Search Results (1,569)

In autonomous-driving real-time semantic segmentation, simultaneously maximizing accuracy, minimizing model size, and sustaining high inference speed remains challenging. This tripartite demand poses significant constraints on the design of lightweight neural networks, as conventional frameworks often suffer from a trade-off between computational efficiency and feature representation capability, thereby limiting their practical deployment in resource-constrained autonomous driving systems. We introduce ISANet, an information supplementary aggregation framework that markedly elevates segmentation accuracy without sacrificing frame rate. ISANet integrates three key components: (i) the Spatial-Supplementary Lightweight Bottleneck Unit (SLBU) that splits channels and employs compensatory branches to extract highly expressive features with minimal parameters; (ii) the Missing Spatial Information Recovery Branch (MSIRB) that recovers spatial details lost during feature extraction; and (iii) the Object Boundary Feature Attention Module (OBFAM) that fuses multi-stage features and strengthens inter-layer information interaction. Evaluated on Cityscapes and CamVid, ISANet attains 76.7% and 73.8% mIoU, respectively, while delivering 58 FPS and 90 FPS with only 1.37 million parameters. Full article

To address the challenges of small target detection in UAV aerial images—such as difficulty in feature extraction, complex background interference, high miss rates, and stringent real-time requirements—this paper proposes an innovative model series named SRTSOD-YOLO, based on YOLO11. The backbone network incorporates a Multi-scale Feature Complementary Aggregation Module (MFCAM), designed to mitigate the loss of small target information as network depth increases. By integrating channel and spatial attention mechanisms with multi-scale convolutional feature extraction, MFCAM effectively locates small objects in the image. Furthermore, we introduce a novel neck architecture termed Gated Activation Convolutional Fusion Pyramid Network (GAC-FPN). This module enhances multi-scale feature fusion by emphasizing salient features while suppressing irrelevant background information. GAC-FPN employs three key strategies: adding a detection head with a small receptive field while removing the original largest one, leveraging large-scale features more effectively, and incorporating gated activation convolutional modules. To tackle the issue of positive-negative sample imbalance, we replace the conventional binary cross-entropy loss with an adaptive threshold focal loss in the detection head, accelerating network convergence. Additionally, to accommodate diverse application scenarios, we develop multiple versions of SRTSOD-YOLO by adjusting the width and depth of the network modules: a nano version (SRTSOD-YOLO-n), small (SRTSOD-YOLO-s), medium (SRTSOD-YOLO-m), and large (SRTSOD-YOLO-l). Experimental results on the VisDrone2019 and UAVDT datasets demonstrate that SRTSOD-YOLO-n improves the mAP@0.5 by 3.1% and 1.2% compared to YOLO11n, while SRTSOD-YOLO-l achieves gains of 7.9% and 3.3% over YOLO11l, respectively. Compared to other state-of-the-art methods, SRTSOD-YOLO-l attains the highest detection accuracy while maintaining real-time performance, underscoring the superiority of the proposed approach. Full article

Time-domain signal models have been widely applied to single-channel music source separation tasks due to their ability to overcome the limitations of fixed spectral representations and phase information loss. However, the high acoustic similarity and synchronous temporal evolution between vocals and accompaniment make accurate separation challenging for existing time-domain models. These challenges are mainly reflected in two aspects: (1) the lack of a dynamic mechanism to evaluate the contribution of each source during feature fusion, and (2) difficulty in capturing fine-grained temporal details, often resulting in local artifacts in the output. To address these issues, we propose an attention-driven time-domain convolutional network for vocal and accompaniment source separation. Specifically, we design an embedding attention module to perform adaptive source weighting, enabling the network to emphasize components more relevant to the target mask during training. In addition, an efficient convolutional block attention module is developed to enhance local feature extraction. This module integrates an efficient channel attention mechanism based on one-dimensional convolution while preserving spatial attention, thereby improving the ability to learn discriminative features from the target audio. Comprehensive evaluations on public music datasets demonstrate the effectiveness of the proposed model and its significant improvements over existing approaches. Full article

