In practical applications of social media and the Internet, deepfake face images involve a plethora of unlabeled samples. To effectively identify unlabeled deepfake images, the domain adaptation technique has gained significant attention. It applies the knowledge learned from labeled samples (source domain) to unlabeled samples (target domain) in a cross-domain manner. However, the existing domain adaptation-based deepfake detection methods primarily focus on intra-type cross-domain scenarios. In this study, we propose an unsupervised domain adaptation-based deepfake face image detection method for extra-type cross-domain scenarios. The core idea of our approach lies in the development of a domain adaptation model that consists of Domain Tag Adversarial (DTA) and Domain Feature Alignment (DFA) algorithms, called DTA-DFA, which empowers the proposed method with strong cross-domain capability. The DTA is utilized to weaken the specificity within each domain, while DFA aligns the distribution between the source and target domains. Compared with the existing deepfake detection methods, the experimental results demonstrate that the proposed method dramatically enhances the extra-type cross-domain detection performance. Moreover, the DTA-DFA model also exhibits a remarkable ability to perform cross-domain detection from large-shot labeled samples to few-shot labeled samples, further verifying its powerful cross-domain capability. Code is released at https://github.com/QinQin741/DTA-DFA-DA-model.

Reflections on the water surface hinder the extraction of valuable information from water surface images. To remove reflections from water surface images, we construct a synthetic dataset and propose a multi-task network for water surface reflection detection and removal. Specifically, we first use a U-Net-based reflection detection module to generate a reflection mask, followed by a GAN-based network to remove the reflection. To extract multi-level features from the images, we design a color feature extraction network and a detail feature extraction network. Finally, to enhance the model's ability to remove large-area reflections, we pre-train the reflection removal network on an image restoration dataset. Experimental results on the proposed synthetic dataset and real water surface reflection images from the Internet show that our method significantly outperforms other methods in water surface reflection detection and removal.

With the rapid advancements in object detection, oriented object detection has gained increasing attention. However, challenges such as boundary discontinuity and square-like problems in oriented object detection persist, as most existing methods directly regress the rotation angle, leading to instability in boundary angle prediction. To address these challenges, this paper introduces a novel rotation angle encoding method called the Composite Trigonometric Function Coder (CTFC), which transforms discrete angles into continuous curves. Leveraging the smooth characteristics of trigonometric functions, CTFC eliminates abrupt curvature changes, thereby avoiding the sudden angle steps inherent in conventional methods and simplifying the optimization process. Experiments conducted on three datasets validate the effectiveness of the proposed method. Additionally, the performance of CTFC has been further analyzed using three different detector heads. Experimental results and data analysis demonstrate that CTFC is efficient and effective in oriented object detection.

Video anomaly detection (VAD) methods are mostly CNN-based or Transformer-based, achieving impressive results, but the focus on detection accuracy often comes at the expense of inference speed. The emergence of state space models in computer vision, exemplified by the Mamba model, demonstrates improved computational efficiency through selective scans and showcases the great potential for long-range modeling. Our study pioneers the application of Mamba to VAD, dubbed VADMamba, which is based on multi-task learning for frame prediction and optical flow reconstruction. Specifically, we propose the VQ-Mamba Unet (VQ-MaU) framework, which incorporates a Vector Quantization (VQ) layer and Mamba-based Non-negative Visual State Space (NVSS) block. Furthermore, two individual VQ-MaU networks separately predict frames and reconstruct corresponding optical flows, further boosting accuracy through a clip-level fusion evaluation strategy. Experimental results validate the efficacy of the proposed VADMamba across three benchmark datasets, demonstrating superior performance in inference speed compared to previous work. Code is available at https://github.com/jLooo/VADMamba.

