Search Results (704)

To address the limitations of traditional lithium battery defect detection—low efficiency, high missed detection rates for minute/composite defects, and inadequate multimodal fusion—this study develops an improved YOLOv8 model based on multimodal fusion and attention enhancement for unified full-lifecycle multi-type defect detection. Integrating visible-light and X-ray modalities, the model incorporates a Squeeze-and-Excitation (SE) module to dynamically weight channel features, suppressing redundancy and highlighting cross-modal complementarity. A Multi-Scale Fusion Module (MFM) is constructed to amplify subtle defect expression by fusing multi-scale features, building on established feature fusion principles. Experimental results show that the model achieves an mAP@0.5 of 87.5%, a minute defect recall rate (MRR) of 84.1%, and overall industrial recognition accuracy of 97.49%. It operates at 35.9 FPS (server) and 25.7 FPS (edge) with end-to-end latency of 30.9–38.9 ms, meeting high-speed production line requirements. Exhibiting strong robustness, the lightweight model outperforms YOLOv5/7/8/9-S in core metrics. Large-scale verification confirms stable performance across the battery lifecycle, providing a reliable solution for industrial defect detection and reducing production costs. Full article

A key challenge in automated marigold harvesting lies in the accurate identification of picking points under complex environmental conditions, such as dense shading and intense illumination. To tackle this problem, this research proposes a lightweight instance segmentation model combined with a harvest position estimation method. Based on the YOLOv11n-seg segmentation framework, we develop a lightweight PDS-YOLO model through two key improvements: (1) structural pruning of the base model to reduce its parameter count, (2) incorporation of a Channel-wise Distillation (CWD)-based feature distillation method to compensate for the accuracy loss caused by pruning. The resulting lightweight segmentation model achieves a size of only 1.3 MB (22.8% of the base model) and a computational cost of 5 GFLOPs (49.02% of the base model). At the same time, it maintains high segmentation performance, with a precision of 93.6% and a mean average precision (mAP) of 96.7% for marigold segmentation. Furthermore, the proposed model demonstrates enhanced robustness under challenging scenarios including strong lighting, cloudy weather, and occlusion, improving the recall rate by 1.1% over the base model. Based on the segmentation results, a method for estimating marigold harvest positions using 3D point clouds is proposed. Fitting and deflection angle experiments confirm that the fitting errors are constrained within 3–12 mm, which lies within an acceptable range for automated harvesting. These results validate the capability of the proposed approach to accurately locate marigold harvest positions under top-down viewing conditions. The lightweight segmentation network and harvest position estimation method presented in this work offer effective technical support for selective harvesting of marigolds. Full article

Road defect detection is essential for timely road damage repair and traffic safety assurance. However, existing object detection algorithms suffer from insufficient accuracy in detecting small road surface defects and are prone to missed detections and false alarms under complex lighting and background conditions. To address these challenges, this study proposes SDC-YOLOv8, an improved YOLOv8-based algorithm for road defect detection that employs attention-enhanced feature learning and adaptive feature reconstruction. The model incorporates three key innovations: (1) an SPPF-LSKA module that integrates Fast Spatial Pyramid Pooling with Large Separable Kernel Attention to enhance multi-scale feature representation and irregular defect modeling capabilities; (2) DySample dynamic upsampling that replaces conventional interpolation methods for adaptive feature reconstruction with reduced computational cost; and (3) a Coordinate Attention module strategically inserted to improve spatial localization accuracy under complex conditions. Comprehensive experiments on a public pothole dataset demonstrate that SDC-YOLOv8 achieves 78.0% mAP@0.5, 81.0% Precision, and 70.7% Recall while maintaining real-time performance at 85 FPS. Compared to the baseline YOLOv8n model, the proposed method improves mAP@0.5 by 2.0 percentage points, Precision by 3.3 percentage points, and Recall by 1.8 percentage points, yielding an F1 score of 75.5%. These results demonstrate that SDC-YOLOv8 effectively enhances small-target detection accuracy while preserving real-time processing capability, offering a practical and efficient solution for intelligent road defect detection applications. Full article

