Gabriel Dauphin | Université Sorbonne Paris Nord / Sorbonne Paris Nord University (original) (raw)
Papers by Gabriel Dauphin
2021 IEEE International Conference on Image Processing (ICIP), 2021
The objective of this paper is to investigate techniques for learning Fully Connected Network (FC... more The objective of this paper is to investigate techniques for learning Fully Connected Network (FCN) models in a lifting based image coding scheme. More precisely, based on a 2D non separable lifting structure composed of three FCN-based prediction stages followed by an FCN-based update one, we first propose to resort to an p loss function, with p ∈ {1, 2}, to learn the three FCN prediction models. While the latter are separately learned in the first approach, a novel joint learning approach is then developed by minimizing a weighted p loss function related to the global prediction error. Experimental results, carried out on the standard Challenge Learned Image Compression (CLIC) dataset, show the benefits of the proposed techniques in terms of rate-distortion performance.
Symmetry
Object detection and tracking has always been one of the important research directions in compute... more Object detection and tracking has always been one of the important research directions in computer vision. The purpose is to determine whether the object is contained in the input image and enclose the object with a bounding box. However, most object detection and tracking methods are applied to daytime objects, and the processing of nighttime objects is imprecise. In this paper, a spectral-spatial feature enhancement algorithm for nighttime object detection and tracking is proposed, which is inspired by symmetrical neural networks. The proposed method consists of the following steps. First, preprocessing is performed on unlabeled nighttime images, including low-light enhancement, object detection, and dynamic programming. Second, object features for daytime and nighttime times are extracted and modulated with a domain-adaptive structure. Third, the Siamese network can make full use of daytime and nighttime object features, which is trained as a tracker by the above images. Fourth, ...
IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Remote sensing image change detection is the key technology for monitoring forest windfall damage... more Remote sensing image change detection is the key technology for monitoring forest windfall damages. A genetic algorithm (GA) is a branch of intelligent optimization techniques available to contribute to the surveys of windstorm and wildfire detection in forest areas. However, traditional GAs remain challenging due to several issues, such as complex calculation, poor noise immunity, and slow convergence. Analysis at the spatial level allows classifications to utilize the contextual and hierarchical information of image objects in addition to solely using spectral information. In addition, ensemble learning presents a possibility for improving classification accuracy. Ensemble classifiers combined with the spatial-based GA offers a promising method [ensemble spatial-spectral genetic algorithm (E-nGA)] for automating the process of monitoring forest loss. The research in this article is presented in four parts. First, block-matching and 3-D filtering is performed to suppress noises while enhancing valuable information. The difference image is, then, generated using the image difference method. Afterward, context-based saliency detection and fuzzy c-means algorithm are conducted on the difference image to reduce the search space. Finally, the proposed E-nGA is executed to further classify the pixels and produce the final change map. Our first proposition is to design improved genetic operators in the GA, relying not only on pixel values but also on spatial information. Our second proposition is to consider an ensemble classification model based on multiple vegetation features for decision integration. Six frequently used classification methods, as well as the simple GA, are executed to demonstrate the effectiveness of the proposed framework in improving the robustness and detection accuracy.
Computers and Electronics in Agriculture
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, 2020
Convolutional neural networks (CNN) can automatically learn features from the hyperspectral image... more Convolutional neural networks (CNN) can automatically learn features from the hyperspectral image data, which could avoid the difficulty of manually extracting features. However, the number of training set for the classification of hyperspectral images is always limited, making it difficult for CNN to obtain effective features and resulting in low classification accuracy. In this paper, a spectral-spatial feature (SSF) extraction based CNN method is proposed for an accurate classification with a small training set. Experimental results based on two standard hyperspectral images demonstrate the effectiveness of the proposed method.
Sensors, 2020
Real-world datasets are often contaminated with label noise; labeling is not a clear-cut process ... more Real-world datasets are often contaminated with label noise; labeling is not a clear-cut process and reliable methods tend to be expensive or time-consuming. Depending on the learning technique used, such label noise is potentially harmful, requiring an increased size of the training set, making the trained model more complex and more prone to overfitting and yielding less accurate prediction. This work proposes a cleaning technique called the ensemble method based on the noise detection metric (ENDM). From the corrupted training set, an ensemble classifier is first learned and used to derive four metrics assessing the likelihood for a sample to be mislabeled. For each metric, three thresholds are set to maximize the classifying performance on a corrupted validation dataset when using three different ensemble classifiers, namely Bagging, AdaBoost and k-nearest neighbor (k-NN). These thresholds are used to identify and then either remove or correct the corrupted samples. The effectiv...
