Search Results (79)

With the rapid development of maritime transportation and resource development activities, maritime distress events are increasingly frequent, and efficient and accurate target recognition and rescue response methods are urgently needed. The traditional monitoring methods are limited by efficiency and real time, which is difficult to adapt to the complex and changeable marine environment. Therefore, based on the RT-DETR model of transformer architecture, an improved scheme for maritime distress target detection is proposed to improve the small target recognition ability and detection efficiency. Specific improvements include: a small target-focused convolution module (SFConv) is designed to enhance the efficiency of feature extraction and reasoning of small-scale targets; The cross-scale feature interaction optimization module (SPE) is further proposed to improve the ability of multi-scale perception and background suppression; The Focaler-DIoU loss function is introduced to enhance the discrimination performance of the model for difficult samples. On the basis of maintaining the end-to-end detection advantage of RT-DETR, the improvement is of 0.83474, which is 5.7% higher than the original model (0.78964). The accuracy and robustness of the model in complex marine environment is significantly improved, and technical support is provided for the construction of an efficient and intelligent marine monitoring and emergency response system. Full article

Automated pavement distress detection (PDD) is critical for the structural health monitoring (SHM) of transportation infrastructure, yet existing methods struggle with real-time multi-target detection under resource constraints. In this paper, YOLOv8-PDD was constructed based on YOLOv8 by introducing the large separable kernel attention (LSKA) mechanism module into the Spatial Pyramid Pooling—Fast (SPPF) module, replacing Complete-IoU (CIoU) loss with Distance-IoU (DIOU) loss as the loss function, and adopting Soft-Non-Maximum Suppression (NMS) to replace the original NMS algorithm. The proposed YOLOv8-PDD achieved 78.3% mean average precision with intersection over union above 0.5 (mAP@0.5 +8.1%) with a minimal complexity increase of +0.2 GFLOPs compared to the baseline YOLOv8n model. While incurring a negligible increase in latency (+0.09 ms), YOLOv8-PDD significantly outperforms YOLOv8n in detection accuracy (mAP@0.5 +8.1%), offering a superior accuracy–efficiency trade-off for real-time applications. YOLOv8-PDD performed well in detecting all categories, with AP values above 75% except for transverse crack and strip patch. Significant improvements in pothole detection AP@0.5 (+22.1%) and strip patch detection AP@0.5 (+17.7%) indicate superior small target and complex background adaptability. Our model achieved a detection efficiency of 68 frames per second (FPS) on consumer-grade CPUs (OpenVINO-optimized), outperforming 10 models (e.g., YOLOv5n and RTDETR-l) in accuracy–speed balance. Full article

In modern smart dairy farms, precise feed management and accurate monitoring of dairy cows’ feeding behavior are crucial for improving production efficiency and reducing feeding costs. However, in practical applications, complex environmental factors such as varying illumination, frequent occlusion, and dense multi-targets pose significant challenges to real-time visual perception. To address these issues, this paper proposes a lightweight multi-target detection model, BFDet-YOLO, for the joint detection of dairy cows’ feeding behavior and feed density levels in pasture environments. Based on the YOLOv10 framework, the model incorporates four targeted improvements: (1) a bidirectional feature fusion network (BiFPN) to address the insufficient multi-scale feature interaction between dairy cows (large targets) and feed particles (small targets); (2) a lightweight downsampling module (Adown) to preserve fine-grained features of feed particles and reduce the risk of small target miss detection; (3) an attention-enhanced detection head (SEAM) to mitigate occlusion interference caused by cow stacking and feed accumulation; (4) an improved bounding box regression loss function (DIoU) to optimize the localization accuracy of non-overlapping small targets. Additionally, this paper constructs a pasture-specific dataset integrating dairy cows’ feeding behavior and feed distribution information, which is annotated and expanded by combining public datasets with on-site monitoring data. Experimental results demonstrate that BFDet-YOLO outperforms the original YOLOv10 and other mainstream target recognition models in terms of detection accuracy and robustness while maintaining a significantly streamlined model scale. On the constructed dataset, the model achieves 95.7% mAP@0.5 and 70.7% mAP@0.5:0.95 with only 1.85 M parameters. These results validate the effectiveness and deployability of the proposed method, providing a reliable visual perception solution for intelligent feeding systems and smart pasture management. Full article

