Search Results (5,171)

Driver fatigue is a primary factor in traffic accidents and poses a serious threat to road safety. To address this issue, this paper proposes a multi-feature fusion fatigue detection method based on an improved YOLOv8 model. First, the method uses an enhanced YOLOv8 model to achieve high-precision face detection. Then, it crops the detected face regions. Next, the lightweight PFLD (Practical Facial Landmark Detector) model performs keypoint detection on the cropped images, extracting 68 facial feature points and calculating key indicators related to fatigue status. These indicators include the eye aspect ratio (EAR), eyelid closure percentage (PERCLOS), mouth aspect ratio (MAR), and head posture ratio (HPR). To mitigate the impact of individual differences on detection accuracy, the paper introduces a novel sliding window model that combines a dynamic threshold adjustment strategy with an exponential weighted moving average (EWMA) algorithm. Based on this framework, blink frequency (BF), yawn frequency (YF), and nod frequency (NF) are calculated to extract time-series behavioral features related to fatigue. Finally, the driver’s fatigue state is determined using a comprehensive fatigue assessment algorithm. Experimental results on the WIDER FACE and YAWDD datasets demonstrate this method’s significant advantages in improving detection accuracy and computational efficiency. By striking a better balance between real-time performance and accuracy, the proposed method shows promise for real-world driving applications. Full article

Low-light image enhancement in architectural scenes presents a considerable challenge for computer vision applications in construction engineering. Images captured in architectural settings during nighttime or under inadequate illumination often suffer from noise interference, low-light blurring, and obscured structural features. Although low-light image enhancement and deblurring are intrinsically linked when emphasizing architectural defects, conventional image restoration methods generally treat these tasks as separate entities. This paper introduces an efficient and robust Frequency-Space Recovery Network (FSRNet), specifically designed for low-light image enhancement in architectural contexts, tailored to the unique characteristics of such scenes. The encoder utilizes a Feature Refinement Feedforward Network (FRFN) to achieve precise enhancement of defect features while dynamically mitigating background redundancy. Coupled with a Frequency Response Module, it modifies the amplitude spectrum to amplify high-frequency components of defects and ensure balanced global illumination. The decoder utilizes InceptionDWConv2d modules to capture multi-directional and multi-scale features of cracks. When combined with a gating mechanism, it dynamically suppresses noise, restores the spatial continuity of defects, and eliminates blurring. This method also reduces computational costs in terms of parameters and MAC operations. To assess the effectiveness of the proposed approach in architectural contexts, this paper conducts a comprehensive study using low-light defect images from indoor concrete walls as a representative case. Experimental results indicate that FSRNet not only achieves state-of-the-art PSNR performance of 27.58 dB but also enhances the mAP of the downstream YOLOv8 detection model by 7.1%, while utilizing only 3.75 M parameters and 8.8 GMACs. These findings fully validate the superiority and practicality of the proposed method for low-light image enhancement tasks in architectural settings. Full article

Automated blood cell detection is of significant importance in the efficient and accurate diagnosis of hematological diseases. The application of this technology has advanced clinical practice in hematology and improved the speed and accuracy of diagnosis, thereby providing patients with more timely medical intervention. In this study, the YOLOv11n model was optimized by integrating gradient accumulation and loss reweighting techniques to improve its detection performance for blood cells in clinical images. The optimized YOLOv11n model shows an improvement in performance. The mAP50 reached 0.9356, the mAP50-95 was 0.6620, and the precision and recall were better than those of existing methods. The model can effectively address issues such as dense cell distribution, cell overlap, and image artifacts. Therefore, it is highly applicable in real-time clinical applications. The results of the ablation experiment demonstrate that there is a synergistic effect between gradient accumulation and loss reweighting, which can improve detection accuracy without increasing the computational burden. The conclusion indicates that the optimized YOLOv11n model has important application prospects as an automated blood cell detection tool and has the potential to integrate with clinical workflows. Full article

Ship instance segmentation in remote sensing images is essential for maritime applications such as intelligent surveillance and port management. However, this task remains challenging due to dense target distributions, large variations in ship scales and shapes, and limited high-quality datasets. The existing YOLOv8 framework mainly relies on convolutional neural networks and CIoU loss, which are less effective in modeling global–local interactions and producing accurate mask boundaries. To address these issues, we propose CDSANet, a novel one-stage ship instance segmentation network. CDSANet integrates convolutional operations, Vision Transformers, and attention mechanisms within a unified architecture. The backbone adopts a Convolutional Vision Transformer Attention (CVTA) module to enhance both local feature extraction and global context perception. The neck employs dynamic-weighted DOWConv to adaptively handle multi-scale ship instances, while SIoU loss improves localization accuracy and orientation robustness. Additionally, CBAM enhances the network’s focus on salient regions, and a MixUp-based augmentation strategy is used to improve model generalization. Extensive experiments on the proposed VLRSSD dataset demonstrate that CDSANet achieves state-of-the-art performance with a mask AP (50–95) of 75.9%, surpassing the YOLOv8 baseline by 1.8%. Full article