2019 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), 2019
This paper focuses on the disparity-compensated stereoscopic image coding. Such approach takes ad... more This paper focuses on the disparity-compensated stereoscopic image coding. Such approach takes advantage of the existing redundancy between the two views as they are intended to render the visual impression of a 3D-scene, in which interview object displacements are understood as depthrelated information. The classical approach is based on Block Matching (BM) algorithm, yielding a disparity map with which the predicted image is most similar to its original version. Then, with no modification of the disparity map, the residual image is encoded, yielding a refinement added to the predicted image. The proposed approach, first, improves all the possible predicted images taking into account this refinement, and then, estimates the disparity map as the one with which the predicted image resembles most that same view. Despite the significant increase in the numerical complexity, the substantial improved performance in terms of Peak-Signal to Noise-Ratio (PSNR) of this new approach is evidence of ongoing progress in this field of research.
Remote Sensing, 2021
The fusion of the hyperspectral image (HSI) and the light detecting and ranging (LiDAR) data has ... more The fusion of the hyperspectral image (HSI) and the light detecting and ranging (LiDAR) data has a wide range of applications. This paper proposes a novel feature fusion method for urban area classification, namely the relative total variation structure analysis (RTVSA), to combine various features derived from HSI and LiDAR data. In the feature extraction stage, a variety of high-performance methods including the extended multi-attribute profile, Gabor filter, and local binary pattern are used to extract the features of the input data. The relative total variation is then applied to remove useless texture information of the processed data. Finally, nonparametric weighted feature extraction is adopted to reduce the dimensions. Random forest and convolutional neural networks are utilized to evaluate the fusion images. Experiments conducted on two urban Houston University datasets (including Houston 2012 and the training portion of Houston 2017) demonstrate that the proposed method ca...
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, 2020
The presence of noise is often unavoidable and has been a serious nuisance factor that needs to b... more The presence of noise is often unavoidable and has been a serious nuisance factor that needs to be taken into account in the hyperspectral image classification. Effective noise handling is one of the most difficult problems in data classification. Ensemble-based filtering has been demonstrated successful in dealing with the class noise problem. In this paper, a novel two-step ensemble-based data filtering method is proposed to improve the hyperspectral image classification accuracy in the presence of class noise. The proposed method is a combination of noise redundancy classifiers and sensitive algorithms. The experimental results on two public hyperspectral datasets demonstrate the effectiveness of the proposed approach.
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2021
In this paper, a novel Synthetic Minority Oversampling Technique based Deep Rotation Forest(SMOTE... more In this paper, a novel Synthetic Minority Oversampling Technique based Deep Rotation Forest(SMOTE-DRoF) algorithm is proposed for the classification of imbalanced hyperspectral image data. It builds a multi -level forests cascade model by training a balanced dataset generated by SMOTE. In this model, each level of the random forest produces misclassification information of the data which are used as guidance information to adjust the sample weight adaptively for the next level. Experiment results on the hyperspectral image Indian Pines AVRIS and University of Pavia ROSIS demonstrate that the proposed method can get better performance than support vector machine, random forest, rotation forest, SMOTE combined random forest, and SMOTE combined rotation forest in imbalance learning.
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2021
The fusion of hyperspectral image (HSI) and light detection and ranging (LiDAR) data can provide ... more The fusion of hyperspectral image (HSI) and light detection and ranging (LiDAR) data can provide complementary information and improve the accuracy of land cover classification. In this paper, a novel fusion method is proposed to fuse the HSI and LiDAR dataset based on multi-scale feature extraction and total variation. In the method, the extended multi-attribute profile (EMAP) is utilized to automatically extract structural information from HSI and LiDAR elements. The extracted features are then estimated in a lower-dimensional space by multi-scale total variation (MSTV). Finally, the classification map is generated by applying random forest classifiers on the fused data. In the experiment, the performance of the proposed method is evaluated on an urban dataset of Houston. The results demonstrate that classification accuracy could be significantly improved by the proposed method compared with other methods.
