Search Results (1,502)

Safety monitoring and visual surveillance in underground coal mines must cope with extreme low light and pervasive coal dust, yet the most accurate low-light image enhancement models rely on self-attention, whose quadratic cost precludes real-time use on the edge-computing platforms deployed underground, such as inspection robots and explosion-proof cameras. Our key observation is that these two degradations are separable by a wavelet decomposition: the low-frequency band carries the illumination to be corrected, whereas dust-induced noise is largely confined to the high-frequency bands. MineSSM turns this observation into an efficient design that routes each band to the operator it needs: a linear-complexity state-space model (Mamba) that homogenizes the global illumination and a lightweight convolutional branch that performs dust suppression on the high-frequency bands, so that no heavy operator ever runs at full resolution, and the two branches are recomposed under a Retinex constraint for faithful color restoration. A frequency-domain analysis of a real dusty mining frame confirms this split, with the smooth veil and lamp glow in the low-frequency band and the discrete dust speckles in the high-frequency bands. MineSSM surpasses the Transformer-based MEFormer on the MELOL mining dataset (26.58 dB PSNR/0.96 SSIM vs. 26.34 dB/0.91 SSIM) and attains the best PSNR and SSIM on the LOLv1 benchmark, while running at 27.8 FPS (0.036 s per $400\times 600$ image) on a desktop GPU with linear resolution scaling. On an embedded NVIDIA Jetson Orin NX it sustains 8.0 FPS at $400\times 600$, supporting near-real-time on-device enhancement at typical surveillance resolutions. Full article

Underwater images captured by sensors suffer from low contrast and blurry details due to the interference of light absorption and scattering in underwater scenes. Good visibility restoration is often desired for practical processing applications. Current image enhancement methods often rely on prior assumptions to reconstruct a clear image without considering the inherent correlation of underwater image degradation, introducing unconsiderable enhancement results. Thus, this paper proposes an underwater enhancement method based on multiple enhanced layers fusion and transmission-driven color restoration, named EFCR, which consists of three key modules: a pixel-based transmission computation (PTC), a multiple-enhanced-layers fusion (MELF), and a transmission-driven color restoration (TCR). First, PTC designs a linear transformation to adjust the saturation and estimates the transmission based on the mapping relationship between the transmission, the brightness, and the saturation, preventing the transmission from being under-estimated. Then, MELF extracts the original details from the luminance channel and enhances these desired details based on the estimated transmission. Meanwhile, adaptive histogram equalization is used to improve the global brightness. Finally, TCR further analyzes the inherent correlation between the transmission and the image degradation, and constructs a compensation factor to adaptively correct the attenuated a and b channels of Lab space, producing a good enhancement result with reasonable brightness and natural colors. Extensive experiments on three underwater image datasets demonstrate the effectiveness and robustness of the proposed method in underwater image restoration. Especially, the average $\overline{r}$ and Blur values of our method at most incline and decline by 99.87% and 10.22%, respectively, which shows our method has obvious advantages in edge enhancement and haze removal. Moreover, our method provides helpful support for color restoration and image salient detection, and also shows good generalization capability for enhancing outdoor hazy images. Full article

Nighttime driving safety remains a critical challenge in modern transportation systems: insufficient ambient lighting significantly degrades visual perception quality, adversely affecting both human drivers and advanced driver-assistance systems (ADAS) and directly threatening road users’ safety. Traditional image enhancement methods often suffer from color distortion and visual artifacts, whereas existing deep learning approaches typically require paired training data and incur substantial computational overhead. To address these limitations, this paper presents BLEN (bio-inspired low-light enhancement network), a zero-reference deep learning framework that integrates biological vision principles with efficient convolutional architectures. Specifically, BLEN leverages Retinex theory for illumination–reflectance decomposition, is inspired by and functionally approximates lateral inhibition mechanisms for edge enhancement, and incorporates a Large-Kernel Convolution with Attention (LKCA) module that reduces the parameter count of the LKCA encoder block by 76% (0.56 M vs. 2.34 M for a standard 13 × 13 convolution) relative to standard large-kernel operations. Extensive experiments on the SICE and LOL benchmarks demonstrate that BLEN achieves state-of-the-art performance among real-time, edge-deployable zero-reference methods on the SICE benchmark, yielding a peak signal-to-noise ratio (PSNR) of 23.67 ± 0.14 dB and a structural similarity index measure (SSIM) of 0.891 ± 0.004 on SICE while maintaining 2.10 M parameters (2.1 MB in INT8, 8.4 MB in FP32). Furthermore, the proposed method enables real-time inference at 31 frames per second (FPS) on embedded platforms, including the HiSilicon SS928 and Jetson Nano, demonstrating that the proposed method is an efficient and effective front-end for camera-based ADAS perception on automotive-grade edge hardware. Full article