Traffic sign detection is a crucial task for autonomous driving perception systems, as it directly impacts vehicle path planning and safety decisions. Existing algorithms face challenges such as feature information attenuation and model lightweighting requirements in the detection of small traffic signs at long distances. To address these issues, this paper proposes a dual-pooling dynamic grouping (DPDG) module. This module dynamically adjusts the number of groups to adapt to different input features, combines global average pooling and max pooling to enhance channel attention representation, and uses a lightweight 3 × 3 convolution-based spatial branch to generate spatial weights. Based on a hierarchical optimization strategy, the DPDG module is integrated into the YOLOv10n network. Experimental results on the traffic sign dataset demonstrate a significant improvement in the performance of the YOLO-DPDG network: Compared to the baseline YOLOv10n model, mAP@0.5 and mAP@0.5:0.95 improved by 8.77% and 10.56%, respectively, while precision and recall were enhanced by 6.16% and 6.62%, respectively. Additionally, inference speed (FPS) increased by 11.1%, with only a 4.89% increase in model parameters. Compared to the YOLOv10-Small model, this method achieves a similar detection accuracy while reducing the number of model parameters by 64.83%. This study provides a more efficient and lightweight solution for edge-based traffic sign detection. Full article

Accurate segmentation of medical images is essential for clinical diagnosis and treatment planning. Hyperspectral imaging (HSI), with its rich spectral information, enables improved tissue characterization and structural localization compared with traditional grayscale or RGB imaging. However, the effective modeling of both spatial and spectral dependencies remains a significant challenge, particularly in small-scale medical datasets. In this study, we propose GSA-Net, a 3D segmentation framework that integrates Gated Spectral-Axial Attention (GSA) to capture long-range interband dependencies and enhance spectral feature discrimination. The GSA module incorporates multilayer perceptrons (MLPs) and adaptive LayerScale mechanisms to enable the fine-grained modulation of spectral attention across feature channels. We evaluated GSA-Net on a hyperspectral cholangiocarcinoma (CCA) dataset, achieving an average Intersection over Union (IoU) of 60.64 ± 14.48%, Dice coefficient of 74.44 ± 11.83%, and Hausdorff Distance of 76.82 ± 42.77 px. It outperformed state-of-the-art baselines. Further spectral analysis revealed that informative spectral bands are widely distributed rather than concentrated, and full-spectrum input consistently outperforms aggressive band selection, underscoring the importance of adaptive spectral attention for robust hyperspectral medical image segmentation. Full article

Small surface defects in printed circuit boards (PCBs) severely affect the reliability of electronic devices, making PCB surface defect detection crucial for ensuring the quality of electronic products. However, the existing detection methods often struggle with insufficient accuracy and the inherent trade-off between detection precision and inference speed. To address these problems, we propose a novel ESDM-HNN-YOLO (EH-YOLO) network based on the improved YOLOv10 for efficient detection of small PCB defects. Firstly, an enhanced spatial-depth module (ESDM) is designed, which transforms spatial-dimensional features into depth-dimensional representations while integrating spatial attention module (SAM) and channel attention module (CAM) to highlight critical features. This dual mechanism not only effectively suppresses feature loss in micro-defects but also significantly enhances detection accuracy. Secondly, a hybrid neck network (HNN) is designed, which optimizes the speed–accuracy balance through hierarchical architecture. The hierarchical structure uses a computationally efficient weighted bidirectional feature pyramid network (BiFPN) to enhance multi-scale feature fusion of small objects in the shallow layer and uses a path aggregation network (PAN) to prevent feature loss in the deeper layer. Comprehensive evaluations on benchmark datasets (PCB_DATASET and DeepPCB) demonstrate the superior performance of EH-YOLO, achieving mAP@50-95 scores of 45.3% and 78.8% with inference speeds of 166.67 FPS and 158.73 FPS, respectively. These results significantly outperform existing approaches in both accuracy and processing efficiency. Full article