Background: In tropical regions, dengue and leptospirosis coexist and share a nonspecific clinical onset that hinders timely diagnosis. Coinfection may worsen the clinical course and increase mortality. Objective: To estimate the prevalence of dengue, leptospirosis, and coinfection among patients with febrile syndrome in Madre de Dios (Peru) and to identify associated clinical factors. Methods: Observational, analytical, cross-sectional, retrospective study conducted at a primary-level health facility. Clinical and laboratory records of patients with febrile syndrome seen in 2024 were analyzed. Categorical variables were summarized as frequencies (%) and numeric variables as mean ± SD or median [IQR]. Comparisons used chi-square or Fisher’s exact test, Student’s t test, or the Mann–Whitney U test, as appropriate. Associations were estimated using Poisson regression models with robust variance, adjusted for sex, reporting prevalence ratios (PRs) and 95% CIs. Analyses were performed in R 4.0.2. Results: A total of 226 patients were included. Positivity was 19.0% for dengue (43/226), 66.8% for leptospirosis (151/226), and 5.8% for coinfection (13/226). In the bivariate analysis, dengue was associated with higher temperature (p < 0.001), lower mean arterial pressure (p = 0.007), mucosal bleeding/ecchymosis (p = 0.049), and lower fluid intake (p = 0.021); temperature was also higher in coinfection (p = 0.021). In Poisson models, dengue was associated with tachycardia (PR = 5.69; 95% CI: 1.95–13.07; p < 0.001), temperature (PR = 1.61 per °C; 1.23–2.12; p = 0.001), bilateral polyarthralgia (PR = 2.55; 1.14–5.04; p = 0.012), and mucosal bleeding/ecchymosis (PR = 3.31; 0.94–8.37; p = 0.027). Leptospirosis was associated with male sex (PR = 0.78 vs. female; 0.65–0.94; p = 0.010) and fever (PR = 2.38; 1.17–6.03; p = 0.035). Leptospira–dengue coinfection was related to higher temperature (PR = 1.75 per °C; 1.05–3.01; p = 0.036). Conclusions: Simple clinical signs such as fever/elevated temperature, tachycardia, bilateral polyarthralgia, and mucosal bleeding can help prioritize suspicion of dengue, leptospirosis, or coinfection; guide requests for dual testing (dengue–Leptospira), early hydration in dengue, and timely initiation of antibiotic therapy in leptospirosis. These findings support the development of integrated triage algorithms and strengthening access to molecular diagnostics in high-burden febrile syndrome settings. Full article

Underground utility tunnels face corrosion, cracks, and leakage after long-term use, endangering urban safety. Traditional methods have strong subjectivity, high miss rates, and poor real-time performance, failing refined management needs. This paper proposes an attention-enhanced YOLOv11 rather than YOLOv10 because its C3k2 backbone and dynamic anchor head already surpass YOLOv10 by 1.8% mAP for pipeline defect detection in utility tunnels. It uses homomorphic filtering to improve low-light image quality; replaces the last two C3k2 modules of the original YOLOv11 with a Multi-Scale Feature Aggregation Module to capture micro-cracks via expanded receptive fields; introduces a bidirectional weighted feature pyramid network in the neck (with C2PSA/BRA attention) for cross-scale feature fusion and background suppression, which yields both fine-grained micro-crack sensitivity and global false-target suppression; and adopts DIoU loss in the detection head to reduce slender defect localization errors. Experiments on 5000 utility tunnel defect images show the improved algorithm achieves 93.2% precision, 92.4% recall, and 92.6% mAP—outperforming the original YOLOv11, Faster R-CNN, and YOLOv5. Ablation experiments confirm module effectiveness, cutting relative error by 75% compared with the baseline. This algorithm can accurately identify multiple types of defects in complex utility tunnel environments, providing technical support for the safe and efficient operation and maintenance of urban infrastructure. Full article

