Search Results (92)

Edge detection is a key building block in real-time image-processing applications such as drone-based infrastructure inspection, autonomous navigation, and remote sensing. However, its computational cost remains a challenge for resource-constrained embedded systems. This work presents a hardware-accelerated edge detection architecture based on a homogeneous 2D-mesh Network-on-Chip (NoC) integrating systolic arrays to efficiently perform the convolution operations required by the Sobel filter. The proposed architecture was first developed and validated as a 3 × 3 mesh prototype on FPGA (Xilinx Zynq-7000, Zynq-7010, XC7Z010-CLG400A, Zybo board, utilizing 26,112 LUTs, 24,851 flip-flops, and 162 DSP blocks), achieving a throughput of 8.8 Gb/s with a power consumption of 0.79 W at 100 MHz. Building upon this validated prototype, a reduced 2 × 2 node cluster with 14-bit word width was subsequently synthesized at the physical level as a proof-of-concept using the OpenLane RTL-to-GDSII open-source flow targeting the SkyWater 130 nm PDK (sky130A). Post-layout analysis confirms the manufacturability of the design, with a total power consumption of 378 mW and compliance with timing constraints, demonstrating the feasibility of mapping the proposed architecture to silicon and its suitability for drone-based infrastructure monitoring applications. Full article

The rapid development of intelligent transportation systems and autonomous driving technologies has made visual perception a key component in ensuring safety and improving efficiency in complex traffic environments. As a core task in visual perception, object detection directly affects the reliability of downstream modules such as path planning and decision control. However, adverse weather conditions (e.g., fog, rain, and snow) significantly degrade image quality—causing texture blurring, reduced contrast, and increased noise—which in turn weakens the robustness of traditional detection models and raises potential traffic safety risks. To address this challenge, this paper proposes an enhanced object detection framework, ECL-YOLOv11 (Edge-enhanced, Context-guided, and Lightweight YOLOv11), designed to improve detection accuracy and real-time performance under adverse weather conditions, thereby providing a reliable solution for in-vehicle perception systems. The ECL-YOLOv11 architecture integrates three key modules: (1) a Convolutional Edge-enhancement (CE) module that fuses edge features extracted by Sobel operators with convolutional features to explicitly retain boundary and contour information, thereby alleviating feature degradation and improving localization accuracy under low-visibility conditions; (2) a Context-guided Multi-scale Fusion Network (AENet) that enhances perception of small and distant objects through multi-scale feature integration and context modeling, improving semantic consistency and detection stability in complex scenes; and (3) a Lightweight Shared Convolutional Detection Head (LDHead) that adopts shared convolutions and GroupNorm normalization to optimize computational efficiency, reduce inference latency, and satisfy the real-time requirements of on-board systems. Experimental results show that ECL-YOLOv11 achieves mAP@50 and mAP@50–95 values of 62.7% and 40.5%, respectively, representing improvements of 1.3% and 0.8% over the baseline YOLOv11, while the Precision reaches 73.1%. The model achieves a balanced trade-off between accuracy and inference speed, operating at 237.8 FPS on standard hardware. Ablation studies confirm the independent effectiveness of each proposed module in feature enhancement, multi-scale fusion, and lightweight detection, while their integration further improves overall performance. Qualitative visualizations demonstrate that ECL-YOLOv11 maintains high-confidence detections across varying motion states and adverse weather conditions, avoiding category confusion and missed detections. These results indicate that the proposed framework provides a reliable and adaptable foundation for all-weather perception in autonomous driving systems, ensuring both operational safety and real-time responsiveness. Full article

