Search Results (1,598)

Strawberries are highly perishable fruits prone to postharvest losses due to defects, diseases, and uneven ripening. This study proposes a deep learning-based approach for automated quality assessment using the YOLOv8n object detection model. A custom dataset of 5663 annotated strawberry images was compiled, covering eight quality categories, including anthracnose, gray mold, powdery mildew, uneven ripening, and physical defects. Data augmentation techniques, such as rotation and Gaussian blur, were applied to enhance model generalization and robustness. The model was trained over 100 and 200 epochs, and its performance was evaluated using standard metrics: Precision, Recall, and mean Average Precision (mAP). The 200-epoch model achieved the best results, with a mAP50 of 0.79 and an inference time of 1 ms per image, demonstrating suitability for real-time applications. Classes with distinct visual features, such as anthracnose and gray mold, were accurately classified. In contrast, visually similar categories, such as ‘Good Quality’ and ‘Unripe’ strawberries, presented classification challenges. Full article

There are significant scale and morphological differences between fire and smoke features in forest fire detection. This paper proposes a detection method based on dual-branch multi-scale adaptive feature fusion network (DMAFNet). In this method, convolutional neural network (CNN) and transformer are used to form a dual-branch backbone network to extract local texture and global context information, respectively. In order to overcome the difference in feature distribution and response scale between the two branches, a feature correction module (FCM) is designed. Through space and channel correction mechanisms, the adaptive alignment of two branch features is realized. The Fusion Feature Module (FFM) is further introduced to fully integrate dual-branch features based on the two-way cross-attention mechanism and effectively suppress redundant information. Finally, the Multi-Scale Fusion Attention Unit (MSFAU) is designed to enhance the multi-scale detection capability of fire targets. Experimental results show that the proposed DMAFNet has significantly improved in mAP (mean average precision) indicators compared with existing mainstream detection methods. Full article

The current paper presents a comprehensive intelligent system designed to optimize the performance of a barrier eddy current separator (BECS), comprising a conveyor belt, a vibration feeder, and a magnetic drum. This system was trained and validated on real-world industrial data gathered directly from the working separator under 81 different operational scenarios. The intelligent models were used to recommend optimal settings for drum speed, belt speed, vibration intensity, and drum angle, thereby maximizing separation quality and minimizing energy consumption. the smart separation module utilizes YOLOv11n-seg and achieves a mean average precision (mAP) of 0.838 across 7163 industrial instances from aluminum, copper, and plastic materials. For shape classification (sharp vs. smooth), the model reached 91.8% accuracy across 1105 annotated samples. Furthermore, the thermal monitoring unit can detect iron contamination by analyzing temperature anomalies. Scenarios with iron showed a maximum temperature increase of over 20 °C compared to clean materials, with a detection response time of under 2.5 s. The architecture integrates a Digital Twin using Azure Digital Twins to virtually mirror the system, enabling real-time tracking, behavior simulation, and remote updates. A full connection with the PLC has been implemented, allowing the AI-driven system to adjust physical parameters autonomously. This combination of AI, IoT, and digital twin technologies delivers a reliable and scalable solution for enhanced separation quality, improved operational safety, and predictive maintenance in industrial recycling environments. Full article