This study introduces a training-free, self-contained adaptive low-light image enhancement (LLIE) framework driven by a metaheuristic optimization algorithm (MOA) and a context-aware dual image quality assessment (IQA) engine. Although deep-learning-based methods exhibit rapid inference, their static parameters often suffer from severe performance degradation in out-of-distribution (OOD) scenarios—such as those involving unseen sensor noise or environmental shifts. To bridge this generalization gap, the proposed framework operates within a decoupled HSV color space, specifically targeting the luminance ($V$) channel to formulate image enhancement as an instance-specific optimization task. We introduce a novel hybrid Log-Gamma mapping function that mathematically unifies the localized dark-stretching capabilities of logarithmic compression with the global dynamic range regulation of power-law gamma curves, thereby substantially expanding the expressiveness of the transformation space. To govern parameter convergence without reference images, a multi-stage Low-Light Image Discrimination (LLID) engine classifies the input frame by computing context-specific trimmed skewness residuals and global intensity means, effectively mitigating highlight biases. Under normal-light conditions, the swarm intelligence engine optimizes the Log-Gamma coefficients via the Patch-based Contrast Quality Index (PCQI) to maximize structural fidelity; conversely, under severe low-light degradations, the framework leverages the Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) to minimize spatial artifacts. Using the Marine Predators Algorithm (MPA), the framework iteratively searches the continuous bounding space to fine-tune a parameter matrix tailored exclusively to each image. Empirical evaluations across four benchmark datasets (Bicycle, DF1000, DICM, and VV) validate the effectiveness of the proposed paradigm. The proposed variant, $OLG\left(\mathrm{MPA}\right)$, secured the top average rank in internal algorithm ablation ($\overline{R}=3.10$) and achieved a competitive global average rank ($\overline{R}=2.95$) against four state-of-the-art deep networks, matching the performance of leading data-driven models. Although the evolutionary optimization loop incurs an average per-frame latency of $17.300 \mathrm{s}$, this instance-specific paradigm successfully trades instantaneous processing speed for absolute domain adaptability and predictable, artifact-free image restoration. Full article

Prolonged underwater exposure degrades reinforced concrete (RC) structures, causing chloride-induced corrosion, spalling, cracking, and rebar exposure. Timely damage identification is critical for structural safety, but conventional non-destructive testing methods face severe limitations underwater due to restricted accessibility, image degradation, and weak-textured, irregular crack boundaries. Vision-based inspection offers a promising alternative but remains constrained by underwater optical degradation. This study proposes a two-stage detection framework for underwater RC based on YOLOv13 (YOLOv13-TSDD). First, an underwater color-detail enhancement network (UCDEN) performs color correction, detail recovery, and contour reconstruction through multi-channel color enhancement and multi-level feature refinement. Second, two detection modules are introduced: a pinwheel-shaped receptive field convolution (PRFConv), improving sensitivity to directional textures and local linear structural responses in shallow layers, and a crack-aware efficient multi-scale attention (CEMA) mechanism, enabling joint channel-spatial recalibration and multi-scale focus on crack-relevant regions. A fine-grained irregular crack IoU (FID-IoU) loss function is also developed, using auxiliary boundary boxes and piecewise weighted mapping to improve bounding-box regression for irregular cracks. Experimental results demonstrate that YOLOv13-TSDD not only achieves the best overall image enhancement performance among the evaluated methods but also delivers the highest detection performance. On the constructed underwater dataset, YOLOv13-TSDD achieves Precision, Recall, and mAP@0.50 of 93.63%, 88.97%, and 94.52%, respectively, demonstrating improved performance under complex underwater conditions. Full article

Underwater object detection is a core technology for environmental perception and autonomous operation of unmanned underwater vehicles (UUVs). However, optical and acoustic sensing alone suffer from physical limitations, leading to missed and false detections in turbid, low-light, or long-range conditions. To overcome these limitations, this paper develops an acoustic–optical multimodal fusion detection module (AOMFDM) tailored for UUV deployment. The module employs dual YOLOv5 models for separate processing of sonar and optical images. An interference source quantification estimation network is introduced to extract environmental degradation features, including noise, blur, illumination, contrast, and color cast. A heterogeneous feature map matching network and a deep sparse autoencoder are further designed to achieve cross-modal alignment and fusion of acoustic and optical features. Additionally, attention mechanisms, anchor-based box annotation, and weighted boxes fusion (WBF) are incorporated to enhance detection robustness. For model training and evaluation, we construct the Underwater Sonar Detection (USD) and Underwater Optical Detection (UOD) datasets, covering diverse water qualities, illumination levels, target materials, and interference scenarios. Experimental results demonstrate that, by exploiting the complementarity of acoustic and optical modalities together with adaptive alignment strategies, the proposed module significantly boosts both detection reliability and generalization capability for UUVs in challenging underwater environments. Full article

