CNN models. Therefore, as inspired by biological perception systems, some recent works proposed the use of recurrent and feedback features in CNNs as an improvement to the existing feed-forward CNNs. These recent works on the integration of recurrence and/or feedback to CNNs mostly tested deep networks on natural scenes with relatively perceptually good resolution color images. In this work, we explored the effectiveness of CNNs with recurrent and feedback features for the solar-power plant classification task on mid-resolution (1 pixel - 30×30 square meters per pixel) multi-spectral satellite images. Experiments show promising results when using top-down signals (especially recurrent and feedback features together) on CNNs for multi-spectral image classification tasks, outperforming the baseline CNN model without any recurrent and feedback structure and other approaches in the literature including deep models. [ABSTRACT FROM AUTHOR]

In the last years, the tremendous progress in image processing and camera technology has reactivated the interest in photogrammetrybased surface mapping. With the advent of Dense Image Matching (DIM), the derivation of height values on a per-pixel basis became feasible, allowing the derivation of Digital Elevation Models (DEM) with a spatial resolution in the range of the ground sampling distance of the aerial images, which is often below 10 cm today. While mapping topography and vegetation constitutes the primary field of application for image based surface reconstruction, multi-spectral images also allow to see through the water surface to the bottom underneath provided sufficient water clarity. In this contribution, the feasibility of through-water dense image matching for mapping shallow water bathymetry using off-the-shelf software is evaluated. In a case study, the SURE software is applied to three different coastal and inland water bodies. After refraction correction, the DIM point clouds and the DEMs derived thereof are compared to concurrently acquired laser bathymetry data. The results confirm the general suitability of through-water dense image matching, but sufficient bottom texture and favorable environmental conditions (clear water, calm water surface) are a preconditions for achieving accurate results. Water depths of up to 5m could be mapped with a mean deviation between laser and trough-water DIM in the dm-range. Image based water depth estimates, however, become unreliable in case of turbid or wavy water and poor bottom texture. [ABSTRACT FROM AUTHOR]

One of the most challenging problems in precision agriculture is to correctly identify and separate crops from the soil. Current precision farming algorithms based on artificially intelligent networks use multi-spectral or hyper-spectral data to derive radiometric indices that guide the operational management of agricultural complexes. Deep learning applications using these big data require sensitive filtering of raw data to effectively drive their hidden layer neural network architectures. Threshold techniques based on the normalized difference vegetation index (NDVI) or other similar metrics are generally used to simplify the development and training of deep learning neural networks. They have the advantage of being natural transformations of hyper-spectral or multi-spectral images that filter the data stream into a neural network, while reducing training requirements and increasing system classification performance. In this paper, to calculate a detailed crop/soil segmentation based on high resolution Digital Surface Model (DSM) data, we propose the redefinition of the radiometric index using a directional mathematical filter. To further refine the analysis, we feed this new radiometric index image of about 3500 × 4500 pixels into a relatively small Convolution Neural Network (CNN) designed for general image pattern recognition at 28 × 28 pixels to evaluate and resolve the vegetation correctly. We show that the result of applying a DSM filter to the NDVI radiometric index before feeding it into a Convolutional Neural Network can potentially improve crop separation hit rate by 65%.

In terms of conventional methods for SAR image and multispectral image fusion can't integrate and reserve good spectral information and spatial resolution at the same time, a new fusion method based on the difference of imaging mechanism of SAR and multispectral images is proposed in this paper. Firstly, the original image is decomposed by Shearlet transform, and the high frequency and low frequency components are obtained respectively. The two components contain different detailed information of the image. Shearlet transform decomposes the image into multi-scale and multi-directional sub-band coefficients, which contain different image features. In addition, Shearlet inverse transform has good image reconstruction capability. And then, according to that the low frequency coefficient and the high frequency coefficient represent different meanings, we design the different fusion rule for them. The fusion rules of low frequency coefficients based on region energy and the high frequency coefficient based on improved pulse coupled neural network are designed. Finally, an information-rich image is obtained by inversing Shearlet transform. Therefore, the fusion results are richer and contain more spatial detail information and spectral information. In order to verify the effectiveness of the proposed method, a test is carried out with data from TerraSAR-X and Landsat5-TM, and the result shows that the proposed method is effective in improving the spatial resolution and keeping more spectral information. Compared with the methods of wavelet transform, contourlet transform, and NSCT transform, this method has a significant improvement in spatial information and spectral information. Cross entropy has a margin of improvement of nearly 100%. The correlation coefficient is higher than 25% increase, and the spectral distortion is better than 40% increase. [ABSTRACT FROM AUTHOR]

