Search Results (374)

Due to the small size of defects, partial occlusion, and cluttered background, insulator defect detection in transmission lines remains challenging. To address these issues, this paper proposes an improved Single Shot MultiBox Detector (SSD) framework. Firstly, a feature pyramid network is introduced for bidirectional multi-scale feature fusion to enhance the representation of small defects. Secondly, after fusing the feature maps, a convolutional block attention module is embedded to suppress background interference and highlight responses related to defects. Thirdly, focus loss replaces the original confidence loss to alleviate the imbalance of foreground and background during the training process. The proposed method achieved 99.03% insulator AP, 98.27% defect AP, and 98.65% mAP on a self-built dataset, which is 9.97 percentage points higher than the baseline SSD. The ablation study confirmed the complementary contributions of the three modules. The proposed detector significantly improves the detection reliability and robustness in complex detection scenarios, providing effective technical support for intelligent maintenance of transmission equipment. Full article

Crop targets in UAV aerial images are typically characterized by small scale, dense distribution, severe mutual occlusion, and complex backgrounds, which often lead to low detection accuracy and large counting errors for existing deep learning models. To address these issues, this study proposes an improved YOLOv12-based crop detection and counting model, named YOLO-DC. By introducing an attention mechanism (LGCB-AM) and a multi-scale detection head (MS-DH), the proposed model effectively enhances local texture extraction, global modeling, foreground–background contrast, and boundary perception for dense small objects. Subsequently, a series of comparative experiments, ablation studies, and transfer experiments were conducted on the wheat and rice datasets. The results show that YOLO-DC achieves a favorable balance among detection accuracy, counting error, and model efficiency and overall outperforms the other comparison models. Ablation studies further verify the effectiveness of the proposed design, showing that LGCB-AM is the key contributor to the performance improvement, while the boundary branch and repulsion branch play critical roles in dense-target discrimination. In addition, an appropriate module insertion strategy can effectively balance high-level semantic enhancement and feature fusion stability. Transfer experiments demonstrate that pretraining on the wheat dataset and fine-tuning on the rice dataset significantly outperform training from scratch, indicating strong cross-crop transfer potential. Overall, the proposed YOLO-DC provides an effective solution for high-precision crop detection and counting in agricultural scenarios. Full article

Aero-engine blades operate under extreme conditions involving high temperature, pressure, rotational speed, and cyclic loads, making them susceptible to surface defects such as micro-cracks. Due to their small scale, weak edges, low contrast, and elongated morphology, micro-cracks are easily affected by metallic reflections, uneven illumination, and complex background textures in borescope images, resulting in high missed-detection rates for conventional detection methods. To address these challenges, this study proposes an improved YOLO11-based framework for aero-engine blade micro-crack detection. The proposed method introduces P1/P2 shallow high-resolution detection branches to enhance the perception of fine crack edges and textures, incorporates Focal Loss to alleviate foreground–background imbalance, applies object-level Tversky Loss to strengthen false-negative constraints, and adopts a hard mining strategy to improve learning for difficult crack samples. Experiments conducted on a real aero-engine borescope image dataset demonstrate that the proposed model achieves a Precision of 0.9981, Recall of 0.9606, F1-score of 0.9790, mAP50 of 0.9781, and mAP50-95 of 0.6938 on an independent test set. Compared with the YOLO11 baseline, the proposed method significantly improves crack detection accuracy, localization quality, and robustness in complex borescope inspection scenarios. Full article

To address the challenge of hand intrusion detection in frozen tuna cutting operations where operators wear thermal-insulating gloves, this study proposes a hand detection method based on dual-domain background modeling with absolute accuracy constraints. To tackle issues arising from low-resolution infrared arrays, such as defective pixels, random noise, and complex low-temperature backgrounds, a data preprocessing pipeline integrating defective pixel correction, exponential moving average (EMA), and median filtering is developed. A dual-domain background suppression (DDBS) strategy, combining spatial-domain and temporal-domain models with sensor absolute accuracy constraints, is employed to extract hand foregrounds under complex thermal conditions. Temperature thresholding, connected-component analysis, and hole-filling are further applied to effectively separate hands from frozen tuna. An experimental platform incorporating a Raspberry Pi 4B and an MLX90640 sensor was constructed, and a dataset comprising 1173 infrared frames was collected for validation purposes. Experimental results demonstrate that the proposed method achieves an accuracy of 94.12%, precision of 91.69%, recall of 97.55%, and F1-score of 94.53% for hand intrusion detection, with an average processing time of approximately 1.84 ms per frame. This provides a cost-effective, real-time solution for hand safety monitoring in frozen food processing operations. Full article