Background/Objectives: This study investigated the use of artificial intelligence (AI) to identify and match barefoot prints belonging to the same individual on soft and sandy soil substrates. Recognizing footprints on soil is challenging due to low contrast and variability in impressions. Methods: We introduce Deep Learning Footprint Identification Technology (DeepFIT), based on a modified You Only Look Once (YOLOv11s) algorithm, using three methods, namely, Bounding Box (BBox), 16 anatomical landmarks, and automatically segmented outlines (Auto-Seg). An Extra Small Detection Head (XSDH) was added to improve feature extraction at smaller scales and enhance generalization through multi-scale supervision, reducing overfitting to specific spatial patterns. Results: Forty adults (20 males, 20 females) participated, with 600 images per individual. As the number of individuals in model training increased, the BBox model’s accuracy declined, resulting in misclassification on the test set. The average performance accuracy across both substrates was 77% for BBox, 90% for segmented outlines, and 96% for anatomical landmarks. Conclusions: The landmark method was the most reliable for identifying and matching barefoot prints on both soft and sandy soils. This approach can assist forensic practitioners in linking suspects to crime scenes and reconstructing events from footprint evidence, providing a valuable tool for forensic investigations. Full article

With the rapid development of autonomous vehicles and intelligent transportation systems, vehicle detection and distance estimation have become critical technologies for ensuring driving safety. However, real-world in-vehicle environments impose strict constraints on computational resources, making it impractical to deploy high-end GPUs. This implies that even highly accurate algorithms, if unable to run in real time on embedded platforms, cannot fully meet practical application demands. Although existing deep learning-based detection and stereo vision methods achieve state-of-the-art accuracy on public datasets, they often rely heavily on massive computational power and large-scale annotated data. Their high computational requirements and limited cross-scenario generalization capabilities restrict their feasibility in real-time vehicle-mounted applications. On the other hand, traditional algorithms such as Semi-Global Block Matching (SGBM) are advantageous in terms of computational efficiency and cross-scenario adaptability, but when used alone, their accuracy and robustness remain insufficient for safety-critical applications. Therefore, the motivation of this study is to develop a stereo vision-based collision warning system that achieves robustness, real-time performance, and computational efficiency. Our method is specifically designed for resource-constrained in-vehicle platforms, integrating a lightweight YOLOv8n detector with SGBM-based depth estimation. This approach enables real-time performance under limited resources, providing a more practical solution compared to conventional deep learning models and offering strong potential for real-world engineering applications. Full article

This study presents the OGS-YOLOv8 model for coffee bean maturity identification, designed to enhance accuracy in identifying coffee beans at different maturity stages in complicated contexts, utilizing an upgraded version of YOLOv8. Initially, the ODConv (full-dimensional dynamic convolution) substitutes the convolutional layers in the backbone and neck networks to augment the network’s capacity to capture attributes of coffee bean images. Second, we replace the C2f layer in the neck networks with the CSGSPC (Convolutional Split Group-Shuffle Partial Convolution) module to reduce the computational load of the model. Lastly, to improve bounding box regression accuracy by concentrating on challenging samples, we substitute the Inner-FocalerIoU function for the CIoU loss function. According to experimental results, OGS-YOLO v8 outperforms the original model by 7.4%, achieving a detection accuracy of 73.7% for coffee bean maturity. Reaching 76% at mAP@0.5, it represents a 3.2% increase over the initial model. Furthermore, GFLOPs dropped 26.8%, from 8.2 to 6.0. For applications like coffee bean maturity monitoring and intelligent harvesting, OGS-YOLOv8 offers strong technical support and reference by striking a good balance between high detection accuracy and low computational cost. Full article

In Mediterranean semi-arid regions, rainfed olive groves are increasingly being abandoned due to drought, low profitability, and rural depopulation. The long-term impact of abandonment on soil conditions is debated, as it may promote vegetation recovery or lead to degradation. In contrast, some farmers are adopting low-disturbance management practices that allow spontaneous vegetation to establish. These contrasting scenarios offer valuable opportunities for comparison. This study aims to develop a framework to assess the impact of different management regimes on soil health and to investigate (1) the impact of spontaneous vegetation cover (SVC) and tillage regimes on soil organic carbon (SOC), and (2) the long-term ecological dynamics of abandoned groves, through a combination of field surveys, remote sensing, and object detection. SOC was assessed using both ground-based and remote sensing-derived indicators. Vegetation cover was quantified via a grid point intercept method. Field data were integrated with a land-use monitoring framework that includes abandonment assessment through historical orthophotos and a deep learning model (YOLOv12) to detect active and abandoned olive groves. Results show that abandoned zones are richer in SOC than active ones. In particular, the active groves with SVC exhibit a mean SOC of 1%, which is higher than that of tilled groves, where SOC is 0.45%, with no apparent moisture loss. Abandoned groves can be reliably identified from aerial imagery, achieving a recall of 0.833 for abandoned patches. Our results demonstrate the potential of YOLOv12 as an innovative and accessible tool for detecting zones undergoing ecological regeneration or degradation. The study underscores the ecological and agronomic potential of spontaneous vegetation in olive agroecosystems. Full article