Background/Objectives: Melanoma is an aggressive type of skin cancer that poses serious health risks if not detected in its early stages. Although early diagnosis enables effective treatment, delays can result in life-threatening consequences. Traditional diagnostic processes predominantly rely on the subjective expertise of dermatologists, which can lead to variability and time inefficiencies. Consequently, there is an increasing demand for automated systems that can accurately classify melanoma lesions and retrieve visually similar cases to support clinical decision-making. Methods: This study proposes a transfer learning (TL)-based deep learning (DL) framework for the classification of melanoma images and the enhancement of content-based image retrieval (CBIR) systems. Pre-trained models including DenseNet121, InceptionV3, Vision Transformer (ViT), and Xception were employed to extract deep feature representations. These features were integrated using a weighted fusion strategy and classified through an Ensemble learning approach designed to capitalize on the complementary strengths of the individual models. The performance of the proposed system was evaluated using classification accuracy and mean Average Precision (mAP) metrics. Results: Experimental evaluations demonstrated that the proposed Ensemble model significantly outperformed each standalone model in both classification and retrieval tasks. The Ensemble approach achieved a classification accuracy of 95.25%. In the CBIR task, the system attained a mean Average Precision (mAP) score of 0.9538, indicating high retrieval effectiveness. The performance gains were attributed to the synergistic integration of features from diverse model architectures through the ensemble and fusion strategies. Conclusions: The findings underscore the effectiveness of TL-based DL models in automating melanoma image classification and enhancing CBIR systems. The integration of deep features from multiple pre-trained models using an Ensemble approach not only improved accuracy but also demonstrated robustness in feature generalization. This approach holds promise for integration into clinical workflows, offering improved diagnostic accuracy and efficiency in the early detection of melanoma. Full article

Early crop yield prediction is a major challenge in precision agriculture, and efficient and rapid yield prediction is highly important for sustainable fruit production. The accurate detection of major fruit characteristics, including flowering, green fruiting, and ripening stages, is crucial for early yield estimation. Currently, most crop yield estimation studies based on the YOLO model are only conducted during a single stage of maturity. Combining multi-growth period data for crop analysis is of great significance for crop growth detection and early yield estimation. In this study, a new network model, YOLOv8-RL, was proposed using citrus multigrowth period characteristics as a data source. A citrus yield estimation model was constructed and validated by combining network identification counts with manual field counts. Compared with YOLOv8, the number of parameters of the improved network is reduced by 50.7%, the number of floating-point operations is decreased by 49.4%, and the size of the model is only 3.2 MB. In the test set, the average recognition rate of citrus flowers, green fruits, and orange fruits was 95.6%, the mAP@.5 was 94.6%, the FPS value was 123.1, and the inference time was only 2.3 milliseconds. This provides a reference for the design of lightweight networks and offers the possibility of deployment on embedded devices with limited computational resources. The two estimation models constructed on the basis of the new network had coefficients of determination R² values of 0.91992 and 0.95639, respectively, with a prediction error rate of 6.96% for citrus green fruits and an average error rate of 3.71% for orange fruits. Compared with network counting, the yield estimation model had a low error rate and high accuracy, which provided a theoretical basis and technical support for the early prediction of fruit yield in complex environments. Full article

Accurate identification of predator–pest relationships is essential for implementing effective and sustainable biological control in agriculture. However, existing image-based methods struggle to recognize insect co-occurrence under complex field conditions, limiting their ecological applicability. To address this challenge, we propose a hybrid deep learning framework that integrates convolutional neural networks (CNNs) and Transformer architectures for multi-label recognition of predator–pest combinations. The model leverages a novel co-occurrence attention mechanism to capture semantic relationships between insect categories and employs a pairwise label matching loss to enhance ecological pairing accuracy. Evaluated on a field-constructed dataset of 5,037 images across eight categories, the model achieved an F1-score of 86.5%, mAP50 of 85.1%, and demonstrated strong generalization to unseen predator–pest pairs with an average F1-score of 79.6%. These results outperform several strong baselines, including ResNet-50, YOLOv8, and Vision Transformer. This work contributes a robust, interpretable approach for multi-object ecological detection and offers practical potential for deployment in smart farming systems, UAV-based monitoring, and precision pest management. Full article

