Search Results (662)

Remote sensing ship detection plays a pivotal role in maritime surveillance, safety assurance, and traffic management. However, current detection methods often face significant challenges due to complex sea-surface background noise, large target-scale variations, and edge-hardware limitations. In this paper, we propose RepLite-YOLO, a lightweight detection framework based on YOLOv11n. Specifically, to alleviate irreversible spatial information loss during downsampling, we adopt the ADown module, originally introduced in YOLOv9, to generate spatially complementary features through its two-branch downsampling mechanism. This design helps preserve salient hull-edge responses while suppressing part of the random sea-surface interference, thereby improving feature robustness for small ship targets. To achieve substantial structural streamlining while maintaining competitive representational capacity under strict hardware constraints, we design the C3k2_OREPA_RS module, utilizing online re-parameterization (OREPA) to efficiently reconstruct deep layers without additional re-parameterization-induced inference operations. Furthermore, we construct the ELANFusion_Block by integrating Depthwise Separable Convolutions (DSC) into the ELAN paradigm to alleviate the multi-scale aggregation bottleneck, and tailor the Detect_DWLite head for highly compressed decoupled prediction. Experimental results show that RepLite-YOLO achieves a favorable balance between detection accuracy and computational efficiency. Compared with YOLOv11n, it reduces the number of parameters by 57.4% and GFLOPs by 49.2%, while maintaining competitive detection accuracy with slight mAP@50 improvements of 1.2 and 1.3 percentage points on the Vessel dataset and Ship Detection dataset, respectively. Full article

Accurate change detection in high-resolution remote sensing imagery is essential for urban planning, land-use monitoring, and disaster response. This study introduces CTA-Net, a Cross-Temporal Attention Network for binary change detection in bi-temporal optical imagery, designed to improve robustness against pseudo-changes caused by illumination variation, seasonal effects, and sensor noise. The proposed method employs a shared Siamese encoder with multi-scale Cross-Temporal Attention modules that derive spatial and channel attention from L2 feature differences, along with a lightweight confidence estimation head for per-pixel uncertainty modelling. A hybrid loss function combining confidence-weighted binary cross-entropy and focal loss is used to address class imbalance. Experiments on the LEVIR-CD dataset demonstrate that CTA-Net achieves an overall accuracy of 98.99%, an F1-score of 87.68%, an Intersection over Union of 78.06%, a Cohen’s kappa of 0.8715, and a Matthews Correlation Coefficient of 0.8721, with stable convergence and minimal overfitting. Qualitative and calibration analyses further indicate that the model produces interpretable attention maps and reliable probabilistic outputs. To evaluate cross-domain generalization, we conduct a transfer learning case study on multispectral Sentinel-2 agricultural imagery. The model is adapted to 11-channel input and fine-tuned on automatically generated change masks derived from NDVI-delta thresholding. Under this supervision protocol, CTA-Net achieves an F1-score of 95.18% and an IoU of 90.81% on a held-out test region, with balanced precision and recall. While these results demonstrate effective adaptation across sensor modality, spatial resolution, and semantic domain, the evaluation reflects agreement with the mask generation procedure rather than independently annotated ground truth. While CTA-Net shows strong performance and reasonable interpretability, its cross-domain evaluation is limited by the use of automatically generated labels. As a result, the reported transferability should be interpreted cautiously until validated on human-annotated datasets. Full article