Recent advancements in semi-supervised learning and few-shot learning have shown significant progress in utilizing both labeled data and the unlabeled. However, most existing approaches assume the availability of at least some labeled data to establish an initial model foundation. In this study, we propose a pre-training method that integrates self-supervised information with pre-trained models, creating a more competitive and practical framework. This approach capitalizes on the strengths of powerful source domain pretrained models while effectively utilizing large-scale, real-time, unlabeled target data. Our proposed method is based on Siamese networks and leverages self-supervised information from unlabeled images. It comprises three key components: a transfer segmentation model, a Siamese network model and an image fusion model. The process begins by inputting an unlabeled image and its segmentation counterpart into the Siamese network for feature extraction. Image fusion is then performed, enabling self-supervised pre-training that enhances the performance of downstream tasks, such as image classification. We perform comprehensive experiments across various unlabeled clinical medical image datasets. The results demonstrate that our pre-trained model significantly enhances the performance of state-of-the-art semi-supervised classification models, including Mean Teacher, MixMatch, SST and SURE. Additionally, our approach strengthens the self-feature representation of unlabeled images, leading to performance gains beyond what is achievable with existing semi-supervised methods.

Achieving satisfactory land cover classification performance with high-resolution remote sensing images (HRSIs) usually requires sufficient samples for a supervised classifier. However, labeling sufficient samples is labor-intensive and time-consuming. In this article, a Novel Sample Augmentation Approach (NSAA) is proposed to synthesize new samples and improve classification accuracies for HRSI when initial known samples are very limited. First, a very small sample set of each class is prepared manually for the algorithm’s initialization. Second, a sample generator based on normal cloud model is proposed, and an adaptive region growing algorithm is suggested to explore some potential samples around a known sample for parameter estimation of the sample generator. Third, to further refine the generated samples around an initial known sample, a near-to-far space constraint strategy is proposed based on the K-means clustering algorithm to improve the quality of the generated samples. The proposed sample augmentation approach is incorporated with a classifier iteratively, and a sample balancing strategy is suggested in the iterative progress. Experiment results based on six real HRSIs and compared with eight state-of-the-art methods demonstrate the feasibility and superiorities of the proposed sample augmentation approach. Moreover, the reliability and robustness of the generated samples are verified by popular deep-learning networks and typical traditional classifiers. The improvement achieved by our proposed approach is about 0.12% – 0.95% in terms of the overall accuracy.

Self-supervised contrastive learning is a powerful pre-training framework for learning the invariant features from the different views of remote sensing images, therefore, the performance of contrastive learning heavily depends on the generation of views. Current view generation is primarily accomplished through different transformations, and the types and parameters of the transformations are require hand-crafted. Hence, the diversity and discriminability of generated views cannot be guaranteed. To address this, we propose a multi-type views optimization method to optimize these transformations. We formulate contrastive learning as a min-max optimization problem, and transformation parameters are optimized by maximizing the contrastive loss. The optimized transformations encourage the negative sample pairs to be close and the positive sample pairs to be far apart. Different from the current adversarial view generation methods, our method can optimize both photometric transformations and geometric transformations. For remote sensing images, the geometric transformation is more critical for view generation, while the existing view optimization methods fail to achieve this. We consider the hue, saturation, brightness, contrast, and geometric rotation transformations in contrastive learning, and evaluate the optimized views on the downstream remote sensing images semantic segmentation task. Extensive experiments are carried on the three remote sensing image segmentation datasets, including ISPRS Potsdam dataset, ISPRS Vaihingen dataset, and LoveDA dataset. Results show that the learned views obtain highly advantages compared to the hand-crafted views and other optimized views. The code associated with this paper has been released and can be accessed at https://github.com/AAAA-CS/AMView.

Multiparty computation (MPC) over rings such as Z264 has received a great deal of attention recently due to its ease of implementation and attractive performance. We assume there are n parties and the adversary corrupts t of them, where 2t < n. In this work, we leverage RMFEs (Reverse Multiplication Friendly Embeddings) to build an MPC protocol over Zpk with constant online communication. An (l, d)-RMFE packs l elements from Zpk into an element in GR(pk, d) = Zpk [X]/h(X), where deg h = d. The existence of asymptotically good RMFE ensures that d/l is bounded by a constant independent of n.

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.

Recent advancements of artificial intelligence based on deep learning algorithms have made it possible to computationally predict compound-protein interaction (CPI) without conducting laboratory experiments. In this manuscript, we integrated a graph attention network (GAT) for compounds and a long short-term memory neural network (LSTM) for proteins, used end-to-end representation learning for both compounds and proteins, and proposed a deep learning algorithm, CPGL (CPI with GAT and LSTM) to optimize the feature extraction from compounds and proteins and to improve the model robustness and generalizability. CPGL demonstrated an excellent predictive performance and outperforms recently reported deep learning models. Based on 3 public CPI datasets, C.elegans, Human and BindingDB, CPGL represented 1 - 5% improvement compared to existing deep-learning models. Our method also achieves excellent results on datasets with imbalanced positive and negative proportions constructed based on the C.elegans and Human datasets. More importantly, using 2 label reversal datasets, GPCR and Kinase, CPGL showed superior performance compared to other existing deep learning models. The AUC were substantially improved by 20% on the Kinase dataset, indicative of the robustness and generalizability of CPGL.