In remote sensing image processing, the traditional fusion algorithm is based on the Intensity-Hue-Saturation (IHS) transformation. This method does not take into account the texture or spectrum information, spatial resolution and statistical information of the photos adequately, which leads to spectrum distortion of the image. Although traditional solutions in such application combine manifold methods, the fusion procedure is rather complicated and not suitable for practical operation. In this paper, an improved IHS transformation fusion algorithm based on the local variance weighting scheme is proposed for remote sensing images. In our proposal, firstly, the local variance of the SPOT (which comes from French "Systeme Probatoire d'Observation dela Tarre" and means "earth observing system") image is calculated by using different sliding windows. The optimal window size is then selected with the images being normalized with the optimal window local variance. Secondly, the power exponent is chosen as the mapping function, and the local variance is used to obtain the weight of the I component and match SPOT images. Then we obtain the I' component with the weight, the I component and the matched SPOT images. Finally, the final fusion image is obtained by the inverse Intensity-Hue-Saturation transformation of the I', H and S components. The proposed algorithm has been tested and compared with some other image fusion methods well known in the literature. Simulation result indicates that the proposed algorithm could obtain a superior fused image based on quantitative fusion evaluation indices. [ABSTRACT FROM AUTHOR]

After decades of mining and industrialization in Qatar, it is important to estimate their impact on soil pollution with toxic metals. The study utilized 300 topsoil (0-30 cm) samples, multi-spectral images (Landsat 8), spectral indices and environmental variables to model and map the spatial distribution of arsenic (As), chromium (Cr), nickel (Ni), copper (Cu), lead (Pb) and zinc (Zn) in Qatari soils. The prediction model used condition-based rules generated in the Cubist tool. In terms of R2 and the ratio of performance to interquartile distance (RPIQ), the models showed good predictive capabilities for all elements. Of all of the prediction results, Cu had the highest R2 = 0.74, followed by As > Pb > Cr > Zn > Ni. This study found that all of the models only chose images from January and February as predictors, which indicates that images from these two months are important for soil toxic metals' monitoring in arid soils, due to the climate and the vegetation cover during this season. Topsoil maps of the six toxic metals were generated. The maps can be used to prioritize the choice of remediation measures and can be applied to other arid areas of similar environmental/socio-economic conditions and pollution causes. [ABSTRACT FROM AUTHOR]

The Social-Spider Optimization (SSO) is one of the recently developed swarm intelligence. It is inspired from the social behavior of spiders living in huge colonies. In this manuscript, a parallel version of this algorithm is formulated and termed as P-SSO by making a position update process of spiders (female, dominant and non-dominant male) running simultaneously. Simulation studies on cluster analysis of benchmark high-dimensional datasets using proposed P-SSO are found to be nearly 10 times computationally faster than the original version of SSO. Comparative analysis with other standard parallel version algorithms like Adaptive Parallel Particle Swarm Optimization (PPSO), Real Coded Parallel Genetic Algorithm (RCPGA) and K-means reveals the superior clustering accuracy of the proposed method. The designed algorithm is also tested on real life application where multi-spectral image segmentation is formulated as a clustering problem. The images are taken from NASA landsat 8. It covers an area of 200 km of Northwest Chennai obtained before and after flood conditions. This is done to analyze the flood severity. The overall accuracy of P-SSO is highest among all the methods. Also, in case of detection of water flooded areas the producer's accuracy is 76.89% which is two times better than K-means. [ABSTRACT FROM AUTHOR]