Biomedical imaging plays a critical role in medical diagnostics and research, yet image noise remains a significant challenge that hinders accurate analysis. To address this issue, we propose BDNet, a real-time biomedical image denoising network optimized for enhancing gradient and high-frequency information while effectively suppressing noise. The network adopts a lightweight U-Net-inspired encoder–decoder architecture, incorporating a Convolutional Block Attention Module at the bottleneck to refine spatial and channel-wise feature extraction. A novel gradient-based loss function—combining Sobel operator-derived gradient loss with L1, L2, and LSSIM losses—ensures faithful preservation of fine structural details. Extensive experiments on the Fluorescence Microscopy Denoising (FMD) dataset demonstrate that BDNet achieves state-of-the-art performance across multiple metrics, including PSNR, RMSE, SSIM, and LPIPS, outperforming both convolutional and Transformer-based models in accuracy and efficiency. With its superior denoising capability and real-time inference speed, BDNet provides an effective and practical solution for improving biomedical image quality, particularly in fluorescence microscopy applications. Full article

Color-to-grayscale conversion is a fundamental preprocessing task with widespread applications in digital printing, electronic ink displays, medical imaging, and artistic photo stylization. A primary challenge in this domain is to simultaneously preserve global luminance distribution and local contrast. To address this, we propose an adaptive conversion method centered on a novel objective function that integrates information entropy with Edge Content (EC), a metric for local gradient information. The key advantage of our approach is its ability to generate grayscale results that maintain both rich overall contrast and fine-grained local details. Compared with previous adaptive linear methods, our approach demonstrates superior qualitative and quantitative performance. Furthermore, by eliminating the need for computationally expensive edge detection, the proposed algorithm provides an effective solution to the color-to-grayscale conversion. Full article

Accurate 3D medical image segmentation is crucial for knowledge-driven clinical decision-making and computer-aided diagnosis. However, current deep learning methods often fail to effectively integrate local structural details from Convolutional Neural Networks (CNNs) with global semantic context from Transformers due to semantic inconsistency and poor cross-scale feature alignment. To address this, Progressive Query Aggregation Network (PQAN), a novel framework that incorporates knowledge-guided feature interaction mechanisms, is proposed. PQAN employs two complementary query modules: Structural Feature Query, which uses anatomical morphology for boundary-aware representation, and Content Feature Query, which enhances semantic alignment between encoding and decoding stages. To enhance texture perception, a Texture Attention (TA) module based on Sobel operators adds directional edge awareness and fine-detail enhancement. Moreover, a Progressive Aggregation Strategy with Forward and Backward Cross-Stage Attention gradually aligns and refines multi-scale features, thereby reducing semantic deviations during CNN-Transformer fusion. Experiments on public benchmarks demonstrate that PQAN outperforms state-of-the-art models in both global accuracy and boundary segmentation. On the BTCV and FLARE datasets, PQAN had average Dice scores of 0.926 and 0.816, respectively. These results demonstrate PQAN’s ability to capture complex anatomical structures, small targets, and ambiguous organ boundaries, resulting in an interpretable and scalable solution for real-world clinical deployment. Full article

Semantic segmentation of high-resolution remote sensing images remains a challenging task due to the intricate spatial structures, scale variability, and semantic ambiguity among ground objects. Moreover, the reliable delineation of fine-grained boundaries continues to impose difficulties on existing CNN- and transformer-based models, particularly in heterogeneous urban and rural environments. In this study, we propose GPRNet, a novel geometry-aware segmentation framework that leverages geometric priors and cross-stage semantic alignment for more precise land-cover classification. Central to our approach is the Geometric Prior-Refined Block (GPRB), which learns directional derivative filters, initialized with Sobel-like operators, to generate edge-aware strength and orientation maps that explicitly encode structural cues. These maps are used to guide structure-aware attention modulation, enabling refined spatial localization. Additionally, we introduce the Mutual Calibrated Fusion Module (MCFM) to mitigate the semantic gap between encoder and decoder features by incorporating cross-stage geometric alignment and semantic enhancement mechanisms. Extensive experiments conducted on the ISPRS Potsdam and LoveDA datasets validate the effectiveness of the proposed method, with GPRNet achieving improvements of up to 1.7% mIoU on Potsdam and 1.3% mIoU on LoveDA over strong recent baselines. Furthermore, the model maintains competitive inference efficiency, suggesting a favorable balance between accuracy and computational cost. These results demonstrate the promising potential of geometric-prior integration and mutual calibration in advancing semantic segmentation in complex environments. Full article