Strawberry picking relies primarily on manual labor, making it the most labor-intensive stage in strawberry cultivation. Harvesting robots have become essential for strawberry production, and fruit ripeness detection models are critical for picking operations. This study collected strawberry ripeness photographs under various natural environments and enhanced feature expression through diverse image enhancement techniques. Considering practical deployment on harvesting robots, the low-parameter, high-accuracy YOLOv8s was selected as the base model. Leveraging the ease of integration of the Global Attention Mechanism (GAM) within the YOLO model, we incorporated GAM before the SPFF module to enhance the extraction capabilities of both global and local features. Experimental results demonstrate that the improved YOLOv8s achieves excellent performance, with a mAP of 91.5% for three maturity classes and a frame rate of 53 FPS. Compared with other mainstream models, the improved YOLOv8s presented in this paper demonstrates superior detection performance, achieving mAP improvements of 12.1%, 8.0%, 6.1%, 4.6%, and 3.1% over YOLOv3, YOLOv5s, YOLOv7s, YOLOv8s, and CBAM-YOLOv8s, respectively. It also exhibits robust detection capabilities under varying lighting conditions and occlusions, meeting the demands for high precision and rapid performance during harvesting operations. Full article

This study aims to improve the accuracy and efficiency of apple defect detection under complex lighting conditions. A novel approach is proposed that integrates filtered imaging with color space reconstruction, utilizing YOLOv12 as the detection framework. “Red Fuji” apples were selected, and an imaging platform featuring adjustable illumination and RGB filters was established. Following pre-experimental optimization of imaging conditions, a dataset comprising 1600 images was constructed. Conversions to RGB, HSI, and LAB color spaces were performed, and YOLOv12 served as the baseline model for ablation experiments. Detection performance was assessed using Precision, Recall, mAP, and FPS metrics. Results indicate that the green filter under 4500 K illumination combined with RGB color space conversion yields optimal performance, achieving an mAP50–95 of 83.1% and a processing speed of 15.15 FPS. This study highlights the impact of filter–color space combinations on detection outcomes, offering an effective solution for apple defect identification and serving as a reference for industrial inspection applications. Full article

Machine harvesting of cotton in Xinjiang has significantly improved harvesting efficiency; however, it has also resulted in a considerable increase in residual mulch content within the cotton, which has severely affected the quality and market value of cotton textiles. Existing mulch detection algorithms based on machine vision generally suffer from complex parameterization and insufficient real-time performance. To overcome these limitations, this study proposes a novel mulch detection algorithm, Mulch-YOLO, developed on the YOLOv11 framework. Specifically, an improved CBAM (Convolutional Block Attention Module) is incorporated into the BiFPN (Bidirectional Feature Pyramid Network) to achieve more effective fusion of multi-scale mulch features. To enhance the semantic representation of mulch features, a modified Content-Aware ReAssembly of Features module, CARAFE-Mulch (Content-Aware ReAssembly of Features), is designed to reorganize feature maps, resulting in stronger feature expressiveness compared with the original representations. Furthermore, the MobileOne module is optimized by integrating the DECA Dilated Efficient Channel Attention (Dilated Efficient Channel Attention) module, thereby reducing both the parameter count and computational load while improving detection efficiency in real time. To verify the effectiveness of the proposed approach, experiments were conducted on a real-world dataset containing 20,134 images of low-visual-saliency plastic mulch. The results indicate that Mulch-YOLO achieves a lightweight architecture and high detection accuracy. Compared with YOLOv11n, the proposed method improves mAP@0.5 by 4.7% and mAP@0.5:0.95 by 3.3%, with a 24% reduction in model parameters. Full article