Addressing the challenges of multi-scene precision pesticide application for field broccoli crops and computational limitations of edge devices, this study proposes a lightweight broccoli detection method named DWG-YOLOv8, based on an improved YOLOv8s architecture. Firstly, Ghost Convolution is introduced into the C2f module, and the standard CBS module is replaced with Depthwise Separable Convolution (DWConv) to reduce model parameters and computational load during feature extraction. Secondly, a CDSL module is designed to enhance the model’s feature extraction capability. The CBAM attention mechanism is incorporated into the Neck network to strengthen the extraction of channel and spatial features, enhancing the model’s focus on the target. Experimental results indicate that compared to the original YOLOv8s, the DWG-YOLOv8 model has a size decreased by 35.6%, a processing time reduced by 1.9 ms, while its precision, recall, and mean Average Precision (mAP) have increased by 1.9%, 0.9%, and 3.4%, respectively. In comparative tests on complex background images, DWG-YOLOv8 showed reductions of 1.4% and 16.6% in miss rate and false positive rate compared to YOLOv8s. Deployed on edge devices using field-collected data, the DWG-YOLOv8 model achieved a comprehensive recognition accuracy of 96.53%, representing a 5.6% improvement over YOLOv8s. DWG-YOLOv8 effectively meets the lightweight requirements for accurate broccoli recognition in complex field backgrounds, providing technical support for object detection in intelligent precision pesticide application processes for broccoli. Full article

Photovoltaic (PV) fault detection faces significant challenges in distinguishing subtle defects from complex backgrounds while maintaining reliability across diverse environmental conditions. Traditional approaches struggle with scalability and accuracy limitations, particularly when detecting electrical damage, physical defects, and environmental soiling in thermal imagery. This paper presents SolarFaultAttentionNet, a novel dual-attention deep learning framework that integrates channel-wise and spatial attention mechanisms within a multi-path CNN architecture for enhanced PV fault classification. The approach combines comprehensive data augmentation strategies with targeted attention modules to improve feature discrimination across six fault categories: Electrical-Damage, Physical-Damage, Snow-Covered, Dusty, Bird-Drop, and Clean. Experimental validation on a dataset of 885 images demonstrates that SolarFaultAttentionNet achieves 99.14% classification accuracy, outperforming state-of-the-art models by 5.14%. The framework exhibits perfect detection for dust accumulation (100% across all metrics) and robust electrical damage detection (99.12% F1 score) while maintaining an optimal sensitivity (98.24%) and specificity (99.91%) balance. The computational efficiency (0.0160 s inference time) and systematic performance improvements establish SolarFaultAttentionNet as a practical solution for automated PV monitoring systems, enabling reliable fault detection critical for maximizing energy production and minimizing maintenance costs in large-scale solar installations. Full article

Taiwan, located in a subtropical region, has experienced continuous warming in recent years, making the Urban Heat Island (UHI) effect one of its most pressing environmental challenges. Importantly, UHI is not confined to Taipei, the most populous city, but is also present in other metropolitan areas. This study investigates UHI effects in the five largest cities in Taiwan and examines climate-related news attention using web crawling. Cross-city comparisons are further conducted through Urban Heat Island Intensity (UHII) and correlation analysis. The results reveal that Taipei records the highest number of UHI-related news reports, particularly during summer, and its UHII is about 1.5 °C to 3 °C higher than in the other four cities. In addition, UHII in Taipei shows a marked increase between 2021 and 2023, suggesting a worsening impact on citizens’ living conditions. Meanwhile, news coverage in Taipei dominates nationwide attention, creating a spatially uneven distribution of media focus. This imbalance may undermine efforts to promote UHI mitigation and adaptation strategies in cities outside Taipei. Overall, this study highlights that UHI is not solely a problem of Taipei but a widespread issue across Taiwan’s urban areas. The findings provide useful references for policymakers and government agencies, emphasizing the need for equitable attention and broader public engagement through media channels to raise awareness and foster comprehensive climate adaptation actions. Full article