Space debris presents a growing operational risk to spacecraft, especially in low Earth orbit, where collisions can generate further debris and increase future collision probability. Active debris removal and in-orbit servicing require robust close-range perception, but on-board systems are constrained by power, memory, processing capability and the need for reliable real-time operation. This paper investigates convolutional object detection for on-board space debris detection using the SPARK 2022 spacecraft detection dataset. A YOLOv3 detector is fine-tuned and used to evaluate post-training compression through static quantisation and pruning. A lightweight architectural variant, YOLO-DWSC, is also introduced by replacing the YOLOv3-tiny backbone convolutions with depthwise separable convolutions while retaining the detection head. The full-precision YOLOv3 model achieves 0.972 mAP₅₀ and 0.884 mAP_50:95, while 8-bit static quantisation reduces model size from 405 MB to 102 MB with only a small reduction in mAP₅₀, although tighter localisation accuracy is more affected. YOLO-DWSC is much smaller and faster, reaching 256.4 FPS on the tested GPU at 43 MB, but with reduced accuracy. We present this work as a controlled case study rather than an attempt at state-of-the-art SPARK 2022 performance. The original challenge test labels were unavailable, and the experiments therefore use a class-balanced re-split of the labelled data. The results should consequently be interpreted as internally controlled comparisons of compression behaviour, not as leaderboard-comparable benchmark results. Pruning and a two-pass refinement method are also evaluated. The results indicate that simple compression methods can be useful for broad region-of-interest detection, but they also show that claims about on-board deployment require caution. Speed benefits are hardware- and runtime-dependent, and safety-critical proximity operations require evaluation criteria better aligned with full-object containment. Full article

Falls among the elderly and vulnerable populations represent a critical public health challenge, and camera-based visual sensor systems have emerged as a promising non-intrusive solution for continuous fall monitoring. However, deploying accurate fall detection on resource-constrained edge sensor nodes remains difficult due to the trade-off between model complexity and detection performance. In this paper, we propose WAD-YOLO, an efficient and lightweight fall detection algorithm tailored for visual sensor systems, based on wavelet transform and dynamic convolution. First, a wavelet transform convolution (WTConv) module is introduced to expand the receptive field of the visual feature extractor via cascaded wavelet decomposition, enabling the sensor-driven model to better capture low-frequency fall-related patterns without parameter explosion. Second, a dynamic upsample (DySample) operator is incorporated into the detection head to achieve content-aware, flexible upsampling by generating dynamic offsets, maintaining high efficiency suitable for real-time sensor data processing. Third, an adaptive downsampling (ADown) module is integrated to reduce spatial resolution while preserving semantic information, further reducing the computational burden for deployment on embedded sensor platforms. Experiments on the public Fall Detection dataset demonstrate that, compared with the baseline YOLOv11n, the proposed method increases precision P by 3.8%, mAP50 by 3.7%, and reduces the parameter count by 3.0 × 10${}^5$. The reduced parameter count and matched GFLOPs relative to YOLOv11n suggest that WAD-YOLO is a theoretically promising candidate for lightweight, high-accuracy fall detection on edge sensor platforms. Full article

In smart grid operation, the scarcity of abnormal samples causes data imbalance, which is a key factor limiting the accuracy of anomaly detection. To address this issue and simultaneously solve the problem of easily losing weak abnormal signals in one-dimensional time-series data, an abnormal data detection method for grid information using an improved AlexNet considering sample imbalance is proposed. Firstly, features like voltage, current, and power are extracted from historical data. Missing values are filled via Lagrange interpolation, and abnormal boundaries are determined using box plots to construct high-quality samples. Secondly, to address the problem of few abnormal samples and imbalanced distribution, an enhanced learning strategy combining time-series translation and Gaussian noise injection is adopted to expand the abnormal samples and obtain sufficient training data. Then, to preserve the integrity of weak signals in one-dimensional time-series data and amplify the differences in abnormal features, the Gram angle field is used to convert multi-dimensional time-series data into a two-dimensional image, achieving the visual representation of time-series features. Finally, combined with the powerful image detection capability of AlexNet, it is improved by lightweighting the network structure, introducing the multi-head self-attention mechanism, and optimizing the training strategy to adapt to abnormal detection in the small sample and imbalanced environment of the grid. The simulation experiments show that the proposed method achieves an accuracy rate of 91.32% on extremely imbalanced datasets, which is at least 3.1% higher than those of other models. Full article

