Explore the vast range of titles available.

In order to efficiently identify early tea diseases, an improved YOLOv8 lesion detection method is proposed to address the challenges posed by the complex background of tea diseases, difficulty in detecting small lesions, and low recognition rate of similar phenotypic symptoms. This method focuses on detecting tea leaf blight, tea white spot, tea sooty leaf disease, and tea ring spot as the research objects. This paper presents an enhancement to the YOLOv8 network framework by introducing the Receptive Field Concentration-Based Attention Module (RFCBAM) into the backbone network to replace C2f, thereby improving feature extraction capabilities. Additionally, a mixed pooling module (Mixed Pooling SPPF, MixSPPF) is proposed to enhance information blending between features at different levels. In the neck network, the RepGFPN module replaces the C2f module to further enhance feature extraction. The Dynamic Head module is embedded in the detection head part, applying multiple attention mechanisms to improve multi-scale spatial location and multi-task perception capabilities. The inner-IoU loss function is used to replace the original CIoU, improving learning ability for small lesion samples. Furthermore, the AKConv block replaces the traditional convolution Conv block to allow for the arbitrary sampling of targets of various sizes, reducing model parameters and enhancing disease detection. the experimental results using a self-built dataset demonstrate that the enhanced YOLOv8-RMDA exhibits superior detection capabilities in detecting small target disease areas, achieving an average accuracy of 93.04% in identifying early tea lesions. When compared to Faster R-CNN, MobileNetV2, and SSD, the average precision rates of YOLOv5, YOLOv7, and YOLOv8 have shown improvements of 20.41%, 17.92%, 12.18%, 12.18%, 10.85%, 7.32%, and 5.97%, respectively. Additionally, the recall rate (R) has increased by 15.25% compared to the lowest-performing Faster R-CNN model and by 8.15% compared to the top-performing YOLOv8 model. With an FPS of 132, YOLOv8-RMDA meets the requirements for real-time detection, enabling the swift and accurate identification of early tea diseases. This advancement presents a valuable approach for enhancing the ecological tea industry in Yunnan, ensuring its healthy development.

With the development of deep fusion intelligent control technology and the application of low-carbon energy, the number of renewable energy sources connected to the distribution grid has been increasing year by year, gradually replacing traditional distribution grids with active distribution grids. In addition, as an important component of the distribution grid, substations have a complex internal environment and numerous devices. The problems of untimely defect detection and slow response during intelligent inspections are particularly prominent, posing risks and challenges to the safe and stable operation of active distribution grids. To address these issues, this paper proposes a high-performance and lightweight substation defect detection model called YOLO-Substation-large (YOLO-SS-large) based on YOLOv5m. The model improves lightweight performance based upon the FasterNet network structure and obtains the F-YOLOv5m model. Furthermore, in order to enhance the detection performance of the model for small object defects in substations, the normalized Wasserstein distance (NWD) and complete intersection over union (CIoU) loss functions are weighted and fused to design a novel loss function called NWD-CIoU. Lastly, based on the improved model mentioned above, the dynamic head module is introduced to unify the scale-aware, spatial-aware, and task-aware attention of the object detection heads of the model. Compared to the YOLOv5m model, the YOLO-SS-Large model achieves an average precision improvement of 0.3%, FPS enhancement of 43.5%, and parameter reduction of 41.0%. This improved model demonstrates significantly enhanced comprehensive performance, better meeting the requirements of the speed and precision for substation defect detection, and plays an important role in promoting the informatization and intelligent construction of active distribution grids.