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2021
Convolution neural network (CNN) has been successfully applied to hyperspectral image classificat... more Convolution neural network (CNN) has been successfully applied to hyperspectral image classification. However, multiclass imbalance is a major problem in the classification of hyper spectral images, and traditional CNN can hardly improve the accuracy of minority classes effectively. In this paper, a new ensemble CNN with enhanced feature subspaces (ECNN-EFSs) algorithm is proposed, which utilizes an imbalanced training set to train the model and achieves accurate classification. Experimental results on two common hyperspectral datasets show that the proposed algorithm outperforms the traditional CNN and ensemble CNN algorithms.
Remote Sensing, 2020
The fusion of multi-spectral and synthetic aperture radar (SAR) images could retain the advantage... more The fusion of multi-spectral and synthetic aperture radar (SAR) images could retain the advantages of each data, hence benefiting accurate land cover classification. However, some current image fusion methods face the challenge of producing unexpected noise. To overcome the aforementioned problem, this paper proposes a novel fusion method based on weighted median filter and Gram–Schmidt transform. In the proposed method, Sentinel-2A images and GF-3 images are respectively subjected to different preprocessing processes. Since weighted median filter does not strongly blur edges while filtering, it is applied to Sentinel-2A images for reducing noise. The processed Sentinel images are then transformed by Gram–Schmidt with GF-3 images. Two popular methods, principal component analysis method and traditional Gram–Schmidt transform, are used as the comparison methods in the experiment. In addition, random forest, a powerful ensemble model, is adopted as the land cover classifier due to its...
Information Sciences, 2021
Abstract In this paper, an adaptive semi-supervised rotation forest (SSRoF) algorithm is proposed... more Abstract In this paper, an adaptive semi-supervised rotation forest (SSRoF) algorithm is proposed for the classification of hyperspectral images with limited training data. Our proposition is based on Rotation Forest (RoF), a classifying technique that has proved to be remarkably accurate in the context of high-dimensional data. It is adapted to the semi-supervised context, by increasing the number of training instances in the learning stage, with high-quality unlabeled samples mined using ensemble margin. SMOTE is adopted to overcome the class imbalance problem. Out-Of-Bag (OOB) instances are used in a second phase to figure out the optimal number of samples to be added to the training set. Five ensemble methods and five semi-supervised methods are employed as comparisons. The results on three real hyperspectral remote sensing datasets demonstrate the effectiveness of the proposed method.
Remote Sensing, 2020
Remote sensing images classification is the key technology for monitoring forest changes. Texture... more Remote sensing images classification is the key technology for monitoring forest changes. Texture features have been demonstrated to have better effectiveness than spectral features in the improvement of the classification accuracy. The accuracy of extracting texture information by window-based method depends on the choice of the window size. Moreover, the size should ideally match the spatial scale of the object or class under consideration. However, most of the existing texture feature extraction methods are all based on a single window and do not adequately consider the scale of different objects. Our first proposition is to use a composite window for extracting texture features, which is a small window surrounded by a larger window. Our second proposition is to reinforce the performance of the trained ensemble classifier by training it using only the most important features. Considering the advantages of random forest classifier, such as fast training speed and few parameters, t...