In slow-time colorized subaperture image (CSI), anisotropic targets that reflect strongly when viewed from specific angles appear in vivid colors, which makes them stand out against isotropic background that reflects energy uniformly across all angles. It leads to more accurate annotation labels for ships, vehicles, and airplanes in SAR images and better SAR automatic target detection (ATD) performance. Unfortunately, although many port-related CSI products collected by satellite-borne SAR systems are released for free public access and could be leveraged for ship detection research, those that could support vehicle and airplane detection are rare. To investigate performance improvement in deep learning-based SAR ATD that could be brought by colored SAR images, three novel SAR-ATD frameworks are proposed for ship, vehicle, and aircraft detection, respectively. (1) Context-guided ensemble learning (CGEL) is proposed for ship detection, where state-of-the-art high-resolution colorized spotlight SAR images are exploited to enhance the visual features of ships and reduce false alarms, while the potential ship berthing/docking areas are delimited with adaptive intensity shading (AIS). (2) Context-driven SAR image recoloring and enhancement mechanism (CD-SAR-REM) is proposed to generate a context-driven color-enhanced version of the original SAR image based on AIS so that potential parking regions are highlighted. (3) Color feature-aided aircraft detection. In case that CSI products are unavailable, pseudo-color SAR images are generated based on phase congruency and the contextual information extracted by the segmentation module is used to refine the initial predictions generated by the core detection network. Experimental results show that the performance of the proposed context-driven ship, vehicle, and aircraft detection methods based on colored SAR images are superior to many state-of-the-art SAR ATD models. Full article

γ-photon tomography provides a non-contact approach for reconstructing and visualizing flow-field parameters. However, the resulting grayscale images often exhibit blurred boundaries and weak texture features, causing conventional colorization methods such as DeOldify to produce cross-region color diffusion and boundary color overflow. To address this, this paper proposes a γ-photon flow-field image colorization algorithm based on the Hybrid Swin Colorization Network (HSCN). A hybrid dual-stream encoder composed of a Swin Transformer semantic stream and a central difference convolution (CDC) gradient branch is combined with cross-stage gradient injection and a spatially gated adaptive fusion mechanism to enhance the perception of high-frequency structures at flow-field boundaries and suppress color overflow. The effectiveness of the algorithm is evaluated in terms of colorization quality and flow-field temperature-parameter inversion using γ-photon flow-field images of two CFD-simulated flow patterns, a large-scale vortical wake and a horizontal wake. The proposed method achieves PSNR, SSIM, FID, and MAE values of 38.7422, 0.9372, 10.7344, and 0.0085, respectively. Compared with DeOldify, PSNR and SSIM are improved by 24.30% and 11.89%, while FID and MAE are reduced by 42.98% and 60.47%, respectively. In addition, HSCN achieved a MAPE of 12.65% across 15 boundary and temperature-transition locations in three representative samples, compared with 31.24% for DeOldify and 28.70% for DDColor. Full article

As China’s urbanization shifts toward quality-oriented development, urban regeneration increasingly prioritizes the perceived quality of public spaces to enhance urban vitality and advance sustainable urban living. This study takes Zhengzhou’s Dongfeng Canal, a revitalized urban core waterfront, as a case to develop a human–machine collaborative analytical framework for exploring nonlinear relationships between visual environmental features and human spatial quality perception. By integrating 779 geolocated panoramic images with volunteers’ subjective rating data, this study adopts deep learning-based semantic segmentation to quantify eight objective visual indicators (e.g., greenness, color diversity, spatial structure). A random forest (RF) model links these indicators to three perceptual dimensions: scenic beauty, safety, and recreational value. Adopting explainable artificial intelligence (SHAP and PDPs), the results indicate that: (1) greenness is positively associated with positive perceptions but exhibits a significant threshold effect; (2) color diversity and waterfront accessibility substantially improve user experience, while excessive uniformity and extreme openness negatively affect perceived spatial quality. These findings challenge the simplistic linear “more-is-better” assumption in urban design and highlight the value of balanced, context-sensitive spatial interventions. This study provides evidence-based, segment-specific strategies for urban waterfront regeneration, advancing people-centered planning that integrates ecological functionality, social inclusivity, and long-term sustainability via Geospatial Artificial Intelligence (GeoAI) and geospatial analytics. Full article

