The removal of rain streaks and raindrops is crucial for enhancing the image visibility and mitigating the weather degradations. However, most existing approaches rely on the paired rainy and clean images, which are challenging to obtain in real-world scenarios. To this end, we propose a novel structure-preserving frequency-regularized text-guided optimal transport (SFTOT) framework, which formulates the unpaired rain streaks and raindrops removal as an optimal transport problem. Specifically, we introduce a structure-preserving transport cost, incorporating the structural similarity constraint to minimize the duality gap between the primal and dual formulations, while preserving the structural details of reconstructed images. Furthermore, by embedding the inherent frequency sparsity of rain streaks and raindrops into the transport cost, we derive a frequency-regularized optimal transport objective, ensuring consistency in frequency distributions between the generated and clean images. Additionally, we employ a pre-trained one-step stable diffusion model as the restoration network, which is fine-tuned using the low-rank adaptation (LoRA) adapters and zero convolutional layers, while integrating the domain-specific text prompts for both degraded and clean images to guide the generation process. Extensive experiments demonstrate that our method surpasses the existing well-performing unpaired learning approaches, achieving notable improvements in both the fidelity and photo-realism.

Existing approaches have significantly advanced remote sensing image dehazing. However, they often rely on conventional encoder-decoder architectures, leading to prolonged inference times. To this end, we propose a novel cross-level interaction and intra-level fusion network for remote sensing image dehazing (CINet), which shifts the focus from encoder-decoder dependencies to an innovative hierarchical architecture centered on skip connections, leading to competitive dehazing performance with decreased calculating complexity. Furthermore, we introduce a cross-level multi-view interaction module (CMIM) to facilitate effective interactions between features across hierarchical levels, mitigating the information loss commonly caused by repeated down-sampling operations. Meanwhile, we develop an intra-level dual-dimension fusion module (IDFM), which leverages height-wise and width-wise self-attention to capture rich spatial-aware information, enabling robust and efficient intra-level feature fusion. Additionally, we propose a multi-view progressive extraction block (MPEB), which decomposes features into four distinct components and applies convolutions with diverse kernel sizes, groups, and dilation factors. This design promotes progressive feature learning while significantly reducing computational overhead. Extensive experiments conducted on nine publicly available datasets validate the effectiveness and superiority of our proposed model.

Object detection is an essential and crucial task in interpretation of optical remote sensing images (RSIs). However, its performance is usually limited due to the complex background and multiscale characteristics of targets. To overcome these limitations, a self-supplementary and revised anchor-free detector is proposed. First, to reduce the computational cost of detection, a partial bottleneck (PBottleneck) structure is designed to efficiently extract multiscale feature information in a lightweight manner. Second, pure spatial feature pyramid network (PSFPN) attaches importance to description of distance and suppresses environmental disturbance by a devised multidirectional distance attention (MDDA) mechanism. In addition, pure fusion strategy (PFS) is created to boost information with no occlusion between various features. Third, toward the multiscale objects issue, self-learning supplementary and revised module (SSRM) is explored to generate more abundant and balanced expression by adaptively incorporating the supplementary and corrected information from adjacent features. Finally, comprehensive experiments are conducted on several publicly available datasets, demonstrating effectiveness of our proposed detector, leading to a new benchmark.

Adverse weather conditions, such as rain, raindrop, snow and haze, consistently degrade images in an unpredictable manner, thereby rendering existing task-specific and task-aligned methods inadequate in addressing this formidable problem. To this end, we investigate the application of Transformer in image restoration and introduce an efficient frequency-oriented method called AIRFormer, which is designed to restore weather-degraded images comprehensively and holistically. Specifically, we identify that the initial self-attention mechanism exhibits distinctive properties akin to a low-pass filter. Therefore, we construct a frequency-guided Transformer encoder by incorporating wavelet-based prior information to guide the extraction of image features. Additionally, considering the non-specific frequency characteristics of self-attention in the later stages, we develop a frequency-refined Transformer decoder that incorporates learnable task-specific queries across spatial dimensions, channel dimensions, and wavelet domains. To facilitate the training of our proposed method, we curate a comprehensive benchmark dataset named AIR40K that, encompasses a wide range of challenging scenarios. Extensive experimental evaluations demonstrate the superiority of our AIRFormer over both task-aligned and all-in-one methods across 15 publicly available datasets. Notably, AIRFormer achieves the best trade-off between the inference time and quality of reconstructed image, comparing with existing methods such as TransWeather and Restormer. The source code, dataset and pre-trained models will be available at https://github.com/chdwyb/AIRFormer.