Background: Chronic pain is a prevalent and disabling condition, affecting 20–30% of the global population, which requires multidisciplinary approaches integrating non-pharmacological therapies and promoting patient engagement in self-management. Objective: To describe the structure, content, outcomes, and lessons learned from multicomponent workshops for chronic non-cancer pain using non-pharmacological therapies. Methods: A quasi-experimental before–after study was conducted in patients attending a chronic pain workshop at San Juan de Dios Hospital (Bormujos, Seville, Spain) between November 2021 and May 2024, with a 3-month follow-up, Validated scales and an ad hoc patient survey were administered at baseline, immediately post-workshop, and at 3-month follow-up. Furthermore, comparative analysis was conducted 4 months before and after the intervention for emergency visits and consultations, medication consumption, and employment status. Analyses employed Chi-square or Fisher’s exact tests (categorical variables); student’s t-tests or Mann–Whitney U (between-group); paired t-tests or Wilcoxon (within-group pre–post); and effect sizes (Cohen’s d, Rosenthal’s r). Significance was set at p < 0.05. Results: 197 patients completed the workshop; 178 (90.4%) were women, mean age: 55.0; 114 (57.9%) had fibromyalgia. Reductions were observed in: pain (scale 0–10) (baseline: 7.0; end of workshop: 5.0; 3 months: 5.0; p < 0.001); anxiety (13.0; 9.0; 11.0; p < 0.001); and depression (11.4; 7.2; 6.8; p < 0.001) (scales 0–21). Increases were noted in: well-being (scale 0–10) (4.0; 6.0; 5.0; p < 0.001); quality of life (scale 0–1) (0.399; 0.581; 0.556; p < 0.001); health status (scale 0–100) (40.0; 60.0; 60.0; p < 0.001); self-esteem (scale 9–36) (23.5; 27.1; 26.6; p < 0.001); and resilience (scale 6–30) (17.0; 18.0; 18.0; p = 0.002, p < 0.001). PROMs were completed by 189 patients at the end of the workshop and 110 at 3 months: pain decreased (end of workshop: 76.7%; 3 months: 80.7%); medication decreased (80.5%; 78.1%); and habits improved (87.2%; 87.6%). 40 patients (37.4%) reduced emergency visits and scheduled consultations. Overall satisfaction: 9.7. Conclusions: The workshop enhanced patients’ self-management and produced improvements in pain, quality of life, emotional well-being, and self-esteem, with effects maintained at 3 months. Full article

Harvesting winter jujubes is a key step in production, yet traditional manual approaches are labor-intensive and inefficient. To overcome these challenges, we propose SCC-YOLO, a lightweight method for winter jujube detection, 3D localization, and cross-platform deployment, aiming to support intelligent harvesting. In this study, RGB-D cameras were integrated with an improved YOLOv11 network optimized by ShuffleNetV2, CBAM, and a redesigned C2f_WTConv module, which enables joint spatial–frequency feature modeling and enhances small-object detection in complex orchard conditions. The model was trained on a diversified dataset with extensive augmentation to ensure robustness. In addition, the original localization loss was replaced with DIoU to improve bounding box regression accuracy. A robotic harvesting system was developed, and an Eye-to-Hand calibration-based 3D localization pipeline was implemented to map fruit coordinates to the robot workspace for accurate picking. To validate engineering applicability, the SCC-YOLO model was deployed on both desktop (PyTorch and ONNX Runtime) and mobile (NCNN with Vulkan+FP16) platforms, and FPS, latency, and stability were comparatively analyzed. Experimental results showed that SCC-YOLO improved mAP by 5.6% over YOLOv11, significantly enhanced detection precision and robustness, and achieved real-time performance on mobile devices while maintaining peak throughput on high-performance desktops. Field and laboratory tests confirmed the system’s effectiveness for detection, localization, and harvesting efficiency, demonstrating its adaptability to diverse deployment environments and its potential for broader agricultural applications. Full article

Efficient threat detection in X-ray cargo inspection is critical for the security of the global supply chain. This study evaluates YOLO-based object-detection models from YOLOv5 to the latest, YOLOv11, which is enhanced with modified loss functions and Soft-NMS to improve accuracy. The YOLO model comparison also includes DETR (Detection Transformer) and Faster R-CNN (Region-based Convolution Neural Network). Standard loss functions struggle with overlapping items, low contrast, and small objects in X-ray imagery. To overcome these weaknesses, IoU-based loss functions—CIoU, DIoU, GIoU, and WIoU—are integrated into the YOLO frameworks. Experiments on a dedicated cargo X-ray dataset assess precision, recall, F1-score, mAP@50, mAP@50–95, GFLOPs, and inference speed. The enhanced model, YOLOv11 with WIoU and Soft-NMS, achieves superior localization, reaching 98.44% mAP@50. This work highlights effective enhancements for YOLO models to support intelligent logistics in transportation services and automated threat detection in cargo security systems. Full article