Manual fruit thinning is labor-intensive and inefficient, making the development of intelligent visual detection systems a crucial approach for improving the quality and production efficiency of the pear industry. However, in natural orchard environments, young pear fruits are small in size with slender fruit stalks, and their texture and color characteristics are highly similar to those of tender branches. Furthermore, variations in illumination and occlusions caused by branches and leaves make it difficult for existing detection models to simultaneously and accurately identify fruits and fruit stalks, limiting their application in automated thinning equipment. In this study, Yuluxiang pear was selected as the research object, and image data were collected under diverse field conditions, including forward-lighting, backlighting, close-range shooting, long-range shooting and fruit overlapping. A dedicated dataset containing 3057 images was established. Based on the RT-DETR-R18 network, a lightweight and high-precision fruit–stalk synchronous detection model was proposed. Specifically, the backbone network was reconstructed by integrating GCConv with C2f modules to enhance global feature extraction for slender fruit stalks. The bottleneck structure was optimized using GCConvC3 to reduce feature degradation under occlusion conditions, and an additional 4× down-sampling P2 detection head was introduced to improve the detection capability for small targets. To fully validate the model performance and stability, three types of experiments were conducted in this study: ablation experiments, repeated experiments with different random seeds, and comparative experiments. Ablation experiments verified the cumulative performance improvements brought by the introduced modules. Repeated experiments with different random seeds were performed to explore training randomness-induced performance fluctuations, and the results demonstrated that the proposed model maintains stable overall detection accuracy with minor metric fluctuations. Comparative experiments demonstrated that the proposed model achieved a compact parameter size of only 15.97 M, with a precision of 95.0% for young pear fruit detection and an mAP50 of 83.0% for fruit stalk detection, outperforming all comparative models in overall mAP50. The training convergence curves and Grad-CAM++ visualization results further confirmed the stable optimization process and enhanced feature attention capability of the proposed model. By achieving a favorable balance between detection accuracy and model lightweightness, this approach provides effective technical support for the development of intelligent fruit thinning equipment and vision-based systems for smart pear orchards. Full article

Existing zero-shot low-light image enhancement methods often underutilize image priors, leading to noise amplification and color distortion. To address these issues, we propose a zero-shot framework for low-light image enhancement. The framework first performs illumination-aware self-supervised denoising to generate a cleaner reference image, which is then used to guide diffusion-based enhancement with a pre-trained backbone. Specifically, the denoising module uses pairwise downsampling together with the proposed illumination prior to suppress noise in dark regions. We then guide the reverse sampling of the pre-trained diffusion model with a refinement strategy operating in both the frequency and spatial domains, so that illumination enhancement and local detail refinement can be jointly achieved during sampling. At each step, Fourier-based reconstruction contributes to illumination enhancement while preserving structural information, and illumination-guided spatial adjustment further refines local brightness. Experiments on multiple benchmark datasets show that the proposed method improves illumination while preserving structural details. Full article

Rail light-strip morphology reflects the wheel-rail contact condition. Reliable automatic analysis remains difficult. The strip is narrow and has weak boundaries, while specular reflection, rail-head texture and trackside background interfere with color inspection images. This study proposes a segmentation-guided geometric method for rail light-strip abnormality analysis. An improved SegFormer jointly segments the background, rail-head and light-strip regions. A boundary detail enhancement module refines weak rail-head and light-strip contours. Focal Loss emphasizes minority and hard boundary pixels. The rail-head mask provides the geometric reference for extracting the light-strip centerline, eccentricity, width sequence and connected-component morphology. The predicted masks are ordered using the corrected mileage record. Every 1000 original-resolution rows then form a consecutive 1 m detection unit. When a geometric rule is triggered, the method reports that unit’s 1 m mileage interval together with its eccentricity, width-change or local-integrity measurement. The model achieves 95.67% mean Intersection over Union (mIoU) on 3520 annotated images. It detects 845 of 876 positive units, with 96.46% recall, 89.23% precision and 92.70% F1-score. The resulting records identify abnormal 1 m mileage intervals and report the corresponding eccentricity, width-change, or local-integrity measurements for targeted manual review. Full article