Permanganate index as one of the most important water quality parameters is usually used to evaluate the oxygen of water and help control the water pollution. Multi-spectral imaging technology combined with BP neural network instead of traditional methods used to measure permanganate index have the following advantages of high speed, high spatial resolution and without requiring reagent. To demonstrate the effectiveness of this method, the multi-spectral images of Hongze lake acquired by Landsat 8 (TM) and the corresponding measured water quality data (permanganate value, for example) were used to build BP neural network model. The BPNN consist of in three layers the input layer with 7 neurons presenting 7 spectral band, hidden layer with 10 neuron, and output layer with one neuron present Permanganate index. To validate the proposed model a totally of 53 samples were collected and onto 75 % (40 samples) were used as training dataset and the rest 25 % (13 samples) for testing. The cross-validation shown that the slopes of the fitted curve between the predicted value and measured value were higher than 0.89 with R2 higher than 0.74382. The left 13 samples were used to validate the model. The results shown that the slope of the fitted curve between the predicted value and measured value with this model was 0.8483 with R2 of 0.7412 and 0.8086. All these results demonstrated that multi-spectral images combined with BP neural network algorithm is effective to monitor water quality. [ABSTRACT FROM AUTHOR]

After decades of mining and industrialization in Qatar, it is important to estimate their impact on soil pollution with toxic metals. The study utilized 300 topsoil (0–30 cm) samples, multi-spectral images (Landsat 8), spectral indices and environmental variables to model and map the spatial distribution of arsenic (As), chromium (Cr), nickel (Ni), copper (Cu), lead (Pb) and zinc (Zn) in Qatari soils. The prediction model used condition-based rules generated in the Cubist tool. In terms of R2 and the ratio of performance to interquartile distance (RPIQ), the models showed good predictive capabilities for all elements. Of all of the prediction results, Cu had the highest R2 = 0.74, followed by As > Pb > Cr > Zn > Ni. This study found that all of the models only chose images from January and February as predictors, which indicates that images from these two months are important for soil toxic metals’ monitoring in arid soils, due to the climate and the vegetation cover during this season. Topsoil maps of the six toxic metals were generated. The maps can be used to prioritize the choice of remediation measures and can be applied to other arid areas of similar environmental/socio-economic conditions and pollution causes.

An earthquake, 7.2° moment magnitude, occurred on April 4, 2010. Its epicenter was located in southern Cucapa Range, Northern Baja California Peninsula, Mexico, in the confluence of a set of active tectonic faults. Two additional hazards after the earthquake affected population: subsidence and liquefaction. Farmer communities and agriculture lands located in southern Mexicali City were flooded due to the liquefaction phenomenon. Great volumes of fine sediments and water sprouted in different points, flooding agricultural lands and some small communities. The fault displacement during the earthquake damaged roads and buildings. Land subsidence was observed in some areas. More than 35,000 inhabitants and 60,000 ha of agricultural lands were affected. To analyze the consequences of such an earthquake, two multi-spectral and two panchromatic Spot images (before and after the earthquake) were acquired by means of the National Commission of Water, the Mexican Government Water Agency. In addition to these optical images, three interferometric pairs from Envisat/Asar radar sensor were acquired on the grounds of the project C1P6926 with the European Space Agency (ESA). A red, green, blue (RGB) false color composite of the multi-spectral images, before and after the earthquake, shows the inundated areas caused by the liquefaction phenomenon. The two panchromatic images form a stereoscopic pair. These images were integrated into multi-spectral images to derive the texture relief caused by the liquefaction phenomenon. An interferometric analysis was applied to the three interferometric pairs. The coherence images and the digital elevation model (DEM) were calculated as well. The interferometry, the amplitude and the DEM were overlaid. This overlay shows subsidence occurrence in the area of study due to the earthquake. From results and field data, it was possible to identify subsidence-affected areas as well as flooded areas due to the liquefaction phenomenon. [ABSTRACT FROM AUTHOR]