The aim of this study was to accurately meet the demand of real-time detection of seedling shortage in large-scale seedling production and solve the problems of low precision of traditional models and insufficient adaptability of mainstream lightweight models. This study proposed a Light-YOLO-Pepper seedling shortage detection model based on the improvement of YOLOv8n. This model was based on YOLOv8n. The SE (Squeeze-and-Excitation) attention module was introduced to dynamically suppress the interference of the nutrient soil background and enhance the features of the seedling shortage area. Depth-separable convolution (DSConv) was used to replace the traditional convolution, which can reduce computational redundancy while retaining core features. Based on K- means clustering, customized anchor boxes were generated to adapt to the hole sizes of 72-unit (large size) and 128-unit (small size and high-density) seedling trays. The results show that the overall mAP@0.5, accuracy and recall rate of Light-YOLO-Pepper model were 93.6 ± 0.5%, 94.6 ± 0.4% and 93.2 ± 0.6%, which were 3.3%, 3.1%, and 3.4% higher than YOLOv8n model, respectively. The parameter size of the Light-YOLO-Pepper model was only 1.82 M, the calculation cost was 3.2 G FLOPs, and the reasoning speeds with regard to the GPU and CPU were 168.4 FPS and 28.9 FPS, respectively. The Light-YOLO-Pepper model was superior to the mainstream model in terms of its lightweight and real-time performance. The precision difference between the two seedlings was only 1.2%, and the precision retention rate in high-density scenes was 98.73%. This model achieves the best balance of detection accuracy, lightweight performance, and scene adaptability, and can efficiently meet the needs of embedded equipment and real-time detection in large-scale seedling production, providing technical support for replanting automation. Full article

Crack detection plays a pivotal role in ensuring the safety and stability of infrastructure. Despite advancements in deep learning-based image analysis, accurately capturing multiscale crack features in complex environments remains challenging. These challenges arise from several factors, including the presence of cracks with varying sizes, shapes, and orientations, as well as the influence of environmental conditions such as lighting variations, surface textures, and noise. This study introduces DAH-YOLO (Dynamic-Attention-Haar-YOLO), an innovative model that integrates dynamic convolution, an attention-enhanced dynamic detection head, and Haar wavelet down-sampling to address these challenges. First, dynamic convolution is integrated into the YOLOv8 framework to adaptively capture complex crack features while simultaneously reducing computational complexity. Second, an attention-enhanced dynamic detection head is introduced to refine the model’s ability to focus on crack regions, facilitating the detection of cracks with varying scales and morphologies. Third, a Haar wavelet down-sampling layer is employed to preserve fine-grained crack details, enhancing the recognition of subtle and intricate cracks. Experimental results on three public datasets demonstrate that DAH-YOLO outperforms baseline models and state-of-the-art crack detection methods in terms of precision, recall, and mean average precision, while maintaining low computational complexity. Our findings provide a robust, efficient solution for automated crack detection, which has been successfully applied in real-world engineering scenarios with favorable outcomes, advancing the development of intelligent structural health monitoring. Full article

This paper presents a low-cost, fully on-premise Edge Artificial Intelligence (AI) system designed to support real-time pest and disease detection in open-field chili pepper cultivation. The proposed architecture integrates AI-Thinker ESP32-CAM module (ESP32-CAM) image acquisition nodes (“Sticks”) with a Raspberry Pi 5–based edge server (“Module”), forming a plug-and-play Internet of Things (IoT) pipeline that enables autonomous operation upon simple power-up, making it suitable for aging farmers and resource-limited environments. A Leaf-First 2-Stage vision model was developed by combining YOLOv8n-based leaf detection with a lightweight ResNet-18 classifier to improve the diagnostic accuracy for small lesions commonly occurring in dense pepper foliage. To address network instability, which is a major challenge in open-field agriculture, the system adopted a dual-protocol communication design using Hyper Text Transfer Protocol (HTTP) for Joint Photographic Experts Group (JPEG) transmission and Message Queuing Telemetry Transport (MQTT) for event-driven feedback, enhanced by Redis-based asynchronous buffering and state recovery. Deployment-oriented experiments under controlled conditions demonstrated an average end-to-end latency of 0.86 s from image capture to Light Emitting Diode (LED) alert, validating the system’s suitability for real-time decision support in crop management. Compared to heavier models (e.g., YOLOv11 and ResNet-50), the lightweight architecture reduced the computational cost by more than 60%, with minimal loss in detection accuracy. This study highlights the practical feasibility of resource-constrained Edge AI systems for open-field smart farming by emphasizing system-level integration, robustness, and real-time operability, and provides a deployment-oriented framework for future extension to other crops. Full article