Welding is a critical joining process in modern manufacturing, with defects contributing to 50–80% of structural failures. Traditional inspection methods are often inefficient, subjective, and inconsistent. To address challenges in weld defect detection—including scale variation, morphological complexity, low contrast, and sample imbalance—this paper proposes ADFE-DET, an adaptive dynamic feature enhancement algorithm. The approach introduces three core innovations: the Dynamic Selection Cross-stage Cascade Feature Block (DSCFBlock) captures fine texture features via edge-preserving dynamic selection attention; the Adaptive Hierarchical Spatial Feature Pyramid Network (AHSFPN) achieves adaptive multi-scale feature integration through directional channel attention and hierarchical fusion; and the Multi-Directional Differential Lightweight Head (MDDLH) enables precise defect localization via multi-directional differential convolution while maintaining a lightweight architecture. Experiments on three public datasets (Weld-DET, NEU-DET, PKU-Market-PCB) show that ADFE-DET improves mAP50 by 2.16%, 2.73%, and 1.81%, respectively, over baseline YOLOv11n, while reducing parameters by 34.1%, computational complexity by 4.6%, and achieving 105 FPS inference speed. The results demonstrate that ADFE-DET provides an effective and practical solution for intelligent industrial weld quality inspection. Full article

To address the challenges of variable target scale, complex background, blurred image, and serious occlusion in the yield detection of Yunnan large-leaf tea tree, this study proposes a deep learning network DE-YOLOv13-S that integrates the visual mechanism of primates. DynamicConv was used to optimize the dynamic adjustment process of the effective receptive field and channel the gain of the primate visual system. Efficient Mixed-pooling Channel Attention was introduced to simulate the observation strategy of ‘global gain control and selective integration parallel’ of the primate visual system. Scale-based Dynamic Loss was used to simulate the foveation mechanism of primates, which significantly improved the positioning accuracy and robustness of Yunnan large-leaf tea tree yield detection. The results show that the Box Loss, Cls Loss, and DFL Loss of the DE-YOLOv13-S network decreased by 18.75%, 3.70%, and 2.54% on the training set, and by 18.48%, 14.29%, and 7.46% on the test set, respectively. Compared with YOLOv13, its parameters and gradients are only increased by 2.06 M, while the computational complexity is reduced by 0.2 G FLOPs, precision, recall, and mAP are increased by 3.78%, 2.04% and 3.35%, respectively. The improved DE-YOLOv13-S network not only provides an efficient and stable yield detection solution for the intelligent management level and high-quality development of tea gardens, but also provides a solid technical support for the deep integration of bionic vision and agricultural remote sensing. Full article

Simultaneous Localization and Mapping (SLAM) utilizes sensor data to concurrently construct environmental maps and estimate its own position, finding wide application in scenarios like robotic navigation and augmented reality. SLAM systems based on 3D Gaussian Splatting (3DGS) have garnered significant attention due to their real-time, high-fidelity rendering capabilities. However, in real-world environments containing dynamic objects, existing 3DGS-SLAM methods often suffer from mapping errors and tracking drift due to dynamic interference. To address this challenge, this paper proposes BDGS-SLAM—a Bayesian Dynamic Gaussian Splatting SLAM framework specifically designed for dynamic environments. During the tracking phase, the system integrates semantic detection results from YOLOv5 to build a dynamic prior probability model based on Bayesian filtering, enabling accurate identification of dynamic Gaussians. In the mapping phase, a multi-view probabilistic update mechanism is employed, which aggregates historical observation information from co-visible keyframes. By introducing an exponential decay factor to dynamically adjust weights, this mechanism effectively restores static Gaussians that were mistakenly culled. Furthermore, an adaptive dynamic Gaussian optimization strategy is proposed. This strategy applies penalizing constraints to suppress the negative impact of dynamic Gaussians on rendering while avoiding the erroneous removal of static Gaussians and ensuring the integrity of critical scene information. Experimental results demonstrate that, compared to baseline methods, BDGS-SLAM achieves comparable tracking accuracy while generating fewer artifacts in rendered results and realizing higher-fidelity scene reconstruction. Full article

Apron incidents remain a critical safety concern in aviation, yet progress in vision-based surveillance has been limited by the lack of open-source datasets with detailed aircraft component annotations and systematic benchmarks. This study addresses these limitations through three contributions. First, a novel hybrid dataset was developed, integrating real and synthetic imagery with pixel-level labels for aircraft, fuselage, wings, tail, and nose. This publicly available resource fills a longstanding gap, reducing reliance on proprietary datasets. Second, the dataset was used to benchmark twelve advanced object detection and segmentation models, including You Only Look Once (YOLO) variants, two-stage detectors, and Transformer-based approaches, evaluated using mean Average Precision (mAP), Precision, Recall, and inference speed (FPS). Results revealed that YOLOv9 delivered the highest bounding box accuracy, whereas YOLOv8-Seg outperformed in segmentation, surpassing some of its newer successors and showing that architectural advancements do not always equate to superiority. Third, YOLOv8-Seg was systematically optimised through an eight-step ablation study, integrating optimisation strategies across loss design, computational efficiency, and data processing. The optimised model achieved an 8.04-point improvement in mAP@0.5:0.95 compared to the baseline and demonstrated enhanced robustness under challenging conditions. Overall, these contributions provide a reliable foundation for future vision-based apron monitoring and collision risk prevention systems. Full article