Reliable detection of small agricultural targets is fundamental to precision crop protection, phenotyping, yield estimation, and robotic intervention. Typical examples include detecting aphids such as Aphis gossypii, whiteflies such as Bemisia tabaci, planthoppers such as Nilaparvata lugens, and other tiny pests on sticky traps or crop canopies for early warning, identifying crop-like weed seedlings for site-specific herbicide spraying, locating early disease lesions for targeted treatment, and detecting young fruits, flowers, or wheat heads for yield estimation and robotic manipulation. Agricultural small-object detection differs from generic small-object detection because target visibility is jointly determined by pixel area, physical size, imaging distance, ground sampling distance, canopy structure, biological similarity, and task-specific intervention requirements. Existing reviews have summarized agricultural object detection or general small-object detection, but they rarely connect agricultural failure modes with detector-level mechanisms and reproducible evaluation practices. This review addresses this gap through a mechanism-oriented synthesis of agricultural small-object detection. First, we revisit the limitations of the COCO-style 32²-pixel threshold and propose an agricultural scale-reporting framework that combines pixel area, physical scale, relative image occupancy, and acquisition geometry. Second, we organize recent methods according to the mechanisms by which they address detail loss, scale shift, occlusion, dense distributions, foreground–background confusion, localization uncertainty, and edge-deployment constraints. Third, we summarize public datasets, quantitative evaluation metrics, reporting checklists, and real-device deployment evidence to support fair and field-oriented comparison. Finally, we identify future directions in multimodal sensing, foundation-model adaptation, label-efficient learning, and hardware-aware optimization. By linking agricultural scene characteristics, detector mechanisms, and evaluation requirements, this review aims to provide a more actionable framework for developing robust small-object detection systems in precision agriculture. Full article

Accurate tooth segmentation plays a crucial role in computer-aided dental diagnosis and treatment planning, particularly in applications such as tooth detection, lesion localization, orthodontic analysis, and implant surgery. However, panoramic dental X-ray images often suffer from tooth adhesion, low contrast, and blurred boundaries, making precise delineation difficult and potentially compromising downstream clinical analysis. To address these challenges, we propose a boundary-aware segmentation framework, termed Boundary-Aware ResU-Net (BA-ResUNet), which is built upon a ResU-Net backbone and enhanced with Coordinate Attention (CA) and explicit boundary modeling mechanisms. Specifically, CA modules are introduced into the encoder to improve spatial representation and positional awareness. In addition, a Boundary Extraction Module (BEM) is designed to capture boundary priors from shallow and deep features, while a Boundary Injection Module (BIM) progressively incorporates these cues into the decoder through foreground enhancement and background suppression. This design enables the network to better preserve inter-tooth gaps and improve boundary delineation. Experiments on the MICCAI STS-2D dental dataset demonstrate that the proposed method achieves superior performance in terms of Dice and IoU compared with representative existing methods. Ablation and qualitative analyses further show that CA and BEM/BIM play synergistic roles in improving regional overlap and boundary localization, particularly in challenging cases involving adhesion, low contrast, and indistinct contours. These results indicate that the proposed framework provides a reliable and effective solution for panoramic tooth segmentation and has promising potential for computer-aided dental applications. Full article