Accurate semantic segmentation of remote sensing images is crucial for geographical studies. However, mainstream segmentation methods, primarily based on Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), often fail to effectively capture edge features, leading to incomplete image feature representation and missing edge information. Moreover, existing approaches generally overlook the modeling of relationships between channel and spatial dimensions, restricting effective interactions and consequently limiting the comprehensiveness and diversity of feature representation. To address these issues, we propose an Edge-Fused Multidimensional Attention Network (EFMANet). Specifically, we employ the Sobel edge detection operator to obtain rich edge information and introduce an Edge Fusion Module (EFM) to fuse the downsampled features of the original and edge-detected images, thereby enhancing the model’s ability to represent edge features and surrounding pixels. Additionally, we propose a Multi-Dimensional Collaborative Fusion Attention (MCFA) Module to effectively model spatial and channel relationships through multi-dimensional feature fusion and integrate global and local information via an attention mechanism. Extensive comparative and ablation experiments on the Vaihingen and Potsdam datasets from the International Society for Photogrammetry and Remote Sensing (ISPRS), as well as the Land Cover Domain Adaptation (LoveDA) dataset, demonstrate that our proposed EFMANet achieves superior performance compared to existing state-of-the-art methods. Full article

Object detection technology plays a vital role in monitoring the growth status of aquaculture organisms and serves as a key enabler for the automated robotic capture of target species. Existing models for underwater biological detection often suffer from low accuracy and high model complexity. To address these limitations, we propose AOD-YOLO—an enhanced model based on YOLOv11s. The improvements are fourfold: First, the SPFE (Sobel and Pooling Feature Enhancement) module incorporates Sobel operators and pooling operations to effectively extract target edge information and global structural features, thereby strengthening feature representation. Second, the RGL (RepConv and Ghost Lightweight) module reduces redundancy in intermediate feature mappings of the convolutional neural network, decreasing parameter size and computational cost while further enhancing feature extraction capability through RepConv. Third, the MDCS (Multiple Dilated Convolution Sharing Module) module replaces the SPPF structure by integrating parameter-shared dilated convolutions, improving multi-scale target recognition. Finally, we upgrade the C2PSA module to C2PSA-M (Cascade Pyramid Spatial Attention—Mona) by integrating the Mona mechanism. This upgraded module introduces multi-cognitive filters to enhance visual signal processing and employs a distribution adaptation layer to optimize input information distribution. Experiments conducted on the URPC2020 and RUOD datasets demonstrate that AOD-YOLO achieves an accuracy of 86.6% on URPC2020, representing a 2.6% improvement over YOLOv11s, and 88.1% on RUOD, a 2.4% increase. Moreover, the model maintains relatively low complexity with only 8.73 M parameters and 21.4 GFLOPs computational cost. Experimental results show that our model achieves high accuracy for aquaculture targets while maintaining low complexity. This demonstrates its strong potential for reliable use in intelligent aquaculture monitoring systems. Full article

Surface defects on stay cables are primary contributors to wire corrosion and breakage. Traditional manual inspection methods are inefficient, inaccurate, and pose safety risks. Recently, cable-climbing robots have shown significant potential for surface defect detection, but existing designs are constrained by large size, limited operational speed, and complex installation, restricting their field applicability. This study presents an intelligent robotic system for detecting cable surface defects. The system features a dual-wheel driving mechanism, and a computer vision–based defect recognition framework is proposed. Image preprocessing techniques, including histogram equalization, Gaussian filtering, and Sobel edge detection, are applied. Interfering information, such as sheath edges and rain lines, is removed using the Hough Line Detection Algorithm and template matching. The geometry of identified defects is automatically calculated using connected component analysis and contour extraction. The system’s performance is validated through laboratory and field tests. The results demonstrate easy installation, adaptability to cable diameters from 70 mm to 270 mm and inclination angles from 0° to 90°, and a maximum speed of 26 m/min. The proposed defect recognition framework accurately identifies typical defects and captures their morphological characteristics, achieving an average precision of 92.37%. Full article

