Sample augmentation is crucial for improving land cover classification performance when the samples are limited. However, the traditional sample augmentation approach concentrates on enlarging the quantity of sample via generation and synthetic technique directly, the sample quality is usually neglected. In this article, we propose a novel sample augmentation approach with threshold estimation (SATE) to improve both the quantity and quality of samples for hyperspectral remotely sensed image (HRSI) classification. Firstly, a threshold estimation algorithm (TEA) is proposed to identify high-confidence potential samples from the initial classification map by utilizing the prediction probabilities of different classes. Second, a semi-variational model is employed to detect and correct pseudo-labels in the spatial domain, further enhancing the quality of selected potential samples. Finally, a farthest point sampling (FPS) algorithm optimizes sample distribution in the spectral domain, improving representation for intra-class heterogeneity. Experimental results based on four real HRSIs and compared with eight state-of-the-art few-shot-based methods verify the feasibility and superiority of the proposed SATE approach. The improvement achieved by our proposed approach is about 0.79% ~ 4.31% in terms of the overall accuracy. Code is available at https://github.com/ImgSciGroup/SATE.

Change detection with remote sensing images (RSIs) plays an important role in the community of remote sensing applications. However, when change detection is conducted with hyperspectral remote sensing images (HRSIs), how to measure the change magnitude between bitemporal HRSIs becomes challenging due to the high dimension of HRSIs. In this article, a novel Distribution Distance based on Inconsistent Adaptive Region (D2IAR) change detection approach is proposed to measure the change magnitude between bitemporal HRSIs for improving the performance of change detection with HRSIs. First, a band selection algorithm called optimal neighborhood reconstruction is employed to reduce the dimensions of HRSIs. Then, an adaptive region around each pixel is generated to explore the contextual feature around each pixel, and kernel density estimation is suggested to estimate the spectral distribution of the pixels within an adaptive region. A distribution distance is defined based on the adaptive region to measure the change magnitude between bitemporal HRSIs. Finally, the change magnitude between pairwise adaptive regions is measured by the proposed distance between the pairwise distributions. Experimental results based on four datasets and comparisons with eight methods indicated the feasibility and superiorities of the proposed D2IAR-based change detection approach with HRSIs. The improvement rates are approximately 0.13%-24.04% for overall accuracy. The code and datasets can be available at: https://github.com/ImgSciGroup/2024-HSICD.

Landslide is one of the most serious geological disasters around the world, and acquiring landslide inventory mapping (LIM) with remote sensed images (RSIs) plays an important role in disaster relief. However, various external imaging conditions of bitemporal RSIs usually cause pseudo-changes and challenges for achieving satisfied LIMs. In this article, a pioneering change magnitude measured distance named Spectral-Spatial Similarity based on Adaptive Region (S3AR) is proposed for achieving LIMs with bitemporal RSIs. First, an adaptive region is proposed to utilize the spatial-contextual information around each pixel, because the shapes and size of a landslide site are usually irregular and unpredictable. Then, a shape description algorithm is proposed for constructing a shape description vector, which aims at measuring the spatial difference of adaptive regions. Finally, to improve the separability between the landslide area and the background, brightness is suggested to couple with the shape description vector of an adaptive region to generate spatial-spectral similarity to measure the change magnitude between pairwise adaptive regions from the bitemporal RSIs. When the entire bitemporal RSIs are scanned and calculated via these steps, a change magnitude image between bitemporal RSIs can be generated, and then binary LIMs are obtained by a binary threshold. Experiments based on comparing eight state-of-the-art approaches demonstrated the feasibility and superiorities of the proposed S3AR for achieving LIMs with bitemporal RSIs. For example, the improvements on the four datasets are 5.81%, 14.06%, 6.03%, and 20.51% in terms of total error.

Laryngeal leukoplakia classification is challenging using white light endoscopy images. Relevant research focus on normal tissues versus non normal tissues, cancer versus non cancer classification. The objective of this paper is to classify laryngeal leukoplakia in white light endoscopy images into six classes: normal tissues, inflammatory keratosis, mild dysplasia, moderate dysplasia, severe dysplasia and squamous cell carcinoma. We proposed a dense multiscale convolutional neural network including parallel multiscale convolution, dense convolution and recurrent convolution in favor of extracting dense multiscale features of laryngeal leukoplakia for fine classification. The proposed network achieved an overall accuracy of 0.8958 for the six-class classification. It has high sensitivity and specificity for each class which are, respectively, 1.0000 and 0.9394 for normal tissues, 0.6667 and 1.0000 for inflammatory keratosis, 0.8889 and 0.9744 for mild dysplasia and moderate dysplasia, 0.7500 and 1.0000 for severe dysplasia, 1.0000 and 0.9767 for squamous cell carcinoma. The experimental results show that our proposed model is superior to the state-of-the-art deep learning-based models.

