Images taken in low-light conditions are frequently affected by limited visibility, diminished contrast and severe noise, adversely impacting the performance of various computer vision tasks. Most variational-based Retinex decomposition methods mainly depend on integer norms to constrain the illumination and reflectance components. However, this strategy may fail to achieve the ideal Retinex decomposition. In this paper, we propose a Retinex-based variational model that incorporates flexible constraints for both illumination and reflectance. Specifically, we impose the Lpnorm constraints with varying values of p to ensure the piece-wise smoothness of the illumination and promote the presence of abundant textures in the reflectance. Moreover, we develop two effective pixel-wise weight matrices that consider variance and gradients of the input image respectively, with the objective of preserving the structural edges of the illumination and retaining more details in the reflectance. In addition, we use an L2norm to estimate the overall noise level and avoid noise amplification. Through incorporating these above constraints, our proposed variational model can obtain a structure-aware illumination and a detail-revealed reflectance. Qualitative and quantitative comparisons on real-world and synthetic datasets indicate that our approach yields results with superior visual quality and outperforms several state-of-the-art algorithms on objective metrics. Besides, our algorithm can also address similar low-level computer vision challenges, such as image dehazing and underwater image enhancement. The source code is available at https://github.com/Enping-Hu/dual weighted lp.

WiFi channel state information (CSI)-based gesture recognition offers unique advantages, including cost-effectiveness and enhanced privacy protection, and has garnered significant attention in recent years. However, existing WiFi-based gesture recognition solutions exhibit poor generalization ability when deployed in new environment, orientation, or location. Although some methods combine labeled source domain and unlabeled target domain to learn domain-independent features, factors, such as data privacy protection, hinder access to source data during practical environment adaptation. Consequently, we consider realistic scenario where source data is unavailable during adaptation of unlabeled test data, and instead, a trained source domain model is used. In this article, we propose Wi-SFDAGR, a WiFi-based source-free domain adaptation gesture recognition framework. Specifically, we treat cross-domain as an unsupervised clustering problem, aiming to ensure that features within local neighborhoods exhibit similar prediction results while those farther apart display different prediction outcomes in the feature space. We theoretically analyze the effect of enhanced prediction consistency between neighbor points extracted from gestures on generalization error. Furthermore, we employ an attraction-dispersion network to strengthen prediction consistency among closely located features in the feature space while reducing it for distantly located features. To mitigate noise introduced during nearest neighbor sample selection in the feature space (where predictions may not align with the input sample’s prediction), we progressively improve nearby sample feature aggregation by estimating uncertainty to reweight local neighborhood predictions. Finally, extensive experiments are conducted on the Widar 3.0 and XRF55 datasets and the results show our proposed framework outperforms most cross-domain methods.

Despite the progress of existing techniques in Camouflaged Object Detection, there are still problems such as multi-target omission, small-object misjudgment, and insufficient localization and segmentation accuracy. With the advantage of image frequency domain transformation, high-frequency features can capture detailed information such as edges and textures of the image, while low-frequency features depict the overall outline of the image, improving the accuracy of camouflage object detection. Therefore, this paper proposes a Frequency Domain-Based Cross-layer Feature Aggregation Network (FCFANet), aiming to improve the problems of multi-target omission, small target loss, object localization deviation, and insufficient segmentation accuracy in complex scenes. FCFANet mainly consists of an Intra- and Inter-layer Enhancement Module (IEM) and a Frequency-Spatial Interaction Fusion Module (FSIFM). IEM reduces noise and enhances the feature representation, while FSIFM extracts frequency information, and enhances feature discrimination by complementary fusion of spatial and frequency domains, thus realizing the precise positioning and high-precision segmentation of camouflaged objects. Compared with 16 state-of-the-art(SOTA) methods, experiments show that FCFANet outperforms other SOTA methods on four benchmark datasets.