Signal, Image and Video Processing, 2020
A stereoscopic image consists of two views rendering a depth sense. Indeed each eye is constraine... more A stereoscopic image consists of two views rendering a depth sense. Indeed each eye is constrained to look at one view, and the small objects displacements across the two views are interpreted as an indication of depth. These displacements are exploited as specific interview redundancies from a compression viewpoint. The classical still compression scheme, called disparity-compensated compression scheme, compresses one view independently of the second view, and a blockbased disparity map modeling the displacements is losslessly compressed. The difference between the original view and its disparity predicted view is then compressed and used by the decoder to compute the compensated view to improve the disparity predicted view. However, a proof of concept work has already shown that selecting disparities according to the compensated view, instead of the predicted view, yields increased rate-distortion performance. This paper derives from the JPEG-coder, a disparity-dependent analytic expression of the distortion induced by the compensated view. This expression is embedded into an algorithm with a reasonable numerical complexity approaching the performance obtained with the proof of concept work. The proposed algorithm, called fast disparity-compensated block matching algorithm, provides at the same bitrate an average performance increase as compared to the classical stereoscopic image coding schemes.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019
Rotation forest (RoF) is a powerful ensemble classifier and has attracted substantial attention d... more Rotation forest (RoF) is a powerful ensemble classifier and has attracted substantial attention due to its performance in hyperspectral data classification. Multi-class imbalance learning is one of the biggest challenges in machine learning and remote sensing. The standard technique for constructing RoF ensemble tends to increase the overall accuracy; RoF has difficulty to sufficiently recognize the minority class. This paper proposes a novel dynamic SMOTE (synthetic minority oversampling technique)-based RoF algorithm for the multi-class imbalance problem. The main idea of the proposed method is to dynamically balance the class distribution before building each rotation decision tree. A resampling rate is set in each iteration (ranging from 10% in the first iteration to 100% in the last) and this ratio defines the number of minority class instances randomly resampled (with replacement) from the original dataset in each iteration. The rest of the minority class instances are generated by the SMOTE method. The reported results on three real hyperspectral datasets show that the proposed method can get better performance than random forest, RoF, and some popular data sampling methods. Elementary particle exchange interactions Micromotors Zirconium Product life cycle management Construction. Military vehicles Associative processing Geophysics Dendrites (neurons) Heart valves. Ion beams Biological cells Adsorption Occupational stress Stripline External stimuli Costing Continents Biomedical optical imaging SMOS mission Biomedical microelectromechanical systems Structural beams Document delivery Google.
2015 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2015
This paper deals with the disparity map estimation problem to encode non-rectified stereoscopic i... more This paper deals with the disparity map estimation problem to encode non-rectified stereoscopic images. This encoding issue is considered as a trade-off between the quality of the predicted view and the bit-rate required to encode the estimated disparity map. A sub-optimal optimization algorithm, known as Modified-M-Algorithm, based on an entropy-distortion metric has already been proposed specifically for rectified stereoscopic images. Indeed the selected disparities reduce not only the distortion of the predicted image but also the entropy of the estimated disparity map under a low computational complexity. An extension of this strategy is proposed to non-rectified stereoscopic images. Simulation results confirm that our extended algorithm still achieves better rate-distortion performance than the traditional block-matching algorithm. Moreover an improvement in terms of rate-distortion performance is also observed even in the case of rectified stereoscopic images.
2021 IEEE International Conference on Image Processing (ICIP), 2021
The objective of this paper is to investigate techniques for learning Fully Connected Network (FC... more The objective of this paper is to investigate techniques for learning Fully Connected Network (FCN) models in a lifting based image coding scheme. More precisely, based on a 2D non separable lifting structure composed of three FCN-based prediction stages followed by an FCN-based update one, we first propose to resort to an p loss function, with p ∈ {1, 2}, to learn the three FCN prediction models. While the latter are separately learned in the first approach, a novel joint learning approach is then developed by minimizing a weighted p loss function related to the global prediction error. Experimental results, carried out on the standard Challenge Learned Image Compression (CLIC) dataset, show the benefits of the proposed techniques in terms of rate-distortion performance.
Symmetry
Object detection and tracking has always been one of the important research directions in compute... more Object detection and tracking has always been one of the important research directions in computer vision. The purpose is to determine whether the object is contained in the input image and enclose the object with a bounding box. However, most object detection and tracking methods are applied to daytime objects, and the processing of nighttime objects is imprecise. In this paper, a spectral-spatial feature enhancement algorithm for nighttime object detection and tracking is proposed, which is inspired by symmetrical neural networks. The proposed method consists of the following steps. First, preprocessing is performed on unlabeled nighttime images, including low-light enhancement, object detection, and dynamic programming. Second, object features for daytime and nighttime times are extracted and modulated with a domain-adaptive structure. Third, the Siamese network can make full use of daytime and nighttime object features, which is trained as a tracker by the above images. Fourth, ...
IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Remote sensing image change detection is the key technology for monitoring forest windfall damage... more Remote sensing image change detection is the key technology for monitoring forest windfall damages. A genetic algorithm (GA) is a branch of intelligent optimization techniques available to contribute to the surveys of windstorm and wildfire detection in forest areas. However, traditional GAs remain challenging due to several issues, such as complex calculation, poor noise immunity, and slow convergence. Analysis at the spatial level allows classifications to utilize the contextual and hierarchical information of image objects in addition to solely using spectral information. In addition, ensemble learning presents a possibility for improving classification accuracy. Ensemble classifiers combined with the spatial-based GA offers a promising method [ensemble spatial-spectral genetic algorithm (E-nGA)] for automating the process of monitoring forest loss. The research in this article is presented in four parts. First, block-matching and 3-D filtering is performed to suppress noises while enhancing valuable information. The difference image is, then, generated using the image difference method. Afterward, context-based saliency detection and fuzzy c-means algorithm are conducted on the difference image to reduce the search space. Finally, the proposed E-nGA is executed to further classify the pixels and produce the final change map. Our first proposition is to design improved genetic operators in the GA, relying not only on pixel values but also on spatial information. Our second proposition is to consider an ensemble classification model based on multiple vegetation features for decision integration. Six frequently used classification methods, as well as the simple GA, are executed to demonstrate the effectiveness of the proposed framework in improving the robustness and detection accuracy.
Computers and Electronics in Agriculture
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, 2020
Convolutional neural networks (CNN) can automatically learn features from the hyperspectral image... more Convolutional neural networks (CNN) can automatically learn features from the hyperspectral image data, which could avoid the difficulty of manually extracting features. However, the number of training set for the classification of hyperspectral images is always limited, making it difficult for CNN to obtain effective features and resulting in low classification accuracy. In this paper, a spectral-spatial feature (SSF) extraction based CNN method is proposed for an accurate classification with a small training set. Experimental results based on two standard hyperspectral images demonstrate the effectiveness of the proposed method.
Sensors, 2020
Real-world datasets are often contaminated with label noise; labeling is not a clear-cut process ... more Real-world datasets are often contaminated with label noise; labeling is not a clear-cut process and reliable methods tend to be expensive or time-consuming. Depending on the learning technique used, such label noise is potentially harmful, requiring an increased size of the training set, making the trained model more complex and more prone to overfitting and yielding less accurate prediction. This work proposes a cleaning technique called the ensemble method based on the noise detection metric (ENDM). From the corrupted training set, an ensemble classifier is first learned and used to derive four metrics assessing the likelihood for a sample to be mislabeled. For each metric, three thresholds are set to maximize the classifying performance on a corrupted validation dataset when using three different ensemble classifiers, namely Bagging, AdaBoost and k-nearest neighbor (k-NN). These thresholds are used to identify and then either remove or correct the corrupted samples. The effectiv...
2019 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA), 2019
This paper focuses on the disparity-compensated stereoscopic image coding. Such approach takes ad... more This paper focuses on the disparity-compensated stereoscopic image coding. Such approach takes advantage of the existing redundancy between the two views as they are intended to render the visual impression of a 3D-scene, in which interview object displacements are understood as depthrelated information. The classical approach is based on Block Matching (BM) algorithm, yielding a disparity map with which the predicted image is most similar to its original version. Then, with no modification of the disparity map, the residual image is encoded, yielding a refinement added to the predicted image. The proposed approach, first, improves all the possible predicted images taking into account this refinement, and then, estimates the disparity map as the one with which the predicted image resembles most that same view. Despite the significant increase in the numerical complexity, the substantial improved performance in terms of Peak-Signal to Noise-Ratio (PSNR) of this new approach is evidence of ongoing progress in this field of research.
Remote Sensing, 2021
The fusion of the hyperspectral image (HSI) and the light detecting and ranging (LiDAR) data has ... more The fusion of the hyperspectral image (HSI) and the light detecting and ranging (LiDAR) data has a wide range of applications. This paper proposes a novel feature fusion method for urban area classification, namely the relative total variation structure analysis (RTVSA), to combine various features derived from HSI and LiDAR data. In the feature extraction stage, a variety of high-performance methods including the extended multi-attribute profile, Gabor filter, and local binary pattern are used to extract the features of the input data. The relative total variation is then applied to remove useless texture information of the processed data. Finally, nonparametric weighted feature extraction is adopted to reduce the dimensions. Random forest and convolutional neural networks are utilized to evaluate the fusion images. Experiments conducted on two urban Houston University datasets (including Houston 2012 and the training portion of Houston 2017) demonstrate that the proposed method ca...
IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium, 2020
The presence of noise is often unavoidable and has been a serious nuisance factor that needs to b... more The presence of noise is often unavoidable and has been a serious nuisance factor that needs to be taken into account in the hyperspectral image classification. Effective noise handling is one of the most difficult problems in data classification. Ensemble-based filtering has been demonstrated successful in dealing with the class noise problem. In this paper, a novel two-step ensemble-based data filtering method is proposed to improve the hyperspectral image classification accuracy in the presence of class noise. The proposed method is a combination of noise redundancy classifiers and sensitive algorithms. The experimental results on two public hyperspectral datasets demonstrate the effectiveness of the proposed approach.
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2021
In this paper, a novel Synthetic Minority Oversampling Technique based Deep Rotation Forest(SMOTE... more In this paper, a novel Synthetic Minority Oversampling Technique based Deep Rotation Forest(SMOTE-DRoF) algorithm is proposed for the classification of imbalanced hyperspectral image data. It builds a multi -level forests cascade model by training a balanced dataset generated by SMOTE. In this model, each level of the random forest produces misclassification information of the data which are used as guidance information to adjust the sample weight adaptively for the next level. Experiment results on the hyperspectral image Indian Pines AVRIS and University of Pavia ROSIS demonstrate that the proposed method can get better performance than support vector machine, random forest, rotation forest, SMOTE combined random forest, and SMOTE combined rotation forest in imbalance learning.
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2021
The fusion of hyperspectral image (HSI) and light detection and ranging (LiDAR) data can provide ... more The fusion of hyperspectral image (HSI) and light detection and ranging (LiDAR) data can provide complementary information and improve the accuracy of land cover classification. In this paper, a novel fusion method is proposed to fuse the HSI and LiDAR dataset based on multi-scale feature extraction and total variation. In the method, the extended multi-attribute profile (EMAP) is utilized to automatically extract structural information from HSI and LiDAR elements. The extracted features are then estimated in a lower-dimensional space by multi-scale total variation (MSTV). Finally, the classification map is generated by applying random forest classifiers on the fused data. In the experiment, the performance of the proposed method is evaluated on an urban dataset of Houston. The results demonstrate that classification accuracy could be significantly improved by the proposed method compared with other methods.
2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS, 2021
Convolution neural network (CNN) has been successfully applied to hyperspectral image classificat... more Convolution neural network (CNN) has been successfully applied to hyperspectral image classification. However, multiclass imbalance is a major problem in the classification of hyper spectral images, and traditional CNN can hardly improve the accuracy of minority classes effectively. In this paper, a new ensemble CNN with enhanced feature subspaces (ECNN-EFSs) algorithm is proposed, which utilizes an imbalanced training set to train the model and achieves accurate classification. Experimental results on two common hyperspectral datasets show that the proposed algorithm outperforms the traditional CNN and ensemble CNN algorithms.
Remote Sensing, 2020
The fusion of multi-spectral and synthetic aperture radar (SAR) images could retain the advantage... more The fusion of multi-spectral and synthetic aperture radar (SAR) images could retain the advantages of each data, hence benefiting accurate land cover classification. However, some current image fusion methods face the challenge of producing unexpected noise. To overcome the aforementioned problem, this paper proposes a novel fusion method based on weighted median filter and Gram–Schmidt transform. In the proposed method, Sentinel-2A images and GF-3 images are respectively subjected to different preprocessing processes. Since weighted median filter does not strongly blur edges while filtering, it is applied to Sentinel-2A images for reducing noise. The processed Sentinel images are then transformed by Gram–Schmidt with GF-3 images. Two popular methods, principal component analysis method and traditional Gram–Schmidt transform, are used as the comparison methods in the experiment. In addition, random forest, a powerful ensemble model, is adopted as the land cover classifier due to its...
Information Sciences, 2021
Abstract In this paper, an adaptive semi-supervised rotation forest (SSRoF) algorithm is proposed... more Abstract In this paper, an adaptive semi-supervised rotation forest (SSRoF) algorithm is proposed for the classification of hyperspectral images with limited training data. Our proposition is based on Rotation Forest (RoF), a classifying technique that has proved to be remarkably accurate in the context of high-dimensional data. It is adapted to the semi-supervised context, by increasing the number of training instances in the learning stage, with high-quality unlabeled samples mined using ensemble margin. SMOTE is adopted to overcome the class imbalance problem. Out-Of-Bag (OOB) instances are used in a second phase to figure out the optimal number of samples to be added to the training set. Five ensemble methods and five semi-supervised methods are employed as comparisons. The results on three real hyperspectral remote sensing datasets demonstrate the effectiveness of the proposed method.