Insulators are critical insulation components in power transmission lines; however long-term exposure to adverse environmental conditions may threaten the safety and stability of power delivery. Existing studies primarily emphasize detection accuracy, while deployment efficiency and inference speed have received insufficient attention, limiting their applicability to CPU-based edge computing devices. To address these limitations, this paper proposes PEBL-YOLO, a lightweight model for insulator defect detection. The proposed model retains the external C3k2 structure of YOLOv11 while simplifying its internal bottleneck module, in which PConv is embedded to improve spatial feature extraction and fusion efficiency. In the neck, the original Path Aggregation Feature Pyramid Network (PAFPN) is reconstructed by integrating a Bidirectional Feature Pyramid Network (BiFPN) with Efficient Channel Attention (ECA), enabling more effective aggregation of multi-scale features and stronger focus on defect-related regions with minimal parameter increase. Moreover, a lightweight shared decoupled detection head is designed to decouple classification and regression branches. By combining parameter sharing with Group Normalization (GN) the detection head further reduces model complexity while maintaining accurate localization capability. Experimental results show that PEBL-YOLO contains only 1.68 M parameters. It achieves Precision, Recall, mAP@0.5, and mAP@0.5:0.95 of 95.0%, 92.1%, 94.4%, and 53.6%, respectively. These results demonstrate that PEBL-YOLO achieves a favorable trade-off between detection accuracy and parameter efficiency, providing a practical solution for lightweight insulator defect detection in edge computing scenarios. Full article

Real-time monitoring of endangered birds on edge AI hardware is constrained by a structural mismatch between modern lightweight detectors and mainstream NPU deployment toolchains. Recent attention-based detectors rely heavily on dynamic-shape operators that fall back to the host CPU on embedded NPUs, negating the advantages of lightweight architectures. To address this, we propose eBirdNet-Nano, a 1.05 M-parameter detector derived from YOLOv12n through a three-level NPU-friendly redesign: a static NPUConv block at the operator level, an NPU-C3k2 module together with an NPU-SE-Block at the module level, and a balanced 64-channel detection head at the head level. The resulting model achieves a 59% parameter reduction over YOLOv12n at only 5.8 GFLOPs while attaining an mAP@0.5 of 0.929 on a curated 24-species endangered-bird dataset collected in Macao. We further evaluate the model across four heterogeneous edge platforms—the Rockchip RK3588 (ARM + NPU), Kendryte K230 (RISC-V + KPU), Raspberry Pi 4B (pure ARM), and LicheePi 4A (pure RISC-V)—to characterize its behavior under distinct execution models. On the RK3588 NPU under INT8 quantization, eBirdNet-Nano delivers 13.83 ms inference latency and 26.76 ms end-to-end latency at 37.4 FPS, attaining the best parameter–latency balance and the highest parameter-normalized throughput (35.62 FPS/M) among six nano-scale YOLO variants, with an overall 3.53× end-to-end speedup over the YOLOv12n FP16 baseline that decomposes into a 2.97× architectural factor and a 1.19× quantization factor. Integrated into the EbirdEye field terminal, the same model sustains 23.5 ms thread-level end-to-end latency during live operation while supporting approximately 13.5 h of battery-powered runtime per charge. The proposed design offers a practical pathway toward deployable, low-power AI terminals for endangered-species conservation in resource-constrained field environments. Full article

Accurate ripeness assessment of tomatoes in natural orchard settings is challenged by severe occlusion, dense clustering, and scale variation among fruits. This paper introduces YOLOv8n−TiD, a lightweight detection framework designed to overcome these obstacles. The architecture enhances the YOLOv8n backbone with a novel C2f-iRD module, which integrates re-parameterized dilated convolutions and inverted residual blocks to enlarge the receptive field while retaining fine-grained texture details. For feature fusion, we propose C2f-iRMB in the neck to ensure cross-scale consistency. To address semantic drift during upsampling, we replace standard interpolation with the DySample operator. The detection head is re-engineered as TADAH (Task-Adaptive Dynamic Alignment Head), enabling genuine task decoupling via deformable convolutions and conditionally shared features. Additionally, we introduce F−PIoUv2, a regression loss that emphasizes medium-quality predictions and curbs excessive bounding box expansion. Evaluations on a custom dataset show that YOLOv8n−TiD cuts parameters by 45%, FLOPs by 19%, and model size by 41%, while raising mAP@0.5 by 1.9 points—all in real time. On Android devices, it sustains 30 FPS inference and generalizes effectively to a distinct cherry tomato cultivar. These findings confirm the method’s robustness in discriminating occluded, small, and visually similar maturity stages, providing a practical vision system for robotic harvesting and field-based grading. Full article