To address the challenges of poor model generalization and suboptimal recognition accuracy stemming from limited and imbalanced sample sizes in tomato leaf disease identification, this study proposes a novel recognition strategy. This approach synergistically combines an enhanced image augmentation method based on generative adversarial networks with a lightweight deep learning model. Initially, an Atrous Spatial Pyramid Pooling (ASPP) module is integrated into the CycleGAN framework. This integration enhances the generator’s capacity to model multi-scale pathological lesion features, thereby significantly improving the diversity and realism of synthesized images. Subsequently, the Convolutional Block Attention Module (CBAM), incorporating both channel and spatial attention mechanisms, is embedded into the MobileNetV4 architecture. This enhancement boosts the model’s ability to focus on critical disease regions. Experimental results demonstrate that the proposed ASPP-CycleGAN significantly outperforms the original CycleGAN across multiple disease image generation tasks. Furthermore, the developed CBAM-MobileNetV4 model achieves a remarkable average recognition accuracy exceeding 97% for common tomato diseases, including early blight, late blight, and mosaic disease, representing a 1.86% improvement over the baseline MobileNetV4. The findings indicate that the proposed method offers exceptional data augmentation capabilities and classification performance under small-sample learning conditions, providing an effective technical foundation for the intelligent identification and control of tomato leaf diseases. Full article

Flange bolts are vital fasteners in civil, mechanical, and aerospace structures, where preload stability directly affects overall safety. Conventional methods for bolt loosening detection often suffer from missed detections, weak feature representation, and insufficient cross-scale fusion under complex backgrounds. This paper presents an integrated detection and angle estimation framework using a lightweight deep learning detection network. A MobileViT backbone is employed to balance local texture with global context. In the spatial pyramid pooling stage, large separable convolutional kernels are combined with a channel and spatial attention mechanism to highlight discriminative features while suppressing noise. Together with content-aware upsampling and bidirectional multi-scale feature fusion, the network achieves high accuracy in detecting small and low-contrast targets while maintaining real-time performance. For angle estimation, the framework adopts an efficient training-free pipeline consisting of oriented FAST and rotated BRIEF feature detection, approximate nearest neighbor matching, and robust sample consensus fitting. This approach reliably removes false correspondences and extracts stable rotation components, maintaining success rates between 85% and 93% with an average error close to one degree, even under reflection, blur, or moderate viewpoint changes. Experimental validation demonstrates strong stability in detection and angular estimation under varying illumination and texture conditions, with a favorable balance between computational efficiency and practical applicability. This study provides a practical, intelligent, and deployable solution for bolt loosening detection, supporting the safe operation of large-scale equipment and infrastructure. Full article

This paper presents a dual-structured convolutional neural network (CNN) for image classification, which integrates two parallel branches: CNN-A with spatial attention and CNN-B with channel attention. The spatial attention module in CNN-A dynamically emphasizes discriminative regions by aggregating channel-wise information, while the channel attention mechanism in CNN-B adaptively recalibrates feature channel importance. The extracted features from both branches are fused through concatenation, enhancing the model’s representational capacity by capturing complementary spatial and channel-wise dependencies. Extensive experiments on a 12-class image dataset demonstrate the superiority of the proposed model over state-of-the-art methods, achieving 98.06% accuracy, 96.00% precision, and 98.01% F1-score. Despite a marginally longer training time, the model exhibits robust convergence and generalization, as evidenced by stable loss curves and high per-class recognition rates (>90%). The results validate the efficacy of dual attention mechanisms in improving feature discrimination for complex image classification tasks. Full article