The Moving Picture Experts Group (MPEG) is developing the Video Coding for Machines (VCM) standard to support efficient video compression for machine vision tasks. The VCM standard primarily targets object detection, tracking, and semantic segmentation. Since VCM mainly focuses on object-centric tasks such as detection and tracking, it employs Region-of-Interest (ROI) coding to allocate more bits to foregrounds, while suppressing background regions. This suppression reduces segmentation accuracy by degrading contextual background information. To address this limitation, we propose a luma background restoration method that reconstructs degraded background regions by exploiting the structural correlation between decoded luma and chroma components without relying on complex chroma modeling. The proposed method integrates multi-channel linear modeling with context-based arithmetic coding to efficiently transmit grouped Linear Model (LM) indices for luma restoration. Under VCM test conditions, experimental results show that the proposed method achieves an average Bjøntegaard Delta mean Intersection-over-Union (BD-mIoU) of 7.70, compared with 7.41 achieved by the latest background preservation method. These results demonstrate that the proposed method effectively restores structural background details in luma regions essential for semantic segmentation in VCM frameworks. Full article

The Binglangjiang buffalo, the only indigenous river-type buffalo in China, poses significant challenges for automated keypoint detection due to its uniformly black, low-texture coat, poor foreground–background contrast, and scarcity of annotated training samples. To address these challenges, this study constructs a benchmark dataset of 10,834 lateral-view images covering 424 individuals, annotated with 10 body measurement keypoints following standardized buffalo measurement protocols. A keypoint detection pipeline is developed by adapting DINOv2 with a top-down heatmap regression head under a single-view imaging setup, reducing hardware complexity for practical farm deployment. Benchmarking against YOLOv8 series and a standard ViT baseline shows that DINOv2-Base achieves 96.51% mAP, surpassing YOLOv8m by 5.6 percentage points. Compared to standard ViT, DINOv2 demonstrates more stable localization across keypoints under model scaling. Specifically, on the scapular tip (P8), a particularly low-texture region, DINOv2 exhibits only 0.28% mAP fluctuation versus 0.82% for standard ViT, indicating greater robustness to limited training data and low-contrast imaging. Body measurement validation on 20 individuals yields MAPE values of 1.76–5.69% across five measurements, confirming reliable non-contact measurement performance. The dataset and pipeline provide practical support for precision livestock management of endangered breeds. Full article

Age-related changes in visual perception alter attentional deployment, yet computational models of visual attention have been validated almost exclusively on younger populations. This limits both the theoretical investigation of age-specific mechanisms and practical applications in age-inclusive design, where researchers depend on specialised eye-tracking equipment to observe such differences. Therefore, we present the Elderly Visual Attention Estimation (EVAE) model, a computational framework that predicts early visual attentional orienting in older adults by combining stimulus-driven image features with age-specific top-down priors. The framework models six dimensions of elderly visual attention from cross-age eye-tracking data: colour brightness sensitivity, centre bias, foreground–background differentiation, depth detection, early attentional prior, and sustained-attention spatial prior. On public datasets, EVAE achieves an AUC-Judd of 0.92, which outperforms existing saliency models and deep learning approaches such as DeepGaze II. The framework is optimised for an input resolution of 128 × 96 pixels, producing fixation probability maps that are upsampled to match the original stimulus resolution for practical interface evaluation. Cross-age validation confirms the model’s specificity, as EVAE predicts attentional behaviour in older adults but does not generalise to younger adults. An ablation study shows that image features and top-down spatial priors each contribute independently to prediction accuracy, and that bottom-up saliency alone cannot account for age-related attentional patterns. Centre bias and early attentional prior are the strongest predictors, indicating that visual ageing involves greater reliance on spatial strategies and compensatory processing. As an alternative to hardware-based eye-tracking, EVAE widens the scope of empirical research into older adults’ visual attention and informs the design of accessible digital interfaces. Full article