An unmanned aerial vehicle (' VIPtero') was assembled and tested with the aim of developing a flexible and powerful tool for site-specific vineyard management. The system comprised a six-rotor aerial platform capable of flying autonomously to a predetermined point in space, and of a pitch and roll compensated multi-spectral camera for vegetation canopy reflectance recording. Before the flight campaign, the camera accuracy was evaluated against high resolution ground-based measurements, made with a field spectrometer. Then, ' VIPtero' performed the flight in an experimental vineyard in Central Italy, acquiring 63 multi-spectral images during 10 min of flight completed almost autonomously. Images were analysed and classified vigour maps were produced based on normalized difference vegetation index. The resulting vigour maps showed clearly crop heterogeneity conditions, in good agreement with ground-based observations. The system provided very promising results that encourage its development as a tool for precision agriculture application in small crops. [ABSTRACT FROM AUTHOR]

This paper presents a comparison of dimension reduction methods based on a novel machine vision application for estimating moisture content in sand used to make concrete. For the application in question it is very important to know the moisture content of the sand so as to ensure good-quality concrete. In order to achieve a continuous in-line approach for the concrete mixing, digital image analysis is used. Multi-spectral images, consisting of nine spectral bands in the visible and near infrared (NIR) range, were acquired. Each image consists of approximately 9 million pixels. Five different sand types were examined with 20-60 images for each type. To reduce the amount of data, features were extracted from the multi-spectral images; the features were summary statistics on single bands and pairs of bands as well as morphological summaries. The number of features (2,016) is high in relation to the number of observations and, therefore, dimension reductive methods are needed. Furthermore, speed, which is an important consideration, is aided by the use of a small number of variables. On top of that, fewer dimensions tend to give more robust results. Two traditional statistical methods for dimension reduction (forward selection and principal components) combined with ordinary least squares and one sophisticated chemometrics algorithm (genetic algorithm-partial least squares) are compared to the recently proposed least angle regression-elastic net (LARS-EN) model selection method. [ABSTRACT FROM AUTHOR]

The fusion of images is an important technique within many disparate fields such as remote sensing, robotics and medical applications. For image fusion, selecting the required region from input images is a vital task. Recently, wavelet-based fusion techniques have been effectively used to integrate the perceptually important information generated by different imaging systems about the same scene. In this paper, a modified wavelet-based region level fusion algorithm for multi-spectral and multi-focus images is discussed. Here, the low frequency sub-bands are combined, not averaged, based on the edge information present in the high frequency sub-bands, so that the blur in fused image can be eliminated. The absolute mean and standard deviation of each image patch over 3 × 3 window in the high-frequency sub-bands are computed as activity measurement and are used to integrate the approximation band. The performance of the proposed algorithm is evaluated using the entropy, fusion symmetry and peak signal-to-noise ratio and is compared with recently published results. The experimental result proves that the proposed algorithm performs better in many applications. [ABSTRACT FROM AUTHOR]

Over the past few years, deep learning algorithms have held immense promise for better multi-spectral (MS) optical remote sensing image (RSI) analysis. Most of the proposed models, based on convolutional neural network (CNN) and fully convolutional network (FCN), have been applied successfully on computer vision images (CVIs). However, there is still a lack of exploration of spectra correlation in MS RSIs. In this study, a deep neural network with a spectrum separable module (DSSM) is proposed for semantic segmentation, which enables the utilization of MS characteristics of RSIs. The experimental results obtained on Zurich and Potsdam datasets prove that the spectrum-separable module (SSM) extracts more informative spectral features, and the proposed approach improves the segmentation accuracy without increasing GPU consumption. [ABSTRACT FROM AUTHOR]