This paper addresses the challenges of high latency and the lack of an effective recovery strategy in mobile robot target following tasks. In this paper, a low-latency mobile robot target tracking method based on the improved YOLO-World algorithm is proposed. The process primarily consists of three parts: target detection, target tracking, and motion control. First, for target detection, we introduce a tailored lightweight backbone network, GSS, within the YOLO-World framework, which progressively expands the receptive field through cascaded convolutional operations and enhances cross-group feature interaction via a channel mixing mechanism, significantly improving model efficiency with minimal loss in detection accuracy. Additionally, depthwise separable convolution is applied to the detection head to reduce computational redundancy. Secondly, in the target tracking part, a lightweight target tracking algorithm based on improved BoT-SORT is adopted, and the tracking delay is effectively reduced by optimizing the ReID feature extraction backbone network. Then, the motion control part adopts an active search strategy based on visual servo control. When the tracked target is lost, the strategy utilizes a camera motion compensation-based tracker to predict the target motion state and controls the robot to actively search for the target accordingly. Subsequently, feature tracking is resumed through target re-recognition, thus re-establishing target following. Experiments on public datasets and real-world scenarios demonstrate that the proposed method achieves strong robustness and real-time performance. Full article

In cotton disease detection, the complex farmland environment and the varying scales of disease spots, especially the presence of small-target disease spots, limit the detection accuracy of lightweight models. To address this issue, an improved YOLOv11n detection algorithm is proposed. First, the backbone network is reconstructed using the GhostConv (G-conv) module, which generates redundant feature maps through linear operations, thereby reducing computational complexity. Second, an Adaptive Calibration and Feature Fusion Architecture Head (ACFFA) with prior calibration and cross-scale fusion capabilities is constructed in the detection stage to handle the problem of varying disease spot scales. Furthermore, the Adaptive Scale-aware Wise Intersection over Union (AS-WIoU) loss function, improved from WIoUv3, is introduced to enhance the stability of bounding box regression and improve detection accuracy for low-resolution, small-target lesions. Experimental results show that on the cotton disease dataset constructed based on the Mendeley Data database, the proposed model achieves mAP50 and mAP50-95 of 90.30% and 73.84%, respectively, with precision and recall of 92.33% and 87.68%, and a parameter count of 3.81 M. The algorithm significantly improves detection accuracy while maintaining efficient inference, making it suitable for real-time monitoring tasks on agricultural embedded terminals. Full article

Under the dwarf-rootstock dense planting method, existing apple detection models for intelligent harvesting suffer from excessive parameter counts that hinder deployment on resource-constrained devices, while lightweight alternatives often sacrifice detection accuracy. To address this dilemma, this paper proposes YOLO-SPM, a lightweight apple detection model based on the YOLOv12n architecture, specifically designed for complex orchard environments. The core innovation lies in a problem-driven, three-stage collaborative optimization strategy: first, PConv is introduced to replace standard convolutions in the A2C2f module, reducing computational redundancy by exploiting channel-wise feature similarity of apple targets; second, the parameter-free SimAM attention mechanism is embedded in the neck network to enhance the model’s focus on occluded fruit features without increasing model size, while MBConv is integrated into the detection head to further reduce computational cost; third, WIoU v3 is adopted as the loss function to compensate for the accuracy loss incurred by lightweight design through its dynamic focusing mechanism on difficult samples. This complementary design ensures that each module addresses a distinct bottleneck of the native YOLOv12n in orchard scenarios, achieving a balance between efficiency and accuracy rather than simple module stacking. Experimental results demonstrate that YOLO-SPM achieves a precision of 92.8% and mAP@0.5 of 93.1%, outperforming the baseline by 4.8 and 5.3 percentage points, respectively, while reducing parameter count, FLOPs, and memory footprint by 40.2%, 35.4%, and 41.8%. This study provides a feasible solution for high-precision apple identification in dwarf-rootstock dense planting orchard environments, with the potential for integration into automated harvesting systems upon future on-device validation. Full article