Benefiting from the high spectral resolution, hyperspectral image (HSI) owns the property of discriminating material. However, the spatial resolution of HSIs is limited by the hardware and, thus, makes HSI super-resolution (SR) a necessary and hot topic. Existed HSI SR methods rarely consider the high-frequency edge information, resulting in unsatisfactory quality of spatial reconstruction. To address the problem mentioned above, we propose a novel method for HSI SR named attention-driven dual feature guidance net (AD-DFGNet), which makes full use of the spatial–spectral information. Specifically, AD-DFGNet mainly consists of three modules, which are shallow feature extraction, DFG blocks, and upsampling fusion module. First, the three adjacent bands of an HSI cube are selected sequentially as one of the inputs to the proposed AD-DFGNet. Their feature dimension is upgraded through shallow feature extraction. Second, middle band of three adjacent bands is used as the other input to DFG block, and it makes the network focus on spatial feature extraction by DFG, which includes feature aggregation guidance (FAG) and gradient–texture attention (GTA) guidance. Then, the output features of DFG blocks are upsampled and fused, in turn, to obtain the single-band SR result. Finally, the SR results of the whole HSI are obtained from the sequential concatenation of each single band. In addition, the proposed method reduces the size of the generated model and makes it possible to apply on different datasets. The efficiency of the AD-DFGNet is validated on three publicly available hyperspectral datasets and yields the state-of-the-art performance.

Abstract Rain can severely hamper the visibility of scene objects. Although existing deep learning methods have reported promising performance, they often fail to obtain satisfactory results in many practical situations, especially when the input image contains both rain streaks and haze‐like degradation. In this paper, a new two‐stage method based on attention smoothed dilated network (SDN) is proposed. Unlike most fully‐supervised methods, the mixture of rain streaks and haze‐like effects is considered in the model. The proposed method consists of two stages. First, a generative adversarial network guided by the rain‐streak attention map is proposed to remove rain streaks, where a multi‐stage attention module is used to accurately locate rain streaks in the generator. Second, haze‐like effects are further removed through SDN with the same structure as the generator. Extensive experiments on multiple datasets show that the method outperforms the state‐of‐the‐art in both objective evaluation and visual quality.

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.

A novel hyperspectral anomaly detection method is proposed in this letter. This method is motivated by two important observations. First, there are hundreds of bands in a hyperspectral image (HSI), among which redundant bands and some noisy bands could be eliminated to increase the discriminability from the spectral domain. Meanwhile, considering the small amount of the anomalies, they may be neglected in the spatial clustering process, and the anomalies can be highlighted by eliminating the clustered result from the original HSI. In this way, the spatial-spectral extraction is proposed to detect the anomalies in the HSI. First, an iterative optimal neighborhood reconstruction (IONR) method is utilized to select the bands while preserving their divergence. Second, the spatial clustering is achieved by minimizing the intradistance in any given category. Finally, the spatial clustered HSI is eliminated from the band selected HSI and acts as the direct input for the detection process. Experimental results and data analysis have demonstrated the effectiveness of the proposed method.

Change detection with heterogeneous remote sensing images (HRSIs) is attractive for observing the Earth’s surface when homogeneous images are unavailable. However, HRSIs cannot be compared directly because the imaging mechanisms for bitemporal HRSIs are different, and detecting change with HRSIs is challenging. In this letter, a simple yet effective deep learning approach based on the classical UNet is proposed. First, a pair of image patches are concatenated together to learn a shared abstract feature in both image patch domains. Then, a multiscale convolution module is embedded in a UNet backbone to cover the various sizes and shapes of ground targets in an image scene. Finally, a combined loss function, which incorporates the focal and dice losses with an adjustable parameter, was incorporated to alleviate the effect of the imbalanced quantity of positive and negative samples in the training progress. By comparisons with five state-of-the-art methods in three pairs of real HRSIs, the experimental results achieved by our proposed approach have the best overall accuracy (OA), average accuracy (AA), recall (RC), and F-Score that are more than 95%, 79%, 60%, and 61%, respectively. The quantitative results and visual performance indicated the feasibility and superiority of the proposed approach for detecting land cover change with HRSIs.