Object detection in wide-field-of-view (wide-FoV) unmanned aerial vehicle (UAV) imagery for Internet of Things (IoT) remote sensing applications requires accurate recognition of tiny objects under severe background redundancy and extreme scale variation. As the field of view expands, conventional dense detectors tend to waste substantial computation on non-informative regions, while feature downsampling and static receptive fields often cause the dilution of foreground information and scale confusion. To address these issues, we propose MFRC-Det, a unified framework built upon two complementary principles: mask-guided feature routing and adaptive context modeling. Specifically, a Superpixel-Masking Generator (SP-Masker) is introduced to estimate an image-space soft foreground prior by comparing Simple Linear Iterative Clustering (SLIC) superpixel histograms with a peripheral background reference, propagating the resulting scores on a superpixel adjacency graph, and projecting the refined region-level scores back to a pixel-level routing mask. Guided by these priors, a Greedy-Cutter (G-Cutter) converts dense feature maps into compact, foreground-focused patches without repeated backbone evaluation on cropped image regions, thereby reducing redundant background computation while preserving local structural coherence. On top of the retained regions, an Adaptive Receptive-field Selection Network (ARSNet) aggregates multi-scale contextual responses from several learnable receptive-field candidate branches. ARSNet predicts spatial selection weights conditioned on the input features, allowing each location to emphasize a suitable receptive-field response for object representation. Experimental results on VisDrone-DET and UAVDT demonstrate that MFRC-Det achieves competitive detection accuracy with favorable computational efficiency. Specifically, MFRC-Det obtains 36.1% AP, 60.4% $A{P}_{50}$, and 38.5 FPS on VisDrone-DET and 21.3% AP, 36.8% $A{P}_{50}$, and 37.4 FPS on UAVDT. These results validate the effectiveness of mask-guided feature routing and adaptive context modeling for wide-FoV UAV object detection and suggest their potential value for computation-efficient aerial perception in IoT remote sensing applications. Full article

Fruit detection and maturity recognition are crucial for intelligent tomato harvesting and management. However, in complex field environments, challenges such as the similarity in color between fruits and leaves, cluttered backgrounds, and severe occlusions significantly hinder accurate tomato detection. To address these issues, this paper proposes a lightweight tomato maturity detection model, termed FDA-YOLO. Building upon the YOLOv11 framework, the proposed model enhances global perception in complex scenarios by introducing a multiscale feature enhancement module. In addition, a foreground–background dual-path attention mechanism is designed to better distinguish fruits from the background, thereby improving detection robustness. Furthermore, a lightweight asymmetric detection head is constructed to reduce computational cost while maintaining high accuracy. These improvements enable the model to achieve more efficient and accurate tomato maturity detection under complex conditions. Extensive experiments are conducted on the LaboroTomato dataset. The results demonstrate that FDA-YOLO achieves the best performance with relatively low computational overhead, reaching 83.4% and 67.5% in mAP50 and mAP50–95, respectively, while also attaining a near-optimal F1 score. Overall, the proposed model achieves an excellent balance between accuracy and efficiency, providing an effective solution for intelligent agricultural monitoring and automated harvesting systems. Full article

Additive manufacturing (AM) monitoring is fundamentally constrained by the severe scarcity of annotated data for layer-wise segmentation. This paper addresses this bottleneck by introducing a scalable, high-fidelity synthetic data generation pipeline built on the Slice-100K dataset, capable of producing large volumes of layer-wise semantic segmentation masks. Through analysis of this large-scale synthetic data, we identify a systemic foreground–background class imbalance (1:24 ratio) inherent to AM monitoring, which causes standard Dice loss formulations to diverge catastrophically into a phenomenon we formalize as the “Dice Crash.” To effectively leverage large amounts of unlabeled data, we adapt the Meta Pseudo-Labeling (MPL) framework for industrial segmentation. We evaluate MPL’s true marginal utility by integrating it with both a standard U-Net and a robust state-of-the-art nnU-Net architecture. Experimental outputs show that while MPL yields substantial performance gains (+15.2%) on weak baselines, integrating it with an optimally configured strong baseline consistently improves segmentation accuracy and suppresses false foreground detections, thereby mitigating confirmation bias. These findings demonstrate that semi-supervised learning via continuous bilevel optimization offers a practical and robust enhancement to data-scarce additive manufacturing monitoring. Because any hidden defects in the topmost layer will be permanently buried by subsequent extrusion, this foundational layer-wise segmentation step is the most critical primitive of the monitoring pipeline. Full article