In recent years, deep neural networks (DNNs) have been widely used in hyperspectral image (HSI) classification. However, it has a strong vulnerability to crafted adversarial examples. Therefore, defense against adversarial examples is an urgent problem to be solved. To date, most defense methods are difficult to defend against unknown attacks. In this paper, we propose a perturbation-disentanglement-based adversarial defense method (PD-Defense) to protect HSI classification networks from unknown attacks. In the proposed method, the adversarial examples are decoupled into attack-invariant features and perturbation features, and the defense is conducted on the attack-invariant feature to defend against unknown attacks. Extensive experiments are performed on two benchmark HSI datasets, including PaviaU and HoustonU 2018. The results indicate that the proposed PD-Defense method achieves an excellent defense performance compared to four state-of-the-art defense methods.

Learning performance is unsatisfactory when training deep-learning networks without prior-knowledge guidance. In this paper, a multi-scale change detection neural network guided by a change gradient image (CGI) was proposed. First, a multi-scale information attentional module was embedded in the backbone of UNet to achieve a multi-scale information fusion task of bi-temporal images. Second, the position channel attention module was promoted to make the neural network pay more attention to the spectral and spatial information in the multi-scale fused feature map. Finally, a change gradient guide module was proposed to optimize backpropagation and overcome the negative effects of pseudo-change. Compared with seven state-of-the-art methods using three pairs of real remote sensing images, the proposed approach could smoothen the salt-and-pepper noise from the detection maps and improve the detection accuracy. The quantitative improvements are about 1.67% and 3.00% in terms of overall accuracy and Kappa coefficient, respectively, thus confirming the feasibility and superiority of the proposed approach for detecting land cover change with remotely sensed images. Code: https://github.com/ImgSciGroup/MACGGNet.git.

Land cover change detection (LCCD) with very high-resolution remote-sensing images (VHR_RSIs) is important in observing surface change on Earth. However, pseudo changes usually reduces the accuracy of the detection map. In this paper, novel piecewise distance based on adaptive region key-points extraction called sparse key-point distance (SKPD) is developed to measure the change magnitude between the bitemporal VHR_RSIs for LCCD. The proposed approach consists of three steps. First, an adaptive region generation algorithm is promoted for exploring spatial-contextual information. Then, the adaptive region around each pixel is sparsely represented with the box-whisker plot theory and the adaptive region is converted into a sparse key point vector. Finally, a piecewise distance is defined to measure the change magnitude between the bi-temporal images. While the entire VHR_RSIs are scanned and the proposed SKPD method proceeds on a pixel by pixel basis, a change magnitude image (CMI) can be generated and a binary threshold method can be applied on the CMI to obtain a change detection map. Experimental results based on four pairs of real VHR_RSIs and four state-of-the-art methods effectively demonstrated the superiority of the proposed approach for achieving LCCD with VHR_RSIs, such as the improvements for the four datasets are 5.25%, 14.76%, 18.13%, and 22.24%, respectively in terms of overall accuracy.

Abstract Deraining has been attracting a lot of attention from researchers, and various methods have been proposed, especially deep‐networks are widely adopted in recent years. Their structures and learning become more and more complicated and diverse, making it difficult to analyze the contributions and improvements. In this paper, a comprehensive review for current rain removal methods is first provided to show their contributions. Specifically, they are reviewed in terms of handing rain streaks and rain mist. Second, besides evaluating their rain removal ability, they are also evaluated in terms of their impact on subsequent stereo‐matching task. To this end, a new deraining dataset is first prepared, called Rain‐Kitti2012 and Rain‐Kitti2015. They are created by adding rain part to clean image‐pairs in Kitti2012 and Kitti2015. By then, nine state‐of‐the‐art deraining methods are evaluated with full‐reference and no‐reference image quality assessment metrics. Furthermore, the blurriness and distortion types introduced during deraining are measured. Finally, three learning‐based stereo matching methods are compared, and they take the outputs of deraining methods as inputs. It is further discussed how derained images influence the accuracy of stereo matching, which can provide some insight for jointly handling rain removal and stereo matching. 1: A comprehensive review for the current rain removal methods is provided. They are categorized into rain‐streak‐oriented and rain‐mist‐oriented approaches in terms of degradation type, and are categorized into model‐driven and data‐driven approaches in terms of methodology. 2: A new image deraining dataset is introduced, which is the first dataset that can be used to perform stereo‐matching‐driven evaluation for deraining methods. The dataset is created by adding rain part to clean images in KITTI2012 and KITTI2015. 3: We evaluate 9 deep learning based deraining methods with full‐reference and no‐ reference metrics. In addition, the types of distortions produced by these methods are discussed and measured quantitatively. And, the impact of 9 deraining methods on the subsequent stereo matching task is evaluated, which can provide some insight on how to design stereo matching task‐driven deraining methods.