Accurate real-time detection of blueberry maturity is vital for automated harvesting. However, existing methods often fail under occlusion, variable lighting, and dense fruit distribution, leading to reduced accuracy and efficiency. To address these challenges, we designed a lightweight deep learning framework that integrates improved feature extraction, attention-based fusion, and progressive transfer learning to enhance robustness and adaptability To overcome these challenges, we propose BMDNet-YOLO, a lightweight model based on an enhanced YOLOv8n. The backbone incorporates a FasterPW module with parallel convolution and point-wise weighting to improve feature extraction efficiency and robustness. A coordinate attention (CA) mechanism in the neck enhances spatial-channel feature selection, while adaptive weighted concatenation ensures efficient multi-scale fusion. The detection head employs a heterogeneous lightweight structure combining group and depthwise separable convolutions to minimize parameter redundancy and boost inference speed. Additionally, a three-stage transfer learning framework (source-domain pretraining, cross-domain adaptation, and target-domain fine-tuning) improves generalization. Experiments on 8250 field-collected and augmented images show BMDNet-YOLO achieves 95.6% mAP@0.5, 98.27% precision, and 94.36% recall, surpassing existing baselines. This work offers a robust solution for deploying automated blueberry harvesting systems. Full article

Lane detection is a fundamental component of perception systems in autonomous driving. Despite significant progress in this area, existing methods still face challenges in complex scenarios such as abnormal weather, occlusions, and curved roads. These situations typically demand the integration of both the global semantic context and local visual features to predict the lane position and shape. This paper presents ORANet, an enhanced lane detection framework built upon the baseline CLRNet. ORANet incorporates two novel modules: Enhanced Coordinate Attention (EnCA) and Channel–Spatial Shuffle Attention (CSSA). EnCA models long-range lane structures while effectively capturing global semantic information, whereas CSSA strengthens the precise extraction of local features and provides optimized inputs for EnCA. These components operate in hierarchical synergy, collectively establishing a complete enhancement pathway from refined local feature extraction to efficient global feature fusion. The experimental results demonstrate that ORANet achieves greater performance stability than CLRNet in complex roadway scenarios. Notably, under shadow conditions, ORANet achieves an F1 score improvement of nearly 3% over CLRNet. These results highlight the potential of ORANet for reliable lane detection in real-world autonomous driving environments. Full article

Impurities in polypropylene random copolymer (PPR) raw materials can seriously affect the performance of the final product, and efficient and accurate impurity detection is crucial to ensure high production quality. In order to solve the problems of high small-target miss rates, weak anti-interference ability, and difficulty in balancing accuracy and speed in existing detection methods used in complex industrial scenarios, this paper proposes an enhanced machine vision detection algorithm based on YOLOv11. Firstly, the FasterLDConv module dynamically adjusts the position of sampling points through linear deformable convolution (LDConv), which improves the feature extraction ability of small-scale targets on complex backgrounds while maintaining lightweight features. The IR-EMA attention mechanism is a novel approach that combines an efficient reverse residual architecture with multi-scale attention. This combination enables the model to jointly capture feature channel dependencies and spatial relationships, thereby enhancing its sensitivity to weak impurity features. Again, a DC-DyHead deformable dynamic detection head is constructed, and deformable convolutions are embedded into the spatial perceptual attention of DyHead to enhance its feature modelling ability for anomalies and occluded impurities. We introduce an enhanced InnerMPDIoU loss function to optimise the bounding box regression strategy. This new method addresses issues related to traditional CIoU losses, including excessive penalties imposed on small targets and a lack of sufficient gradient guidance in situations where there is almost no overlap. The results indicate that the average precision (mAP@0.5) of the improved algorithm on the self-made PPR impurity dataset reached 88.6%, which is 2.3% higher than that of the original YOLOv11n, while precision (P) and recall (R) increased by 2.4% and 2.8%, respectively. This study provides a reliable technical solution for the quality inspection of PPR raw materials and serves as a reference for algorithm optimisation in the field of industrial small-target detection. Full article