The images acquired from near infrared cameras can contain thermal noise, which degrades the quality of the images. The quality of the images obtained from underwater environments suffer from the complex hydrological environment. All these issues make the profile-extraction in these images a difficult task. In this work, two non-learning systems are built for making filters by using wavelets transform combined with simple functions. They can be shown to extract profiles in the images acquired from the near infrared camera and underwater environment. Furthermore, they are useful for low-light image enhancement, edge/array detection, and image fusion. The increase in the measurement by entropy can be found by enhancing the scale of the filters. When processing the near infrared images, the values of running time, the memory usage, Signal-to-Noise Ratio (SNR), and Peak Signal-to-Noise Ratio (PSNR) are generally smaller in the operators of Canny, Roberts, Log, Sobel, and Prewitt than those in the Atanh filter and Sech filter. When processing the underwater images, the values of running time, the memory usage, SNR, and PSNR are generally smaller in Sobel operator than those in the Atanh filter and Sech filter. When processing the low-light images, it can be seen that the Atanh filter obtains the highest values of the running time and the memory usage compared to the filter based on the Retinex model, the Sech filter, and a matched filter. Our designed filters require little computational resources comparing to learning-based ones and hold the merits of being multifunctional, which may be useful for advanced imaging in the field of bio-medical engineering. Full article

Monocular depth estimation is an essential component in computer vision that enables 3D scene understanding, with critical applications in autonomous driving and augmented reality. This paper proposes a lightweight self-supervised framework from single RGB images for multi-scale feature extraction and artifact elimination in monocular depth estimation (MsGf). The proposed framework first designs a Cross-Dimensional Multi-scale Feature Extraction (CDMs) module. The CDMs module combines parallel multi-scale convolution with sequential feature convolutions to achieve multi-scale feature extraction with minimal parameters. Additionally, a Sobel Edge Perception-Guided Filtering (SEGF) module is proposed. The SEGF module uses the Sobel operator to decompose the features into horizontal direction features and vertical direction features, and then generates the filter kernel through two steps of filtering to effectively suppress artifacts and better capture structural and edge features. A large number of ablation experiments and comparative experiments on the KITTI and Make3D datasets demonstrate that the MsGf with only 0.8 M parameters can achieve better performance than the current most advanced methods. Full article

Although Lempel–Ziv complexity (LZC) can reflect changes in object characteristics by measuring changes in independent patterns in the signal, it can only be applied to one-dimensional time series and cannot be directly applied to two-dimensional images. To address this issue, this paper proposed a two-dimensional Lempel–Ziv complexity by combining the concept of local receptive field in convolutional neural networks. This extends the application scenario of LZC from one-dimensional time series to two-dimensional images, further broadening the scope of application of LZC. First, the pixels and size of the image were normalized. Then, the image was encoded according to the sorting of normalized values within the 4 × 4 region. Next, the encoding result of the image was rearranged into a vector by row. Finally, the Lempel–Ziv complexity of the image could be obtained based on the rearranged vector. The proposed method was further used for defect detection in conjunction with the dilation operator and Sobel operator, and validated by two practical cases. The results showed that the proposed method can effectively identify independent pattern changes in images and can be used for defect detection. The accuracy rate of defect detection can reach 100%. Full article