Efficient and reliable road damage detection is a critical component of intelligent transportation and infrastructure control systems that rely on visual sensing technologies. Existing road damage detection models are facing challenges such as missed detection of fine cracks, poor adaptability to lighting changes, and false positives under complex backgrounds. In this study, we propose an enhanced YOLO-based framework, YOLO-ERCD, designed to improve the accuracy and robustness of sensor-acquired image data for road crack detection. The datasets used in this work were collected from vehicle-mounted and traffic surveillance camera sensors, representing typical visual sensing systems in automated road inspection. The proposed architecture integrates three key components: (1) a residual convolutional block attention module, which preserves original feature information through residual connections while strengthening spatial and channel feature representation; (2) a channel-wise adaptive gamma correction module that models the nonlinear response of the human visual system to light intensity, adaptively enhancing brightness details for improved robustness under diverse lighting conditions; (3) a visual focus noise modulation module that reduces background interference by selectively introducing noise, emphasizing damage-specific features. These three modules are specifically designed to address the limitations of YOLOv10 in feature representation, lighting adaptation, and background interference suppression, working synergistically to enhance the model’s detection accuracy and robustness, and closely aligning with the practical needs of road monitoring applications. Experimental results on both proprietary and public datasets demonstrate that YOLO-ERCD outperforms recent road damage detection models in accuracy and computational efficiency. The lightweight design also supports real-time deployment on edge sensing and control devices. These findings highlight the potential of integrating AI-based visual sensing and intelligent control, contributing to the development of robust, efficient, and perception-aware road monitoring systems. Full article

Object detection for autonomous vehicles under adverse weather conditions—such as rain, fog, snow, and low light—remains a significant challenge due to severe visual distortions that degrade image quality and obscure critical features. This paper presents YOLOv11-TWCS, an enhanced object detection model that integrates TransWeather, the Convolutional Block Attention Module (CBAM), and Spatial-Channel Decoupled Downsampling (SCDown) to improve feature extraction and emphasize critical features in weather-degraded scenes while maintaining real-time performance. Our approach addresses the dual challenges of weather-induced feature degradation and computational efficiency by combining adaptive attention mechanisms with optimized network architecture. Evaluations on DAWN, KITTI, and Udacity datasets show improved accuracy over baseline YOLOv11 and competitive performance against other state-of-the-art methods, achieving mAP@0.5 of 59.1%, 81.9%, and 88.5%, respectively. The model reduces parameters and GFLOPs by approximately 19–21% while sustaining high inference speed (105 FPS), making it suitable for real-time autonomous driving in challenging weather conditions. Full article

Behavior recognition and multi-object tracking of dairy cows in free-style cow barn environments play a crucial role in monitoring their health status and serve as an essential means for intelligent scientific farming. This study proposes an efficient embedded algorithm, MTW-BYTE, for dairy cow behavior recognition and multi-object tracking. It addresses challenges in free-style cow barn environments, including the impact of lighting variations and common occlusions on behavior recognition, as well as trajectory interruptions and identity ID switching during multi-object tracking. First, the MTW-YOLO cow behavior recognition model is constructed based on the YOLOv11n object detection algorithm. Replacing parts of the backbone network and neck network with MANet and introducing the Task Dynamic Align Detection Head (TDADH). The CIoU loss function of YOLOv11n is replaced with the WIoU loss. The improved model not only effectively handles variations in lighting conditions but also addresses common occlusion issues in cows, enhancing multi-scale behavior recognition capabilities and improving overall detection performance. The improved MTW-YOLO algorithm improves Precision, Recall, mAP50 and F1 score by 4.5%, 0.1%, 1.6% and 2.2%, respectively, compared to the original YOLOv11n model. Second, the ByteTrack multi-object tracking algorithm is enhanced by designing a dynamic buffer and re-detection mechanism to address cow trajectory interruptions and identity ID switching. The MTW-YOLO algorithm is cascaded with the improved ByteTrack to form the multi-target tracking algorithm MTW-BYTE. Compared with the original multi-target tracking algorithm YOLOv11n-ByteTrack (a combination of YOLOv11n and the original ByteTrack), this algorithm improves HOTA by 1.1%, MOTA by 3.6%, MOTP by 0.2%, and IDF1 by 1.9%, reduces the number of ID changes by 11, and achieves a frame rate of 43.11 FPS, which can meet the requirements of multi-target tracking of dairy cows in free-style cow barn environments. Finally, to verify the model’s applicability in real-world scenarios, the MTW-BYTE algorithm is deployed on an NVIDIA Jetson AGX Orin edge device. Based on real-time monitoring of cow behavior on the edge device, the pure inference time for a single frame is 16.62 ms, achieving an FPS of 29.95, demonstrating efficient and stable real-time behavior detection and tracking. The ability of MTW-BYTE to be deployed on edge devices to identify and continuously track cow behavior in various scenarios provides hardware feasibility verification and algorithmic support for the subsequent deployment of intelligent monitoring systems in free-style cow barn environments. Full article