Morel detection in agroforestry cultivation scenes remains challenging because soil-background camouflage, illumination variation, and dense clustered growth can lead to missed small targets and false positives in background regions. This study proposes Morel-YOLO, a lightweight morel detection method based on YOLOv13n for agricultural perception. The model retains the original multi-scale feature-fusion framework and introduces three targeted modifications: a StarNet backbone for reducing redundant computation, a DSC3k2_DWRSeg module in the shallow ${\mathrm{P}}_3$ branch for strengthening fine-grained texture and small-target representation, and a Detect_MBConv head for reducing prediction-branch overhead while preserving detection accuracy. On the test set, Morel-YOLO achieves 91.9% precision, 86.6% recall, 93.6% ${\mathrm{mAP}}_{50}$, and 70.8% ${\mathrm{mAP}}_{50–95}$, improving ${\mathrm{mAP}}_{50–95}$ by 1.3 percentage points over YOLOv13n. The model contains 1.48 M parameters, has a model size of 3.31 MB, and requires 6.2 GFLOPs. On the Small-hard and Dense-hard subsets, ${\mathrm{mAP}}_{50–95}$ reaches 69.1% and 66.8%, respectively, corresponding to gains of 1.5 and 1.3 percentage points over the baseline. Under IoU = 0.75, both false positives and false negatives are also reduced on the two hard subsets. These results suggest that Morel-YOLO improves the balance among detection accuracy, robustness, and model compactness on the evaluated dataset; however, its practical deployment on embedded agricultural platforms still requires dedicated on-device validation. Full article

Dense underwater aquaculture poses significant challenges for intelligent image processing because asymmetric occlusion, turbidity, aeration-like bubbles, and motion blur frequently degrade fish contours and quasi-periodic scale textures. These disturbances often cause conventional detectors to miss detections, merge bounding boxes, experience feature collapse, and exhibit unstable counting. To address this problem, we propose DenseFish-v13, a symmetry-aware NMS-free YOLOv13-Mamba framework for dense underwater fish detection and bio-kinematic behavior recognition. The framework integrates a Bio-Harmonic Frequency Gate to preserve biological texture patterns while suppressing bubble-like frequency noise, a Bi-directional Multi-scale Wavelet Mamba backbone for global occlusion-aware structure recovery, and an asymmetry-aware density repulsion strategy to separate highly overlapping fish instances during bipartite matching. In addition, a lightweight Bio-Kinematic Behavior Head converts continuous detections into interpretable trajectory descriptors for behavior-state recognition. Experiments on the Dense-Aqua benchmark, constructed from public aquaculture datasets, show that DenseFish-v13 achieves 64.8% mAP@50:95 and a Counting MAE of 3.7 on the overall test set, while reaching 64.2% mAP@50:95 and a Counting MAE of 4.1 on the extreme-density split. Under a strong synthetic bubble perturbation, the model shows only a 1.3 percentage-point drop in mAP and maintains 125 FPS on Jetson Orin NX. These results demonstrate its effectiveness in robust, real-time underwater aquaculture monitoring. Full article