The performance of a neural network is highly dependent on the labeled samples. However, the labeled samples are primarily clean, which prevents the network from capturing the features of the samples near the decision boundary. For hyperspectral images (HSIs), high spectral dimensions and same-spectra foreign matter lead to more boundary samples in the data. In this letter, we investigate an adversarial attack algorithm against these problems for HSIs. A modified DeepFool algorithm is implemented to generate boundary adversarial samples with minimal disturbance, and the generated boundary adversarial samples are simply added to the training set to improve the accuracy of the boundary samples in the data. Furthermore, we iteratively complete network training and boundary adversarial sample generation so that the decision boundary can be adjusted according to the real-time classification situation. Extensive experiments are carried out on the two HSI datasets, and the results demonstrate that the modified DeepFool algorithm can improve the accuracy of the decision boundary. Our findings also show that adversarial attacks are sensitive to high-dimensional and multiple-category data and are worthy of further study.

With the fast development of remote sensing platforms and sensors technology, change detection with heterogeneous remote sensing images (Hete-CD) has become an attractive topic in recent years and plays a vital role in land cover change detection for responding to natural disaster emergencies when homogeneous images are unavailable. Although Hete-CD has been developed for about three decades, and various related methods have been developed and applied successfully in practice, a systematic and comprehensive review of the current achievements regarding Hete-CD remains lacking. Therefore, in this article, we first present an overview of Hete-CD in terms of the related literature. Second, the major techniques of Hete-CD are reviewed in terms of publicly available datasets, the taxonomy of major techniques, results, performance, and quantitative evaluation. Then, some classical methods are selected for comparison and discussion. Finally, based on the discussion and literature review, challenges, opportunities, and future directions for Hete-CD are concluded. The review aims to provide a “one-stop-shop” understanding of the problems with the categories of existing approaches, open opportunities and challenges, and potential future directions for Hete-CD.

Deep neural networks have strong feature learning ability, but their vulnerability cannot be ignored. Current research shows that deep learning models are threatened by adversarial examples in remote sensing (RS) classification tasks, and their robustness drops sharply in the face of adversarial attacks. Therefore, many adversarial attack methods have been studied to predict the risks faced by a network. However, the existing adversarial attack methods mainly focus on single-modal image classification networks, and the rapid growth of RS data makes multimodal RS image classification a research hotspot. Generating multimodal adversarial examples needs to consider a high attack success rate, subtle perturbation, and collaborative attack ability between different modalities. In this article, we investigate the vulnerability of multimodal RS classification networks and propose a multifeature collaborative adversarial network (MFCANet) for generating multimodal adversarial examples. Two modality-specific generators are designed to generate the multimodal collaborative perturbations with strong attack ability, and two modality-specific discriminators make the generated multimodal adversarial examples closer to the real instances. In addition, a modality-specific generative loss and a modality-specific discriminative loss are proposed, and an alternating optimization strategy is designed for training the proposed MFCANet. Extensive experiments are carried out on the International Society for Photogrammetry and Remote Sensing (ISPRS) Vaihingen 2D dataset and ISPRS Potsdam 2D dataset. The results show that the attack performance of the proposed method is stronger than that of the fast gradient sign method (FGSM), project gradient descent (PGD), and Carlini and Wagner (C&W) attack methods.

In this paper, a novel hyperspectral image (HSI) anomaly detection method is proposed. This method is inspired by three ideas. First, the spatial resolution of the HSIs is sacrificed for their spectral information. Structural information of the HSIs tends to be smooth and distorts from that of the real scene. Second, with a loose false alarm rate, it is not difficult to pick out all the anomalies. Third, gradients of these probable anomalies can be transformed to enhance the spatial information of the HSI. Meanwhile, it is desirable that the enhanced HSI could be detected more precisely. Three modules are designed with respect to these three ideas, which are locating the probable pixels, local gradient guidance, and the anomaly detection for the enhanced HSI. Specifically, some probable anomalies are firstly selected. Secondly, the gradients of these selected pixels are transformed and utilized to guide the spatial enhancement for the HSI locally. Finally, the final detection is implemented on the enhanced HSI. Experimental results obtained on four real HSIs demonstrate the effectiveness of the proposed method.