Object detection is a fundamental task in the analysis and interpretation of remote sensing images. However, compared to natural images, remote sensing images are characterized by broad diversity in object scales, fuzzy objects, and complex background, which bring great challenges to object detection. For overcoming the above problems, a task alignment interaction and cross-scale guidance enhancement network (TCNet) is proposed in this letter. Firstly, a generalized mean spatial pyramid pooling (GeMSPP) is designed and embedded in the backbone to adapt to changes of complex environment and reduce loss of features. Secondly, cross-scale guided enhancement network (CGEN) is proposed to generate high-quality non-aliasing multi-scale target features for each feature level by guiding the fusion of deep features and enhancing feature expression. Thirdly, Task alignment interactive head (TAIH) is adopted to enhance the classification and regression accuracy of the prediction box, so as to suppress background interference and highlight object features. Experiments conducted on public DIOR and RSOD datasets illustrate that the proposed modules can effectively improve the accuracy of detection and our network has superior performance compared with other state-of-the-art detectors.

Dehazing based on deep learning has attracted a lot of attention recently. Most dehazing networks seldom consider two critical features of real outdoor-scene haze,i.e., depth and haze density, resulting in degraded performance on real hazy images compared with synthetic hazy images. Moreover, the uncertainty problem is crucial in the image restoration field, but it is often ignored. In this letter, we propose a novel multi-scale density-aware network (MSDAN) for single image dehazing, where a key dual feedback module (DFB) is proposed and embedded in the decoder part of MSDAN. Furthermore, the DFB includes a feedforward mechanism and two feedback mechanisms: feature feedback (FF) and transmission feedback (TF). Specifically, the feedforward mechanism predicts a low-scale transmission map ($t$-map), while FF and TF aim to enhance confident features to reduce model uncertainty in the training process and correct features by introducing depth and density information. In addition, two novel modules: confident feature attention module (CFA) and transmission adjustment module (TADJ) are proposed as cores for confident features estimation of FF and TF, respectively. Extensive quantitative and qualitative experiments are conducted on several public datasets, which demonstrate that the proposed algorithm outperforms the state-of-the-art algorithms.

Abstract A new two‐dimensional chaotic system in the form of a cascade structure is designed, which is derived from the Chebyshev system and the infinite collapse system. Performance analysis including trajectory, Lyapunov exponent and approximate entropy indicate that it has a larger chaotic range, better ergodicity and more complex chaotic behaviour than those of advanced two‐dimensional chaotic system recently proposed. Moreover, to protect the security of the crowd image data, the newly designed two‐dimensional chaotic system is utilized to propose a visually meaningful image cryptosystem combined with singular value decomposition and Bernstein polynomial. First, the plain image is compressed by singular value decomposition, and then encrypted to the noise‐like cipher image by scrambling and diffusion algorithm. Later, the steganographic image is obtained by randomly embedding the cipher image into a carrier image in spatial domain through the Bernstein polynomial‐based embedding method, thereby realizing the double security of image information and image appearance. Besides, the visual quality of the steganographic image can be improved by the adjustment factor according to different carrier images during the embedding process. Ultimately, security analyses indicate that it has higher encryption efficiency (2 Mbps) and the visual quality of steganography image can reach 39 dB.

To find out the area that road collapse may occur, the ground penetrating radar (GPR) is utilized to detect the underground structure. And a high speed array impulse GPR mounted on a high-speed vehicles is specially designed for the detection in the city. The gain control method is an important step to make the useful signal more visible in the data processing. To process the cross-section of three-dimension data collected by the high speed array impulse GPR, two kinds of methods based on the envelope of extremum are proposed in this paper. Compared with the conventional method, the first kind of extremum envelope method has a good performance in compensating the signal attenuation but it enhances the interfering signals as well. So another improved extremum envelope method is introduced to keep a balance. It is proved that the second kind of extremum envelope method is appropriate for the high speed array impulse GPR system.

Pavement life span is often affected by the amount of voids in the base and subgrade soils, especially the soil moisture content. Ground Penetrating Radar (GPR) is one of the desirable techniques to indirectly measure the in-situ soil moisture content through electrical properties of soils. The inversion using transmission line matrix method from GPR data is applied for converting moisture content of the soils. Laboratory and field tests proved satisfactory results.

A new chaos communication system based on reverse‐time chaotic oscillator (RTCO) is proposed in this study. In the system, driven by bipolar sequence, RTCO can directly generate chaotic wave signals that can encode arbitrary binary information, which is much easier than that of the existing chaotic communication scheme in that needs the initial condition estimation. Then the analytical expression of matched filter for the basis function of RTCO is derived. The proposed matched filter is capable of decreasing the effect of noise in the channel. Next, the binary information can be obtained by detecting the summation of multi‐sampling during the symbol period through a setting threshold over additive white Gaussian noise (AWGN) channel, which further decreases the influence of noise in decoding procedure. In addition, the binary information can also be obtained over the Rayleigh channel, and its bit error rate (BER) expression is derived. Finally, the feasibility and the validity of the proposed system are given with numerical simulations. It is shown that in the proposed communication system, the encoded chaotic signal is generated with a much simpler method. Furthermore, the BER is lower than that in over AWGN channel, and the performance of the proposed system over Rayleigh channel is better than that of differential‐chaos‐shift‐keying.