Surface defects of photovoltaic (PV) cells can seriously affect power generation efficiency. Accurately detecting such defects and handling them in a timely manner can effectively improve power generation efficiency. Aiming at the high-precision and real-time requirements for surface defect detection during the use of PV cells, this paper proposes a PV cell surface defect detection algorithm based on SEC-YOLOv8. The algorithm first replaces the Spatial Pyramid Pooling Fast module with the SPPELAN pooling module to reduce channel calculations between convolutions. Second, an ECA attention mechanism is added to enable the model to pay more attention to feature extraction in defect areas and avoid target detection interference from complex environments. Finally, the upsampling operator CARAFE is introduced in the Neck part to solve the problem of scale mismatch and enhance detection performance. Experimental results show that the improved model achieves a mean average precision (mAP@0.5) of 69.2% on the PV cell dataset, which is 2.6% higher than the original network, which is designed to achieve a superior balance between the competing demands of accuracy and computational efficiency for PV defect detection. Full article

Temporal action localization (TAL) is a research hotspot in video understanding, which aims to locate and classify actions in videos. However, existing methods have difficulties in capturing long-term actions due to focusing on local temporal information, which leads to poor performance in localizing long-term temporal sequences. In addition, most methods ignore the boundary importance for action instances, resulting in inaccurate localized boundaries. To address these issues, this paper proposes a state space model for temporal action localization, called Separated Bidirectional Mamba (SBM), which innovatively understands frame changes from the perspective of state transformation. It adapts to different sequence lengths and incorporates state information from the forward and backward for each frame through forward Mamba and backward Mamba to obtain more comprehensive action representations, enhancing modeling capabilities for long-term temporal sequences. Moreover, this paper designs a Boundary Correction Strategy (BCS). It calculates the contribution of each frame to action instances based on the pre-localized results, then adjusts weights of frames in boundary regression to ensure the boundaries are shifted towards the frames with higher contributions, leading to more accurate boundaries. To demonstrate the effectiveness of the proposed method, this paper reports mean Average Precision (mAP) under temporal Intersection over Union (tIoU) thresholds on four challenging benchmarks: THUMOS13, ActivityNet-1.3, HACS, and FineAction, where the proposed method achieves mAPs of 73.7%, 42.0%, 45.2%, and 29.1%, respectively, surpassing the state-of-the-art approaches. Full article

Foraging behavior in hens is an important indicator of animal welfare. It involves both the search for food and exploration of the environment, which provides necessary enrichment. In addition, it has been inversely linked to damaging behaviors such as severe feather pecking. Conventional studies rely on manual observation to investigate foraging location, duration, timing, and frequency. However, this approach is labor-intensive, time-consuming, and subject to human bias. Our study developed computer vision-based methods to automatically detect foraging hens in a cage-free research environment and compared their performance. A cage-free room was divided into four pens, two larger pens measuring 2.9 m × 2.3 m with 30 hens each and two smaller pens measuring 2.3 m × 1.8 m with 18 hens each. Cameras were positioned vertically, 2.75 m above the floor, recording the videos at 15 frames per second. Out of 4886 images, 70% were used for model training, 20% for validation, and 10% for testing. We trained multiple You Only Look Once (YOLO) object detection models from YOLOv9, YOLOv10, and YOLO11 series for 100 epochs each. All the models achieved precision, recall, and mean average precision at 0.5 intersection over union (mAP@0.5) above 75%. YOLOv9c achieved the highest precision (83.9%), YOLO11x achieved the highest recall (86.7%), and YOLO11m achieved the highest mAP@0.5 (89.5%). These results demonstrate the use of computer vision to automatically detect complex poultry behavior, such as foraging, making it more efficient. Full article

Many traffic-sign detection systems are available to assist drivers with particular conditions such as small and distant signs, multiple signs on the road, objects similar to signs, and other challenging conditions. Real-time object detection is an indispensable aspect of these detection systems, with detection speed and efficiency being critical parameters. In terms of these parameters, to enhance performance in road-sign detection under diverse conditions, we proposed a comprehensive methodology, SSAM_YOLOv5, to handle feature extraction and small-road-sign detection performance. The method was based on a modified version of YOLOv5s. First, we introduced attention modules into the backbone to focus on the region of interest within video frames; secondly, we replaced the activation function with the SwishT_C activation function to enhance feature extraction and achieve a balance between inference, precision, and mean average precision (mAP@50) rates. Compared to the YOLOv5 baseline, the proposed improvements achieved remarkable increases of 1.4% and 1.9% in mAP@50 on the Tiny LISA and GTSDB datasets, respectively, confirming their effectiveness. Full article