Remote Sensing, 2020
Remote sensing images classification is the key technology for monitoring forest changes. Texture... more Remote sensing images classification is the key technology for monitoring forest changes. Texture features have been demonstrated to have better effectiveness than spectral features in the improvement of the classification accuracy. The accuracy of extracting texture information by window-based method depends on the choice of the window size. Moreover, the size should ideally match the spatial scale of the object or class under consideration. However, most of the existing texture feature extraction methods are all based on a single window and do not adequately consider the scale of different objects. Our first proposition is to use a composite window for extracting texture features, which is a small window surrounded by a larger window. Our second proposition is to reinforce the performance of the trained ensemble classifier by training it using only the most important features. Considering the advantages of random forest classifier, such as fast training speed and few parameters, t...
Signal, Image and Video Processing, 2020
A stereoscopic image consists of two views rendering a depth sense. Indeed each eye is constraine... more A stereoscopic image consists of two views rendering a depth sense. Indeed each eye is constrained to look at one view, and the small objects displacements across the two views are interpreted as an indication of depth. These displacements are exploited as specific interview redundancies from a compression viewpoint. The classical still compression scheme, called disparity-compensated compression scheme, compresses one view independently of the second view, and a blockbased disparity map modeling the displacements is losslessly compressed. The difference between the original view and its disparity predicted view is then compressed and used by the decoder to compute the compensated view to improve the disparity predicted view. However, a proof of concept work has already shown that selecting disparities according to the compensated view, instead of the predicted view, yields increased rate-distortion performance. This paper derives from the JPEG-coder, a disparity-dependent analytic expression of the distortion induced by the compensated view. This expression is embedded into an algorithm with a reasonable numerical complexity approaching the performance obtained with the proof of concept work. The proposed algorithm, called fast disparity-compensated block matching algorithm, provides at the same bitrate an average performance increase as compared to the classical stereoscopic image coding schemes.
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019
Rotation forest (RoF) is a powerful ensemble classifier and has attracted substantial attention d... more Rotation forest (RoF) is a powerful ensemble classifier and has attracted substantial attention due to its performance in hyperspectral data classification. Multi-class imbalance learning is one of the biggest challenges in machine learning and remote sensing. The standard technique for constructing RoF ensemble tends to increase the overall accuracy; RoF has difficulty to sufficiently recognize the minority class. This paper proposes a novel dynamic SMOTE (synthetic minority oversampling technique)-based RoF algorithm for the multi-class imbalance problem. The main idea of the proposed method is to dynamically balance the class distribution before building each rotation decision tree. A resampling rate is set in each iteration (ranging from 10% in the first iteration to 100% in the last) and this ratio defines the number of minority class instances randomly resampled (with replacement) from the original dataset in each iteration. The rest of the minority class instances are generated by the SMOTE method. The reported results on three real hyperspectral datasets show that the proposed method can get better performance than random forest, RoF, and some popular data sampling methods. Elementary particle exchange interactions Micromotors Zirconium Product life cycle management Construction. Military vehicles Associative processing Geophysics Dendrites (neurons) Heart valves. Ion beams Biological cells Adsorption Occupational stress Stripline External stimuli Costing Continents Biomedical optical imaging SMOS mission Biomedical microelectromechanical systems Structural beams Document delivery Google.
2015 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2015
This paper deals with the disparity map estimation problem to encode non-rectified stereoscopic i... more This paper deals with the disparity map estimation problem to encode non-rectified stereoscopic images. This encoding issue is considered as a trade-off between the quality of the predicted view and the bit-rate required to encode the estimated disparity map. A sub-optimal optimization algorithm, known as Modified-M-Algorithm, based on an entropy-distortion metric has already been proposed specifically for rectified stereoscopic images. Indeed the selected disparities reduce not only the distortion of the predicted image but also the entropy of the estimated disparity map under a low computational complexity. An extension of this strategy is proposed to non-rectified stereoscopic images. Simulation results confirm that our extended algorithm still achieves better rate-distortion performance than the traditional block-matching algorithm. Moreover an improvement in terms of rate-distortion performance is also observed even in the case of rectified stereoscopic images.