Abstract Single image de‐raining based on convolutional neural network (CNN) has made considerable progress in recent years. However, usually the de‐rained result has dark artifacts and image textures tend to be over‐smoothed. In this paper, a pyramid non‐local enhanced residual dense network is proposed to reduce such distortion. Firstly, the down‐sampled images are input into the Laplacian pyramid, which can extract the overall and partial texture clues, and subsequently a set of images of different scales are produced. Secondly, these images are fed into a non‐local enhanced residual dense block, which can not only capture long‐distance dependencies of feature maps, but also fully utilizes the hierarchical features in every dense block, leading to high accuracy of rain streaks extraction and better preservation of image edge detail. Finally, the de‐rained image is gradually restored by Gaussian reconstruction pyramid. Experimental results on both synthetic data and real‐world data show that the artifacts distortion is obviously reduced by the proposed network. And the quality of de‐rained image is significantly improved compared with the state‐of‐the‐art methods.

Abstract Salient target detection in hyperspectral image is a significant task in image segmentation, target tracking, image classification and so on. Many existing saliency detection algorithms for hyperspectral image detection cannot present the boundary of the salient target well and the description of the target is not enough. A method based on visual attention to detect the salient target of hyperspectral image is proposed in this paper. In this method, frequency‐tuned (FT) salient detection model is combined with spectral salient to detect target in hyperspectral image. FT model is used to get target with clear border, and spectral information is made full use of to improve the accuracy of target detection. Firstly, FT is used to detect saliency of hyperspectral image and the saliency map is generated. Then, spectral information of the hyperspectral image is measured by similarity, and the spectral saliency is obtained by calculating spectral angle distance between the spectral vectors. Finally, the FT's saliency map and the spectral saliency map are combined to form the final saliency target maps. Experimental results show that our method is superior to other methods in saliency target detection of hyperspectral image, and the precision‐recall curve and F‐measure are better as well.

Hyperspectral image (HSI) super-resolution is currently attracting great interest in remote sensing, since it allows the generation of high spatial resolution HSIs and circumventing the main limitation of the imagery sensors. This paper proposes a novel deep intra fusion network (IFN) for the HSI super-resolution, in which both the spatial and the spectral information have been fully and automatically exploited. Specifically, parallel convolutions are applied to two adjacent bands and their difference band, and obtain the high-dimensional features. Meanwhile, an automatically aggregation module is applied in the IFN to achieve the intra-fusion between these features. In this way, both the spatial information of the current band and the spectral information between neighboring bands are utilized in the super-resolving process. Experimental results and data analysis suggest the effectiveness of the proposed method.

Images captured in the sand–dust weather often suffer from serious colour cast and poor contrast, and this has serious implications for outdoor computer vision systems. To address these problems, a normalised gamma transformation‐based contrast‐limited adaptive histogram equalisation (CLAHE) with colour correction in Lab colour space for sand–dust image enhancement is proposed in this study. This method consists of image contrast enhancement and image colour correction. To avoid producing new colour deviation, the input sand–dust images are first transformed from red, green, and blue colour space into Lab colour space. Then, the contrast of the lightness component (L channel) of the sand–dust image is enhanced using CLAHE. To avoid unbalanced contrast, as well as to reduce the overincreased brightness caused by CLAHE, a normalised gamma correction function is introduced to CLAHE. After that, the a and b chromatic components are recovered by a grey‐world‐based colour correction method. Experiments on real sand–dust images demonstrate that the proposed method can obtain the highest percentage of new visible edges for all testing images. The contrast restoration exhibits good colour fidelity and proper brightness.