Effective management of Micropterus salmoides resources requires accurate assessment of their abundance and distribution. Fisheries acoustics is a key method for such evaluations, yet its application is limited by insufficient target strength (TS) data. This study combines the Sobel edge detection technique with the Kirchhoff ray-mode model to estimate the TS of Micropterus salmoides cultured in Guangdong, China, and validates the results through in situ measurements. The relationships between TS and fish body length were established at 38 kHz, 70 kHz, 120 kHz, and 200 kHz. At 200 kHz, the average in situ TS was –42.41 dB, with a fitted formula of TS = 32.00 lgL − 88.24. Further validation was performed using time- and frequency-domain analyses of echo signals. The results show that TS increases with swim bladder volume, indicating its dominant influence. The relationship between TS and frequency is nonlinear and affected by the swim bladder angle, swimming posture, and behavioral patterns. This study also improves the computational efficiency of the Kirchhoff ray-mode model. Overall, it provides essential parameters for acoustic stock assessment of Micropterus salmoides, providing a scientific basis for their sustainable management and conservation. Full article

The harmonized multi-sensor satellite data assists users by providing seamless analysis-ready data with enhanced temporal resolution. The Harmonized Landsat Sentinel (HLS) product has gained popularity due to the seamless integration of Landsat OLI and Sentinel-2 MSI, achieving a temporal resolution of 2.8 to 3.5 days. However, applications that require monitoring intervals of less than three days or cloudy data can limit the usage of HLS data. Gaofen-1 (GF-1) Wide Field of View (WFV) data provides the capacity further to enhance the data availability by harmonization with HLS. In this study, GF-1/WFV data is harmonized with HLS by employing deep learning-based conditional Generative Adversarial Networks (cGANs). The harmonized WFV data with HLS provides an average temporal resolution of 1.5 days (ranging from 1.2 to 1.7 days), whereas the temporal resolution of HLS varies from 2.8 to 3.5 days. This enhanced temporal resolution will benefit applications that require frequent monitoring. Various processes are employed in HLS to achieve seamless products from the Operational Land Imager (OLI) and Multispectral Imager (MSI). This study applies 6S atmospheric correction to obtain GF-1/WFV surface reflectance data, employs MFC cloud masking, resamples the data to 30 m, and performs geographical correction using AROP relative to HLS data, to align preprocessing with HLS workflows. Harmonization is achieved without using BRDF normalization and bandpass adjustment like in the HLS workflows; instead, cGAN learns cross-sensor reflectance mapping by utilizing a U-Net generator and a patchGAN discriminator. The harmonized GF-1/WFV data were compared to the reference HLS data using various quality indices, including SSIM, MBE, and RMSD, across 126 cloud-free validation tiles covering various land covers and seasons. Band-wise scatter plots, histograms, and visual image color quality were compared. All these indices, including the Sobel filter, histograms, and visual comparisons, indicated that the proposed method has effectively reduced the spectral discrepancies between the GF-1/WFV and HLS data. Full article

Focusing on the problem of insufficient detection accuracy caused by blurred target boundaries, variable scales, and severe noise interference in side-scan sonar images, this paper proposes a high-precision detection network named ESL-YOLO, which integrates edge perception and adaptive quality assessment. Firstly, an Edge Fusion Module (EFM) is designed, which integrates the Sobel operator into depthwise separable convolution. Through a dual-branch structure, it realizes effective fusion of edge features and spatial features, significantly enhancing the ability to recognize targets with blurred boundaries. Secondly, a Self-Calibrated Dual Attention (SCDA) Module is constructed. By means of feature cross-calibration and multi-scale channel attention fusion mechanisms, it achieves adaptive fusion of shallow details and deep-rooted semantic content, improving the detection accuracy for small-sized targets and targets with elaborate shapes. Finally, a Location Quality Estimator (LQE) is introduced, which quantifies localization quality using the statistical characteristics of bounding box distribution, effectively reducing false detections and missed detections. Experiments on the SIMD dataset show that the mAP@0.5 of ESL-YOLO reaches 84.65%. The precision and recall rate reach 87.67% and 75.63%, respectively. Generalization experiments on additional sonar datasets further validate the effectiveness of the proposed method across different data distributions and target types, providing an effective technical solution for side-scan sonar image target detection. Full article