Object detection in aerial images can provide great support in traffic planning, national defense reconnaissance, hydrographic surveys, infrastructure construction, and other fields. Objects in aerial images are characterized by small pixel–area ratios, dense arrangements between objects, and arbitrary inclination angles. In response to these characteristics and problems, we improved the feature extraction network Inception-ResNet using the Fast Architecture Search (FAS) module and proposed a one-stage anchor-free rotation object detector. The structure of the object detector is simple and only consists of convolution layers, which reduces the number of model parameters. At the same time, the label sampling strategy in the training process is optimized to resolve the problem of insufficient sampling. Finally, a decoupled object detection head is used to separate the bounding box regression task from the object classification task. The experimental results show that the proposed method achieves mean average precision (mAP) of 82.6%, 79.5%, and 89.1% on the DOTA1.0, DOTA1.5, and HRSC2016 datasets, respectively, and the detection speed reaches 24.4 FPS, which can meet the needs of real-time detection. Full article

With the rapid development of smart devices and the Internet of Things (IoT), the explosive growth of data has placed increasingly higher demands on real-time processing and intelligent decision making. Cloud-edge collaborative computing has emerged as a mainstream architecture to address these challenges. However, in sky-ground integrated systems, the limited computing capacity of edge devices and the inconsistency between cloud-side fusion results and edge-side detection outputs significantly undermine the reliability of edge inference. To overcome these issues, this paper proposes a cloud-edge collaborative model adaptation framework that integrates deep reinforcement learning via Deep Q-Networks (DQN) with local feature transfer. The framework enables category-level dynamic decision making, allowing for selective migration of classification head parameters to achieve on-demand adaptive optimization of the edge model and enhance consistency between cloud and edge results. Extensive experiments conducted on a large-scale multi-view remote sensing aircraft detection dataset demonstrate that the proposed method significantly improves cloud-edge consistency. The detection consistency rate reaches 90%, with some scenarios approaching 100%. Ablation studies further validate the necessity of the DQN-based decision strategy, which clearly outperforms static heuristics. In the model adaptation comparison, the proposed method improves the detection precision of the A321 category from 70.30% to 71.00% and the average precision (AP) from 53.66% to 53.71%. For the A330 category, the precision increases from 32.26% to 39.62%, indicating strong adaptability across different target types. This study offers a novel and effective solution for cloud-edge model adaptation under resource-constrained conditions, enhancing both the consistency of cloud-edge fusion and the robustness of edge-side intelligent inference. Full article

This study addresses the challenges of manual measurement bias and low robustness in detecting small, occluded targets in complex marine environments during real-time onboard sorting of Portunus trituberculatus. We propose YOLO-DFAM, an enhanced YOLOv11n-based model that replaces the global average pooling in the Focal Modulation module with a spatial–channel dual-attention mechanism and incorporates the ASF-YOLO cross-scale fusion strategy to improve feature representation across varying target sizes. These enhancements significantly boost detection, achieving an mAP@50 of 98.0% and precision of 94.6%, outperforming RetinaNet-CSL and Rotated Faster R-CNN by up to 6.3% while maintaining real-time inference at 180.3 FPS with only 7.2 GFLOPs. Unlike prior static-scene approaches, our unified framework integrates attention-guided detection, scale-adaptive tracking, and lightweight weight estimation for dynamic marine conditions. A ByteTrack-based tracking module with dynamic scale calibration, EMA filtering, and optical flow compensation ensures stable multi-frame tracking. Additionally, a region-specific allometric weight estimation model (R² = 0.9856) reduces dimensional errors by 85.7% and maintains prediction errors below 4.7% using only 12 spline-interpolated calibration sets. YOLO-DFAM provides an accurate, efficient solution for intelligent onboard fishery monitoring. Full article