This article presents an intrafusion network (IFN) for hyperspectral image (HSI) super-resolution (SR). Given that the HSI is a 3-D data cube with both the spatial information and the spectral information, the key challenge to construct HSI SR is how to efficiently exploit the spectral information among consecutive low-resolution (LR) bands, besides the spatial information. The proposed IFN consists of three modules, including the spectral difference module, the parallel convolution module, and the intrafusion module, which directly utilizes both the spatial information and the spectral information for reconstructing the high-resolution HSI. Different from most of the existed methods that tackle the spatial and spectral information separately, the proposed spatial-spectral utilization is achieved in one integrated network, which opens up a new way for HSI SR. Meanwhile, applications of this three modules strategy (first spectral difference, then parallel convolution, and finally, intrafusion) on both the conventional convolutional neural network and the residual network with deeper depth have shown the generalization capacity of this proposal. Experimental results and data analysis demonstrate the effectiveness of the proposed method using three hyperspectral data sets.

Limited by existing electromagnetic sensors, the hyperspectral image (HSI) is characterized by having a high spectral resolution but a low spatial resolution. The super-resolution (SR) technique, which aims at enhancing the spatial resolution of the input image, is a hot topic in computer vision. This paper presents a rapid HSI SR method based on a deep information distillation network (IDN) and an intra-fusion operation to fully utilize the spatial-spectral information. Specifically, some bands are firstly selected and super-resolved by utilizing their spatial information through IDN. Non-selected bands are super-resolved by spectral interpolation. Moreover, to take a full advantage of the information these non-selected bands conveys, intra-fusion is operated on the input HSI and the spectrally-interpolated high resolution HSI. Contrary to most existed fusion methods which require multiple observations of the same scene, this intra-fusion is more flexible, and makes further utilization of the information the input HSI conveys simultaneously. In addition, this method requires less computation and is more suitable for practical applications. Experimental data and comparative analysis have demonstrated the effectiveness this method.

Rain image enhancement is important for outdoor computer vision applications. In this study, the authors propose a multi‐stage filtering method for single rainy image enhancement. It is based on their new rainy image model, and consists of two main operations: rain streaks removal and rain fog removal. For rain streaks removal, based on one key observation that the low‐pass version of a rainy image and that of a non‐rainy image of the same scene are almost the same after appropriate low‐pass filtering, they remove rain streaks from rainy images by decomposing an input rainy image (or a rainy component image) into the low‐frequency (LF) part and the high‐frequency (HF) part via an LF smooth filter, i.e. the traditional Gaussian filter with a simple subtraction operation in multiple different stages. After rain streaks removal, dark channel prior‐based method was employed for rain fog removal. Experimental results show that the proposed algorithm generated comparable outputs with most of the state‐of‐the‐art algorithms with low computation cost.

Images captured in hazy weather are usually of poor quality, which has a negative effect on the performance of outdoor computer imaging systems. Therefore, haze removal is critical for outdoor imaging applications. In this paper, a quick single-image dehazing method based on a new effective image prior, luminance dark prior, was proposed. This new image prior arose from the observation that most local patches in the luminance image of a haze-free outdoor YUV color space image usually contain pixels of very low intensity, which is similar to the dark channel prior used with HE for RGB images. Using this new prior, a transmission map was used to estimate the thickness of the haze in an image directly from the luminance component of the YUV color image. To obtain a transmission map with a clear edge outline and depth layer of scene objects, a joint filter containing a bilateral filter and Laplacian operator was employed. Experimental results demonstrated that the proposed method unveiled details and recovered vivid colors even in heavily hazy regions, and provided superior visual effects to many other existing methods.

This paper develops a novel decentralized dimensionality reduction algorithm for the distributed tensor data across sensor networks. The main contributions of this paper are as follows. First, conventional centralized methods, which utilize entire data to simultaneously determine all the vectors of the projection matrix along each tensor mode, are not suitable for the network environment. Here, we relax the simultaneous processing manner into the one-vector-by-one-vector (OVBOV) manner, i.e., determining the projection vectors (PVs) related to each tensor mode one by one. Second, we prove that in the OVBOV manner each PV can be determined without modifying any tensor data, which simplifies corresponding computations. Third, we cast the decentralized PV determination problem as a set of subproblems with consensus constraints, so that it can be solved in the network environment only by local computations and information communications among neighboring nodes. Fourth, we introduce the null space and transform the PV determination problem with complex orthogonality constraints into an equivalent hidden convex one without any orthogonality constraint, which can be solved by the Lagrange multiplier method. Finally, experimental results are given to show that the proposed algorithm is an effective dimensionality reduction scheme for the distributed tensor data across the sensor networks.