In the field management of maize, phenomena such as missed sowing and empty seedlings directly affect the final yield. By implementing seedling replenishment activities and promptly evaluating seedling growth, maize output can be increased by improving seedling survival rates. To address the challenges posed by complex field environments (including varying light conditions, weeds, and foreign objects), as well as the performance limitations of model deployment on resource-constrained devices, this study proposes a Lightweight Real-Time You Only Look Once (LRT-YOLO) model. This model builds upon the You Only Look Once version 11n (YOLOv11n) framework by designing a lightweight, optimized feature architecture (OF) that enables the model to focus on the characteristics of small to medium-sized maize seedlings. The feature fusion network incorporates two key modules: the Feature Complementary Mapping Module (FCM) and the Multi-Kernel Perception Module (MKP). The FCM captures global features of maize seedlings through multi-scale interactive learning, while the MKP enhances the network’s ability to learn multi-scale features by combining different convolution kernels with pointwise convolution. In the detection head component, the introduction of an NMS-free design philosophy has significantly enhanced the model’s detection performance while simultaneously reducing its inference time. The experiments show that the $mA{P}_{50}$ and $mA{P}_{50:95}$ of the LRT-YOLO model reached 95.9% and 63.6%, respectively. The model has only 0.86M parameters and a size of just 2.35 M, representing reductions of 66.67% and 54.89% in the number of parameters and model size compared to YOLOv11n. To enable mobile deployment in field environments, this study integrates the LRT-YOLO model with the ByteTrack multi-object tracking algorithm and deploys it on the NVIDIA Jetson AGX Orin platform, utilizing OpenCV tools to achieve real-time visualization of maize seedling tracking and counting. Experiments demonstrate that the frame rate (FPS) achieved with TensorRT acceleration reached 23.49, while the inference time decreased by 38.93%. Regarding counting performance, when tested using static image data, the coefficient of determination ($R^2$) and root mean square error (RMSE) were 0.988 and 5.874, respectively. The cross-line counting method was applied to test the video data, resulting in an $R^2$ of 0.971 and an RMSE of 16.912, respectively. Experimental results show that the proposed method demonstrates efficient performance on edge devices, providing robust technical support for the rapid, non-destructive counting of maize seedlings in field environments. Full article

Hyperspectral imaging (HSI) is a noncontact camera-based technique that enables deep learning models to learn various plant conditions by detecting light reflectance under illumination. In this study, we investigated the effects of four light sources—halogen (HAL), incandescent (INC), fluorescent (FLU), and light-emitting diodes (LED)—on the quality of spectral images and the vase life (VL) of cut roses, which are vulnerable to abiotic stresses. Cut roses ‘All For Love’ and ‘White Beauty’ were used to compare cultivar-specific visible reflectance characteristics associated with contrasting petal pigmentation. HSI was performed at four time points, yielding 640 images per light source from 40 cut roses. The results revealed that the light source strongly affected both the image quality (mAP@0.5 60–80%) and VL (0–3 d) of cut roses. The HAL lamp produced high-quality spectral images across wavelengths (WL) ranging from 480 to 900 nm and yielded the highest object detection performance (ODP), reaching mAP@0.5 of 85% in ‘All For Love’ and 83% in ‘White Beauty’ with the YOLOv11x models. However, it increased petal temperature by 2.7–3 °C, thereby stimulating leaf transpiration and consequently shortening the VL of the flowers by 1–2.5 d. In contrast, INC produced unclear images with low spectral signals throughout the WL and consequently resulted in lower ODP, with mAP@0.5 of 74% and 69% in ‘All For Love’ and ‘White Beauty’, respectively. The INC only slightly increased petal temperature (1.2–1.3 °C) and shortened the VL by 1 d in the both cultivars. Although FLU and LED had only minor effects on petal temperature and VL, these illuminations generated transient spectral peaks in the WL range of 480–620 nm, resulting in decreased ODP (mAP@0.5 60–75%). Our results revealed that HAL provided reliable, high-quality spectral image data and high object detection accuracy, but simultaneously had negative effects on flower quality. Our findings suggest an alternative two-phase approach for illumination applications that uses HAL during the initial exploration of spectra corresponding to specific symptoms of interest, followed by LED for routine plant monitoring. Optimizing illumination in HSI will improve the accuracy of deep learning-based prediction and thereby contribute to the development of an automated quality sorting system that is urgently required in the cut flower industry. Full article