In response to the limited research on fire detection in cotton pickers and the issue of low detection accuracy in visual inspection, this paper proposes a computer vision-based detection method. The method is optimized according to the structural characteristics of cotton pickers, and a lightweight improved YOLOv11 algorithm is designed for cotton fire detection in cotton pickers. The backbone of the model is replaced with the MobileNetV2 network to achieve effective model lightweighting. In addition, the convolutional layers in the original C3k2 block are optimized using partial convolutions to reduce computational redundancy and improve inference efficiency. Furthermore, a visual attention mechanism named CBAM-ECA (Convolutional Block Attention Module-Efficient Channel Attention) is designed to suit the complex working conditions of cotton pickers. This mechanism aims to enhance the model’s feature extraction capability under challenging environmental conditions, thereby improving overall detection accuracy. To further improve localization performance and accelerate convergence, the loss function is also modified. These improvements enable the model to achieve higher precision in fire detection while ensuring fast and accurate localization. Experimental results demonstrate that the improved model reduces the number of parameters by 38%, increases the frame processing speed (FPS) by 13.2%, and decreases the computational complexity (GFLOPs) by 42.8%, compared to the original model. The detection accuracy for flaming combustion, smoldering combustion, and overall detection is improved by 1.4%, 3%, and 1.9%, respectively, with an increase of 2.4% in mAP (mean average precision). Compared to other models—YOLOv3-tiny, YOLOv5, YOLOv8, and YOLOv10—the proposed method achieves higher detection accuracy by 5.9%, 7%, 5.9%, and 5.3%, respectively, and shows improvements in mAP by 5.4%, 5%, 4.8%, and 6.3%. The improved detection algorithm maintains high accuracy while achieving faster inference speed and fewer model parameters. These improvements lay a solid foundation for fire prevention and suppression in cotton collection boxes on cotton pickers. Full article

Smoke appears earlier than flames, so image-based fire monitoring techniques mainly focus on the detection of smoke, which is regarded as one of the effective strategies for preventing the spread of initial fires that eventually evolve into serious fires. Smoke monitoring in mine fires faces serious challenges: the underground environment is complex, with smoke and backgrounds being highly integrated and visual features being blurred, which makes it difficult for existing image-based monitoring techniques to meet the actual needs in terms of accuracy and robustness. The conventional ground-based methods are directly used in the underground with a high rate of missed detection and false detection. Aiming at the core problems of mixed target and background information and high boundary uncertainty in smoke images, this paper, inspired by the principle of information entropy, proposes a method for recognizing smoke from mine fires by integrating entropy-enhanced image processing and improved YOLOv8. Firstly, according to the entropy change characteristics of spatio-temporal information brought by smoke diffusion movement, based on spatio-temporal entropy separation, an equidistant frame image differential fusion method is proposed, which effectively suppresses the low entropy background noise, enhances the detail clarity of the high entropy smoke region, and significantly improves the image signal-to-noise ratio. Further, in order to cope with the variable scale and complex texture (high information entropy) of the smoke target, an improvement mechanism based on entropy-constrained feature focusing is introduced on the basis of the YOLOv8m model, so as to more effectively capture and distinguish the rich detailed features and uncertain information of the smoke region, realizing the balanced and accurate detection of large and small smoke targets. The experiments show that the comprehensive performance of the proposed method is significantly better than the baseline model and similar algorithms, and it can meet the demand of real-time detection. Compared with YOLOv9m, YOLOv10n, and YOLOv11n, although there is a decrease in inference speed, the accuracy, recall, average detection accuracy mAP (50), and mAP (50–95) performance metrics are all substantially improved. The precision and robustness of smoke recognition in complex mine scenarios are effectively improved. Full article