The visibility of images plays a crucial role in Intelligent Transportation Systems (ITS). However, images captured under hazy environments can degrade visual quality, significantly reducing the working performance of ITS. Although existing dehazing methods have achieved remarkable performance for daytime hazy images, they struggle to overcome the unique degradations under nighttime haze conditions such as glows, weak illumination, hidden noise, and color distortions. To simultaneously address these degradations, we propose VNDHR, a novel Variational Nighttime Dehazing framework using Hybrid Regularization focusing on enhancing the perceptual visibility of nighttime hazy scenarios. Specifically, a new physical model that accounts for multiple degradations under nighttime haze conditions is first constructed. Then, a novel hybrid variational model comprising an$\ell _{p}$norm, a weighted$\ell _{2}$norm, and a total variation regularization is developed to obtain a structure-aware illumination and a noise-free reflectance, simultaneously. To remove the nonhomogeneous haze in the illumination, we employ the dark channel prior to estimate parameters in each grid patch. Furthermore, a simple but effective nonlinear stretching function is designed to enhance the texture in the decomposed reflectance component. Finally, the dehazed illumination and the stretched reflectance are combined to generate a haze-free result. Experiments performed on synthetic and real-world nighttime hazy images prove that our VNDHR framework achieves state-of-the-art dehazing performance, providing results with clear details and less noise. Besides, our VNDHR can also handle various types of degraded images well, such as low-light images, daytime hazy images, sandstorm images, and underwater images.

Light field saliency detection can leverage the rich visual features of light field(LF) to highlight the salient regions, but existing CNN-based saliency detection methods are specifically designed for RGB image, not for light field. To tackle this problem, a three-stream cross-modal feature aggregation network is proposed for 4D light field saliency detection. To fully utilize the rich visual features of light field, three sub-networks are set up to analyse focal stack, all-focus image, and depth map respectively. Then, feature aggregation modules are used to aggregate cross-level features in a top-down manner. Finally, a cross-modal feature fusion module is designed to fuse the aggregated features of various modalities from the three sub-networks, which can identify salient object quickly and precisely. Extensive experiments on three benchmark datasets show that the effectiveness and superiority of the proposed algorithm qualitatively and quantitatively on five evaluation metrics compared with state-of-the-art(SOTA) methods.

Most of approaches to salient object detection focused on two‐dimensional images, while rare attention was attached to the light field which can provide exclusive visual information for salient object detection and other computer vision applications. An effective algorithm of salient object detection is proposed for light field data. First, boundary connectivity is calculated on all‐focus image. Then, background probability based on boundary connectivity is achieved by computing geodesic distance. Second, the authors rank the similarity of the superpixels of both all‐focus image and depth map via graph‐based manifold ranking to carry out two initial saliency maps. Third, weighted by background probability, the two initial saliency maps are fused to produce final saliency results, integrated by objectness cue. The authors also exploit how to integrate effectively objectness with other visual features, and compare two fusion strategies: linear fusion and Bayesian integration. Experiments show that light field features are helpful for saliency detection, and Bayesian integration framework is the better choice than linear fusion method. Meanwhile, the way how to combine multiple features is crucial. The proposed algorithm handles challenging natural scenarios such as cluttered background, similar foreground and background, and so on, and produces visual favourable results in comparison with the eight state‐of‐the‐art methods.

Automatic detection of salient objects in images has gained its popularity in computer vision field for its usage in numerous vision tasks in recent years. Depth information plays an important role in the human vision system while it is underutilized in most existing two-dimensional (2-D) saliency detection methods. In this letter, a multistage salient object detection framework via minimum barrier distance transform and saliency fusion based on multilayer cellular automata (MCA) is proposed. First, we independently generate the 3-D spatial prior, depth bias, and RGB-produced and depth-induced saliency maps. Next, the two saliency maps are weighted by depth bias to obtain two initial maps. Then, we adopt a saliency optimization step to generate more precise depth-induced saliency map. Moreover, the initial RGB-produced and the optimized depth-induced maps are further fused with 3-D spatial prior. Finally, we utilize MCA to fuse all saliency maps generated previously and obtain the final saliency result with complete salient object. The proposed method is evaluated on the publicly available benchmark dataset, RGBD1000. Compared to several state-of-the-art 2-D and depth-aware approaches, the experimental results demonstrate the effectiveness and superiority of our method, which can accurately detect the salient objects from RGB-D images, and has the most satisfactory overall performance.