Non-destructive prediction of harvest timing is increasingly important in greenhouse melon cultivation, yet image-based methods alone often fail to reflect environmental factors affecting fruit development. Likewise, environmental or fertigation data alone cannot capture fruit-level variation. This gap calls for a multimodal approach integrating both sources of information. This study presents a fusion model combining RGB images with environmental and fertigation data to predict optimal harvest timing for melons. A YOLOv8n-based model detected fruits and estimated diameters under marker and no-marker conditions, while an LSTM processed time-series variables including temperature, humidity, CO₂, light intensity, irrigation, and electrical conductivity. The extracted features were fused through a late-fusion strategy, followed by an MLP for predicting diameter, biomass, and harvest date. The marker condition improved detection accuracy; however, the no-marker condition also achieved sufficiently high performance for field application. Diameter and weight showed a strong correlation (R² > 0.9), and the fusion model accurately predicted the actual harvest date of 28 August 2025. These results demonstrate the practicality of multimodal fusion for reliable, non-destructive harvest prediction and highlight its potential to bridge the gap between controlled experiments and real-world smart farming environments. Full article

This study addresses the challenges of early recognition of fruit and vegetable diseases and pests in facility horticultural greenhouses and the difficulty of real-time deployment on edge devices, and proposes a lightweight cross-scale intelligent recognition network, Light-HortiNet, designed to achieve a balance between high accuracy and high efficiency for automated greenhouse pest and disease detection. The method is built upon a lightweight Mobile-Transformer backbone and integrates a cross-scale lightweight attention mechanism, a small-object enhancement branch, and an alternative block distillation strategy, thereby effectively improving robustness and stability under complex illumination, high-humidity environments, and small-scale target scenarios. Systematic experimental evaluations were conducted on a greenhouse pest and disease dataset covering crops such as tomato, cucumber, strawberry, and pepper. The results demonstrate significant advantages in detection performance, with mAP@50 reaching $0.872$, mAP@50:95 reaching $0.561$, classification accuracy reaching $0.894$, precision reaching $0.886$, recall reaching $0.879$, and F1-score reaching $0.882$, substantially outperforming mainstream lightweight models such as YOLOv8n, YOLOv11n, MobileNetV3, and Tiny-DETR. In terms of small-object recognition capability, the model achieved an mAP-small of $0.536$ and a recall-small of $0.589$, markedly enhancing detection stability for micro pests such as whiteflies and thrips as well as early-stage disease lesions. In addition, real-time inference performance exceeding 20 FPS was achieved on edge platforms such as Jetson Nano, demonstrating favorable deployment adaptability. Full article

Defects on large-scale structural surfaces can compromise integrity and pose safety hazards, highlighting the need for efficient automated inspection. UAVs provide a flexible and effective platform for such inspections, yet traditional vision-based methods often require high computational resources and show limited sensitivity to small defects, restricting practical UAV deployment. To address these challenges, we propose ESS-DETR, a lightweight and high-precision detection model designed for UAV-based surface inspection, built upon core modules: EMO-inspired lightweight backbone that integrates convolution and efficient attention mechanisms to reduce parameters; Scale-Decoupled Loss that adaptively balances targets of various sizes to enhance accuracy and robustness for small and irregular defect patterns frequently encountered in UAV imagery; and SPPELAN multi-scale fusion module that improves feature discrimination under complex reflections, shadows, and lighting variations typical of aerial inspection environments. Experimental results demonstrate that ESS-DETR reduces computational complexity from 103.4 to 60.5 GFLOPs and achieves a Precision of 0.837, Recall of 0.738, and mAP of 79, outperforming Faster R-CNN, RT-DETR, and YOLOv11, particularly for small-scale defects, confirming that ESS-DETR effectively balances accuracy, efficiency, and onboard deployability, providing a practical solution for intelligent UAV-based surface inspection. Full article

The recognition of targets in ship remote sensing images is crucial for ship collision avoidance, military reconnaissance, and emergency rescue. However, climatic factors such as clouds and fog can obscure and blur remote sensing image targets, leading to missed and false detections in target detection. Therefore, it is necessary to study ship remote sensing target detection that considers the impact of cloud and fog occlusion. Due to the large scale and vast amount of information in remote sensing images, in order to achieve high-precision target detection based on limited resource platforms, a comparison of the detection accuracy and parameter quantity of the YOLO series algorithms was first conducted. Based on the analysis results, the YOLOv8s network model with the least number of parameters while ensuring detection accuracy was selected for lightweight network model improvement. The FasterNet was utilized to replace the backbone feature extraction network of YOLOv8s, and the detection accuracy and lightweight level of the resulting FN-YOLOv8s network model were both improved. Furthermore, structural improvements were made to the AOD-Net dehazing network. By introducing a smoothness loss function, the halo artifacts often generated during the image dehazing process were addressed. Meanwhile, by integrating the atmospheric light value and transmittance, the accumulation error was effectively reduced, significantly enhancing the dehazing effect of remote sensing images. Full article