In response to the challenges in UAV-oriented ground small-object localization and detection, including the easy loss of tiny target features, insufficient scale adaptability, severe interference from complex backgrounds, as well as high missed and false detection rates and the inadequate localization accuracy of the conventional YOLOv11n model in such scenarios, this paper takes YOLOv11n as the basic framework and performs systematic optimization from three aspects, network structure, core modules, and feature enhancement, proposing a lightweight small-object-enhanced detection algorithm named YOLOSO for UAV applications. By introducing a P2 high-resolution feature branch with a stride of 4, a four-scale detection structure consisting of P2-P3-P4-P5 is constructed, which reduces the minimum detection stride from 8 to 4 and alleviates the loss of detailed feature information for ultra-tiny targets. A bidirectional “top-down + bottom-up” multi-scale feature fusion strategy is utilized to improve the complementation between deep semantic information and shallow detailed features, while the core modules C3k2SO and C2PSASO are optimized and redesigned, respectively; by adjusting the channel compression ratio (0.25 for shallow modules and 0.75 for deep modules in C3k2SO; 0.25 in C2PSASO), optimizing the convolution kernel configuration (combining 1 × 3 and 3 × 1 convolutions), increasing the number of attention heads (from 4 to 8), and introducing residual connections with a 1 × 1 convolutional branch, the refinement and focusing ability of small-object feature extraction are improved. Additionally, an Enhanced Dual-branch Convolutional Block Attention Module (ED-CBAM) is proposed to further suppress background interference. Experimental results on the VisDrone2019-DET dataset demonstrate that the proposed YOLOSO contains 3.56M parameters and maintains a lightweight structure, attaining P, R, and mAP50 values of 47.2%, 36.8%, and 37.3% in the test set, which are 4.5 percentage points, 4.8 percentage points, and 3.7 percentage points higher than those of the baseline YOLOv11n (42.7%, 32.0% and 33.6%), respectively. Meanwhile, the medium-to-large version YOLOSO-S (14.85M parameters, 45.3% mAP50) reduces the number of parameters by 53.6% compared with the same-scale Rtdetr-L (32.0M) while achieving significantly better performance (37.8% mAP50). Experiments on the DOTAv1 dataset further confirm the generalization of YOLOSO, achieving 62.2% precision and 27.3% mAP50, outperforming all compared YOLO models. Evaluated on the DOTA-v1 dataset, YOLOSO achieves a feasible FPS of 20.53. Although slightly slower than mainstream lightweight YOLO models, the substantial accuracy gains fully offset the minor inference speed loss, and such performance trade-off is acceptable for practical UAV deployment. Ablation experiments verify that structural optimization (2.8 percentage points mAP50 improvement, from 33.6% to 36.4%) and the proposed C2PSASO (0.7 percentage points mAP50 improvement to 34.3%) and C3k2SO (1.4 percentage points mAP50 improvement to 35.0%) modules all contribute positive performance gains with favorable complementarity. While retaining lightweight characteristics, the model effectively enhances the detection accuracy of small objects in unmanned aerial vehicle scenarios and can provide technical references for practical applications such as remote sensing monitoring and security patrolling. Full article

Rice leaf diseases severely threaten global food security, and efficient on-site detection remains challenging for resource-constrained field inspection robots. This work introduces a lightweight visual detection framework designed for the real-time and accurate identification of rice leaf diseases on agricultural edge mobile platforms. A dataset of 4622 annotated images compiled from mobile-device acquisition and publicly available online sources, covering three representative disease categories, together with an independent public benchmark, was used for evaluation. The framework integrates three complementary modules: adaptive multi-scale feature extraction via a dynamic hybrid convolution backbone (C3k2-DICN), cross-scale parameter sharing in the detection head (CSDH) to reduce redundancy, and dual-path downsampling (ADown) to preserve disease-discriminative information during resolution compression. Compared to the YOLO11n baseline, the proposed approach reduced GFLOPs by 36.5% and parameter count by 34.6%, while achieving 88.42% mAP@0.5 and 45.82% mAP@0.5:0.95 on the compiled dataset and 91.71% mAP@0.5 on the public benchmark, indicating accuracy competitive with or superior to all evaluated comparison models. Deployed on an NVIDIA Jetson TX2 with TensorRT FP16 acceleration, the model ran in real time on-device, reaching 32.2 FPS for the TensorRT inference stage and 19.8 FPS for the full end-to-end pipeline including image pre- and post-processing. The framework offers a practical basis for lightweight on-device rice disease detection; closed-loop validation on a moving field robot is left to future work. Full article