Infrared imaging technology has been widely adopted for industrial gas leak detection due to its capability for large field-of-view, long-range, and dynamic monitoring. However, in practical applications, natural object interference within the scene, together with the blurred contours and low contrast of infrared images, severely degrades the performance of gas detection and leakage region segmentation. To address these challenges, this paper proposes a gas leak detection method that integrates gas characteristics with spatiotemporal information. Specifically, the non-solid characteristics of gas are incorporated to constrain the foreground extraction process of the Gaussian Mixture Model (GMM), thereby suppressing interfering moving objects. Furthermore, by exploiting the spatiotemporal information in infrared image sequences, a multi-scale cross-attention fusion model is designed to fuse multi-scale and global feature representations, improving the accuracy of foreground detection. Finally, density-based clustering is employed to achieve complete segmentation of gas regions with irregular shapes. Experimental results demonstrate that the proposed method effectively suppresses interference from solid objects, accurately detects gas leakage, and successfully segments the diffusion regions. Compared with existing approaches, the proposed method shows significant advantages and provides a valuable reference for research on infrared imaging-based gas leak detection. Full article

With the growing demand for intelligent monitoring in land-based aquaculture, rapid and accurate fish counting from visual data has become important for stocking density regulation, feeding management, and production decisions. To address the challenges in above-water fish images, including scale variation, severe occlusion and adhesion, blurred boundaries, and frequent switching between low- and high-density scenes, this study proposes MultiTask-Fish, a shared backbone multitask counting method. The network uses ResNet34 as the backbone and integrates a feature pyramid network and channel attention to learn unified feature representations. It jointly predicts detection heatmaps, foreground masks, separation boundaries, density maps, density gating, and global count regression, allowing the model to combine local localization cues, structural information, and global statistics. Based on existing polygon annotations, heatmap, mask, boundary, and density supervision are automatically generated for integrated multitask training. Experiments on 495 fish images, including 346 training and 149 validation images, showed that the proposed method achieved an MAE of 5.875, an RMSE of 11.839, and an MAPE of 0.152 on the validation set, while reducing the MAE on the high-density subset from 16.717 to 13.895. These results demonstrate its effectiveness for fish counting in complex above-water aquaculture scenes. Full article

Salient object detection in optical remote sensing images remains challenging due to complex backgrounds, blurred boundaries, small objects, unstable foreground–background contrast, and dense object distributions. Existing convolution-based methods are effective at modeling local structures, but they are limited in capturing long-range dependencies, whereas Transformer-based approaches usually incur substantial computational cost when handling high-resolution remote sensing imagery. To address these issues, this paper proposes EGMamba-Net, an edge-guided global–local collaborative network for salient object detection in optical remote sensing images. Specifically, a hybrid global–local backbone is first constructed to preserve shallow texture, edge, and geometric details while introducing Mamba-based global modeling in deeper stages for efficient long-range dependency representation. An Edge Prior Enhancement Module (EPEM) is then designed to explicitly extract boundary priors from shallow features and refine feature representations through edge-guided modulation. To alleviate the representation conflict between global semantics and local details, a Global–Local Interaction Module (GLIM) is further developed, where convolutional local modeling and Mamba-based global modeling interact through cross-gating for complementary feature learning. Moreover, a Region-Adaptive Routing Decoder (RARD) is introduced to dynamically assign different refinement paths according to regional saliency response, boundary intensity, and contextual complexity, thereby improving the recovery of small, low-contrast, and densely distributed objects. In addition, a Difficulty-Aware Joint Loss (DAJL) is designed to enhance optimization on boundary regions and hard samples, improving robustness under challenging conditions. Extensiveexperiments on ORSSD, EORSSD, and ORSI-4199 datasets demonstrate the superiority of the proposed method. In particular, on the more challenging EORSSD dataset, EGMamba-Net achieves 0.9389 S-measure, 0.8972 max F-measure, and 0.0066 MAE. Compared with the representative remote-sensing method DAF-Net, it improves S-measure and max F-measure by 0.0223 and 0.0358, respectively, indicating stronger capability in background suppression, structural preservation, and boundary recovery. Full article