As a globally significant oil crop, precise ripeness identification of palm fruits directly impacts harvesting efficiency and oil quality. However, the progress and application of identifying the ripeness of palm fruits have been impeded by the computational limitations of agricultural hardware and the insufficient robustness in accurately identifying palm fruits in complex on-tree environments. To address these challenges, this paper proposes an efficient recognition network tailored for complex canopy-level palm fruit ripeness assessment. Progressive combination optimization enhances the baseline network, which utilizes the YOLOv8 architecture. This study has individually enhanced the backbone network, neck, detection head, and loss function. Specifically, the backbone integrates the StarNet framework, while the detection head incorporates the lightweight LSCD structure. To enhance recognition precision, StarNet-derived Star Blocks replace standard bottleneck modules in the neck, forming optimized C2F-Star components, complemented by DIoU loss implementation to accelerate convergence. The resultant on-tree model for recognizing palm fruit ripeness achieves substantial efficiency gains. While simultaneously elevating detection precision to 76.0% mAP@0.5, our method’s GFLOPs, parameters, and model size are only 4.5 G, 1.37 M, and 2.85 MB, which are 56.0%, 46.0%, and 48.0% of the original model. The effectiveness of the model in recognizing palm fruit ripeness in complex environments, such as uneven lighting, motion blur, and occlusion, validates its robustness. Full article

The popularity of keeping ornamental fish has grown increasingly, as their vibrant presence can provide a calming influence. Accurately assessing the health of ornamental fish is important but challenging. For this, researchers have focused on developing fish tracking methods that provide trajectories for health assessment. However, issues such as mirror images, occlusion, and motion prediction errors can significantly reduce the accuracy of existing algorithms. To address these problems, we propose a novel ornamental fish tracking method based on deep learning techniques. We first utilize the You Only Look Once (YOLO) v5 deep convolutional neural network algorithm with Distance Intersection over Union–Non Maximum Suppression (DIoU-NMS) to handle occlusion problems. We then design an object removal algorithm to eliminate fish mirror image coordinates. Finally, we adopt an improved DeepSORT algorithm, replacing the original Kalman Filter with an advanced Noise Scale Adaptive (NSA) Kalman Filter to enhance tracking accuracy. In our experiment, we evaluated our method in three simulated real-world fish tank environments, comparing it with the YOLOv5 and YOLOv7 methods. The results show that our method can increase Multiple Object Tracking Accuracy (MOTA) by up to 13.3%, Higher Order Tracking Accuracy (HOTA) by up to 10.0%, and Identification F1 Score by up to 14.5%. These findings confirm that our object removal algorithm effectively improves Multiple Object Tracking Accuracy, which facilitates early disease detection, reduces mortality, and mitigates economic losses—an important consideration given many owners’ limited ability to recognize common diseases. Full article

With its unique climate and geographical advantages, Yunnan Province in China has become one of the country’s most important citrus-growing regions. However, the dense foliage and large fruit size of citrus trees often result in significant occlusion, and the fluctuating light intensity further complicates accurate assessment of fruit maturity. To address these challenges, this study proposes an improved model based on YOLOv8, named ORD-YOLO, for citrus fruit maturity detection. To enhance the model’s robustness in complex environments, several key improvements have been introduced. First, the standard convolution operations are replaced with Omni-Dimensional Dynamic Convolution (ODConv) to improve feature extraction capabilities. Second, the feature fusion process is optimized and inference speed is increased by integrating a Re-parameterizable Generalized Feature Pyramid Network (RepGFPN). Third, the detection head is redesigned using a Dynamic Head structure that leverages dynamic attention mechanisms to enhance key feature perception. Additionally, the loss function is optimized using InnerDIoU to improve object localization accuracy. Experimental results demonstrate that the enhanced ORD-YOLO model achieves a precision of 93.83%, a recall of 91.62%, and a mean Average Precision (mAP) of 96.92%, representing improvements of 4.66%, 3.3%, and 3%, respectively, over the original YOLOv8 model. ORD-YOLO not only maintains stable and accurate citrus fruit maturity recognition under complex backgrounds, but also significantly reduces misjudgment caused by manual assessments. Furthermore, the model enables real-time, non-destructive detection. When deployed on harvesting robots, it can substantially increase picking efficiency and reduce post-maturity fruit rot due to delayed harvesting. These advancements contribute meaningfully to the quality improvement, efficiency enhancement, and digital transformation of the citrus industry. Full article

Accurate detection of surface defects on passion fruits is crucial for maintaining market competitiveness. Numerous small defects present significant challenges for manual inspection. Recently, deep learning (DL) has been widely applied to object detection. In this study, a lightweight neural network, StarC3SE-CBAM-DIoU-YOLOv5s (SCD-YOLOv5s), is proposed based on YOLOv5s for real-time detection of tiny surface defects on passion fruits. Key improvements are introduced as follows: the original C3 module in the backbone is replaced by the enhanced StarC3SE module to achieve a more efficient network structure; the CBAM module is integrated into the neck to improve the extraction of small defect features; and the CIoU loss function is substituted with DIoU-NMS to accelerate convergence and enhance detection accuracy. Experimental results show that SCD-YOLOv5s performs better than YOLOv5s, with precision increased by 13.2%, recall by 1.6%, and F₁-score by 17.0%. Additionally, improvements of 6.7% in mAP@0.5 and 5.5% in mAP@0.95 are observed. Compared with manual detection, the proposed model enhances detection efficiency by reducing errors caused by subjective judgment. It also achieves faster inference speed (26.66 FPS), and reductions of 9.6% in parameters and 8.6% in weight size, while maintaining high detection performance. These results indicate that SCD-YOLOv5s is effective for defect detection in agricultural applications. Full article