Training samples are usually required to train a classifier for supervised classification of very high spatial resolution (VHR) remote sensing images. However, labeling samples is often a labor-intensive and time-consuming task. To solve this problem, this study integrates histogram distribution analysis, double-window flexible pace search (DFPS), and box–whisker plot (BP) techniques into an iterative algorithm to enrich training samples. The major steps of the proposed algorithm are given as follows. First, to acquire the feature distribution of a class, a histogram of each class (HOC) based on the raw classification map is generated. Second, to cover the spectral heterogeneity of an intraclass, some pixel points in each bin of HOC are selected as the coarse training sample set (CTS). Third, to further purify the CTS, DFPS, and BP techniques are adopted to exclude outlier samples and select the representative samples to signify the corresponding class. Finally, the refined training samples are used to retrain the classifier, and the preceding steps are constructed as an iterative algorithm. Experiments were performed on three real VHR remote sensing images to demonstrate the superiorities of the proposed approach in improving classification performance with respect to the maps obtained directly by the initial training set. In addition, compared with cognate state-of-the-art methods, the proposed approach achieved an approximately 2%–13% improvement in classification accuracy. Code available here:https://github.com/ImgSciGroup/IEEE-GRSL-GSEA-Code.

Landslide inventory mapping (LIM) is an important application in remote sensing for assisting in the relief of landslide geohazards. However, while conducting LIM tasks performing change detection analysis using bi-temporal very high-resolution (VHR) remote sensing images, due to landslide usually occurred in a mountain area, the phenological difference and outcrop rock may bring pseudo-changes to LIM results. In this paper, a novel change detection approach based on Adaptive Region Shape Similarity (ARSS) is proposed for LIM with VHR remote sensing images to improve detection performance. First, an adaptive region around each pixel is extended to explore the contextual information. Then, direction lines within an adaptive region are defined to describe the shape of the adaptive region. Finally, the pixels located on each direction line are taken into account to build the corresponding histogram. The shape similarity between the pairwise histogram curves is measured by using the Discrete Frchet Distance (DFD). Once the bi-temporal images are processed by using the abovementioned steps, a change magnitude image (CMI) is generated, while a threshold is then used to obtain a final binary change map. The proposed approach is applied to three pairs of landslide sites images acquired with aerial plane and one land use change dataset acquired by Quick Bird Satellite. Compared with ten state-of-the-art methods, the proposed approach achieved LIMs and detection results with higher accuracies and better performance.

Neuron detection is a key step in individualizing and counting neurons which are important for assessing physiological and pathophysiological information. A large number of methods including deep learning networks have been proposed but mainly targeting regions with few aggregated neurons. The objective of this paper is to address an automated neuron detection problem in heterogeneous hippocampus region with different degrees of neuron aggregation. Since deep learning networks require a lot of ground truths but neuron instance annotation is impossible in regions where numerous neurons are clustered, ground truth of centroids marked at the center of neurons is created for training. We propose a multiscale convolutional neural network (CNN) to regress neuron centroid mapping across image. Using multiscale information makes the proposed network applicable not only for single individual neurons, but also for a large number of aggregated neurons. Experimental results show that our method is superior to state-of-the-art deep learning-based algorithms. To our knowledge, this is the first deep learning study to detect neurons in regions of highly clustered neurons.

In biomedical research, cell counting is important to assess physiological and pathophysiological information. However, the automated analysis of microscopic images of tissues remains extremely challenging. We propose an automated processing protocol for proper segmentation of individual cells in microscopic images. A Gaussian filter is applied to improve signal to noise ratio (SNR) then an original minmax method is proposed to produce an image in which information describing both cell centers (minima) and boundaries are enhanced. Finally, a contour-based model initialized from minima in the min-max cartography is carried out to achieve cell individualization. This method is evaluated on a NeuN-stained macaque brain section in sub-regions presenting various levels of fraction of neuron surface occupation. Comparison with several methods of reference demonstrates that the performances of our method are superior. A first application to the segmentation of neurons in the hippocampus illustrates the ability of our approach to deal with massive and complex data.