Background/Objectives: Liver metastasis after surgery for adrenocortical carcinoma (ACC) is a critical factor affecting patient prognosis; however, relevant ultrasound imaging features remain poorly characterized. This retrospective study aims to systematically describe the conventional ultrasound and contrast-enhanced ultrasound (CEUS) features of post-surgical hepatic metastases from ACC and to evaluate the clinical utility of ultrasonography in the diagnosis and follow-up. Methods: A total of 10 patients with post-surgical ACC liver metastases via ultrasound-guided liver biopsy between January 2000 and June 2026 at West China Hospital of Sichuan University were retrospectively enrolled. All patients underwent conventional ultrasound (B-mode and color Doppler flow imaging, CDFI) and CEUS. Given the small sample size, only descriptive statistics were performed, and all findings should be interpreted as exploratory. Results: All 10 patients were female (age range: 38–56 years), 70% had multiple lesions. On B-mode ultrasound, 80% of lesions appeared hypoechoic, 100% exhibited heterogeneous internal echotexture, 80% had irregular shapes, and 60% displayed well-defined margins. CDFI detected internal or perilesional blood flow signals in 90% of lesions, predominantly perilesional (50%). CEUS demonstrated arterial-phase hyperenhancement in all cases (50% heterogeneous hyperenhancement, 30% peripheral-dominant enhancement, and 20% ring-like nodular hyperenhancement), followed by rapid wash-out during the portal venous or delayed phases, with 100% of lesions showing hypoenhancement at 180 s. Conclusions: These exploratory findings suggest that post-surgical ACC liver metastases typically manifest on conventional ultrasound as hypoechoic, heterogeneous solid masses with variable margins and predominant perilesional blood flow. CEUS reveals a characteristic “fast-in, fast-out” malignant enhancement pattern. CEUS may serve as a useful adjunct to conventional imaging within a multimodal surveillance strategy, but larger prospective studies are needed to confirm its diagnostic value. Full article

Diabetic retinopathy (DR) is a common complication of diabetes and one of the leading causes of preventable vision loss worldwide. Because the manual grading of color fundus images is slow and depends on the availability of trained specialists, automated screening tools are needed. This study proposes a lightweight channel-wise refinement strategy for automatic five-class DR grading, built on a ResNet50 backbone. Two custom blocks are evaluated: CBR, which applies a 3 × 3 convolution, batch normalization, and a ReLU activation to make the channel representation more compact, and CBS, which applies a 3 × 3 convolution, batch normalization, and a SiLU activation to reinforce local spatial features. On the Diabetic Retinopathy Balanced dataset, the baseline ResNet50 reached an accuracy of 90.77%, a precision of 90.60%, a recall of 90.79%, and an F1-score of 90.64%. In the ablation study, the best configuration was ResNet50 + CBR, with an accuracy of 91.85%, a precision of 91.75%, a recall of 91.88%, and an F1-score of 91.76%. The full CBR-CBS Hybrid ResNet50 was close behind, with an accuracy of 91.81% and an F1-score of 91.71%. The CBR block accounts for most of this improvement, which suggests that channel-wise refinement helps the model separate subtle lesion patterns. These results establish lightweight channel-wise refinement (CBR) as an effective, compact, and interpretable enhancement of ResNet50 for automated five-class DR grading, delivering a consistent multi-metric gain over the baseline and accuracy competitive with the literature, which makes it a promising solution for large-scale screening. Full article

In complex orchard environments, sweet persimmons tend to grow in dense clusters and display similar coloration across different maturity stages, leading to heavy occlusion and poor inter-class color discriminability. To address these challenges, this paper presents RCPNet, a detection network tailored for such field conditions. The model integrates a Rectangular Self-Calibration Module (RCM) and a Context Feature Calibration Gating (CFCG) module. RCM strengthens axial context capture, while CFCG improves feature calibration; together they reduce local feature ambiguity and help reconstruct missing information in occluded regions. For distinguishing fruits at different ripening stages that share similar colors, a Parallelized Patch-aware Attention (PPA) detection head is adopted. By leveraging self-attention and multi-branch strategies, this head suppresses feature degradation and notably enhances sensitivity to color contrast. Experiments on sweet persimmon images show that RCPNet improves mean Average Precision (mAP) by 2.7 percentage points and mAP@0.5:0.95 by 3.7 percentage points over the baseline, reaching 93.6% detection accuracy for immature fruits. Ablation studies and comparisons with mainstream detectors indicate that the proposed model, though slightly heavier than lightweight detectors of analogous capacity, surpasses the accuracy of a larger small-scale counterpart and exhibits satisfactory robustness. Strong performance on a self-collected flat jujube dataset further confirms its generalization ability. The method delivers highly accurate detection for occluded and near-color fruits, providing technical support for precise fruit recognition and automated picking. Full article