In response to the challenges of low accuracy in traditional pepper blight identification under natural complex conditions, particularly in detecting subtle infections on early-stage leaves, stems, and fruits. This study proposes a multi-site pepper blight disease image recognition algorithm based on YOLOv8, named MSPB-YOLO. This algorithm effectively locates different infection sites on peppers. By incorporating the RVB-EMA module into the model, we can significantly reduce interference from shallow noise in high-resolution depth layers. Additionally, the introduction of the RepGFPN network structure enhances the model’s capability for multi-scale feature fusion, resulting in a marked improvement in multi-target detection accuracy. Furthermore, we optimized CIOU to DIOU by integrating the center distance of bounding boxes into the loss function; as a result, the model achieved an impressive mAP@0.5 score of 96.4%. This represents an enhancement of 2.2% over the original algorithm’s mAP@0.5. Overall, this model provides effective technical support for promoting intelligent management and disease prevention strategies for peppers. Full article

In commercial poultry farming, automated behavioral monitoring systems hold significant potential for optimizing production efficiency and improving welfare outcomes at scale. The behavioral detection of free-range broilers matters for precision farming and animal welfare. Current research often focuses on either behavior detection or individual tracking, with few studies exploring their connection. To continuously track broiler behaviors, the Only Detect Broilers Once (ODBO) method is proposed by linking behaviors with identity information. This method has a behavior detector, an individual Tracker, and a Connector. First, by integrating SimAM, WIOU, and DIOU-NMS into YOLOv8m, the high-performance YOLOv8-BeCS detector is created. It boosts P by 6.3% and AP by 3.4% compared to the original detector. Second, the designed Connector, based on the tracking-by-detection structure, transforms the tracking task, combining broiler tracking and behavior recognition. Tests on sort-series trackers show HOTA, MOTA, and IDF1 increase by 27.66%, 28%, and 27.96%, respectively, after adding the Connector. Fine-tuning experiments verify the model’s generalization. The results show this method outperforms others in accuracy, generalization, and convergence speed, providing an effective method for monitoring individual broiler behaviors. In addition, the system’s ability to simultaneously monitor individual bird welfare indicators and group dynamics could enable data-driven decisions in commercial poultry farming management. Full article

This study investigates how urban decline and intensifying flood hazards interact to threaten Japan’s urban environments, focusing on three main dimensions. First, a fine-scale analysis of spatial shrinkage was conducted using transition potential maps generated with a maximum entropy classifier. This approach enabled the identification of neighborhoods at high risk of future abandonment, revealing that peripheral districts, such as Hirakue-cho and Shimoirino-cho, are especially susceptible due to their distance from central amenities. Second, this study analyzed the 2019 Naka River flood induced by Typhoon Hagibis, evaluating water detection performance through both a U-Net-based deep learning model applied to Sentinel-1 SAR imagery in ArcGIS Pro and the DioVISTA Flood Simulator. While the SAR-based approach excelled in achieving high accuracy with a score of 0.81, the simulation-based method demonstrated higher sensitivity, emphasizing its effectiveness in flagging potential flood zones. Third, forward-looking scenarios under Representative Concentration Pathways (RCP) 2.6 and RCP 8.5 climate trajectories were modeled to capture the potential scope of future flood impacts. The primary signal is that flooding impacts 3.2 km² of buildings and leaves 11 of 82 evacuation sites vulnerable in the worst-case scenario. Japan’s proven disaster expertise can still jolt adaptation toward greater flexibility. Adaptive frameworks utilizing real-time and predictive insights powered by remote sensing, GIS, and machine intelligence form the core of proactive decision-making. By prioritizing the repositioning of decaying suburbs as disaster prevention hubs, steadily advancing hard and soft measures to deployment, supported by the reliability of DioVISTA as a flood simulator, and fueling participatory, citizen-led ties within a community, resilience shifts from a reactive shield to a living ecosystem, aiming for zero victims. Full article