While previous studies have greatly improved our knowledge on the motion capability of the cervical spine, few reported on the kinematics of the entire head-neck complex (C0-T1) during dynamic activities of the head in the upright posture. This study investigated in vivo kinematics of the entire head-neck complex (C0-T1) of eight female asymptomatic subjects during dynamic left–right head axial rotation using a dual fluoroscopic imaging system and 3D-to-2D registration techniques. During one-sided head rotation (i.e., left or right head rotation), the primary rotation of the overall head-neck complex (C0-T1) reached 55.5 ± 10.8°, the upper cervical spine region (C0-2) had a primary axial rotation of 39.7 ± 9.6° (71.3 ± 8.5% of the overall C0-T1 axial rotation), and the lower cervical spine region (C2-T1) had a primary rotation of 10.0 ± 3.7° (18.6 ± 7.2% of the overall C0-T1 axial rotation). Coupled bending rotations occurred in the upper and lower cervical spine regions in similar magnitude but opposite directions (upper: contralateral bending of 18.2 ± 5.9° versus lower: ipsilateral bending of 21.4 ± 5.1°), resulting in a compensatory cervical lateral curvature that balances the head to rotate horizontally. Furthermore, upper cervical segments (C0-1 or C1-2) provided main mobility in different rotational degrees of freedom needed for head axial rotations. Additionally, we quantitatively described both coupled segmental motions (flexion–extension and lateral bending) by correlation with the overall primary axial rotation of the head-neck complex. This investigation offers comprehensive baseline data regarding primary and coupled motions of craniocervical segments during head axial rotation.

Gas extraction is an important measure for coal mine gas disaster control. Its effect is closely correlated to the drilling depth. The existing methods usually determine the drilling depth by manually counting the number of drill pipes, and the number of drill pipes can be automatically counted by object detection and real-time tracking algorithms. An improved object detection model was proposed for the problem of the poor performance of the object detection algorithm due to such interference factors as bright light, low illuminance and heavy dust and mist in coal mines. In terms of data augmentation, the ACE dehazing algorithm is introduced to improve image quality. In order to solve the problem of leak detection caused by the irregular shape that appears due to the interference of bright light, the deformable convolution DCNv2 module was integrated in the C2f module to make the sampling points of the convolution kernel diffuse irregularly, so as to fully extract the shape features of the drill pipe and then improve the detection rate of the model. For the problem of too low confidence of the model in detecting drill pipes due to uneven illumination, the attention paid by the model to the features of the drill pipe could be improved by embedding the SimAM non-parametric attention mechanism module in the backbone network, which can further improve the confidence of the drill pipe. For the problem of low average category detection accuracy caused by the changeable environment of the underground drilling site, the dynamic head was used to improve the ability of the model to extract the features of the drill pipe in scale, space, and channel, and improve the average category detection accuracy of the drill pipe. To address the issue of diverse angle differences between predicted and real boxes, CIoU loss function is replaced with the SIoU loss function. Finally, the improved detection algorithm was verified with the homemade drill pipe dataset. The experimental results showed that: the improved model effectively alleviated the problem of partial leak detection of the original network for scenes such as heavy dust and mist and uneven illumination; the recall rate increased by 4.9%; the mean average precision was improved by 5.3%. At the same time, it maintains a high real-time performance (the FPS is 117), providing the basis of the drill pipe detection model for the application of real-time tracking of the number of drill pipes.

We propose a lightweight Multi-Head Self-Attention (MHSA) mechanism for plant phenotypic feature extraction, which integrates cross-species transfer learning with dynamic head pruning to improve efficiency without compromising accuracy. The primary challenge stems from minimizing redundant computations without compromising the model’s capacity to generalize over varied plant species, an issue intensified by the substantial dimensionality of attention mechanisms in Vision Transformers. Our solution, the Transferable Attention Head Alignment (TAHA) framework, operates in three stages: pre-training on a source species, cross-species alignment via a Domain Alignment Loss (DAL), and head pruning based on a transferability score. The framework selects and keeps solely the attention heads with the highest transferability, thus diminishing model intricacy without compromising the ability to distinguish phenotypic traits. Furthermore, the pruned MHSA module is smoothly combined with standard Transformer backbones, which makes efficient deployment on edge devices possible. Experiments were conducted on real edge hardware (Raspberry Pi 4, NVIDIA Jetson Nano) and GPU platforms, showing our approach attains accuracy similar to full-head models yet cuts computational expenses by as much as 40% (14.1 ms inference latency on Raspberry Pi 4, 519 M parameters). The method holds special importance for scalable plant phenotyping, in situations where computational capacity is frequently constrained yet generalization across species is essential. Moreover, the repeated alignment and pruning procedure permits gradual adjustment to novel species without complete retraining, which increases feasibility for agricultural applications in practical settings. Supplementary experiments on phylogenetically distant species (Arabidopsis → pine) demonstrate the framework’s generalization limits, with a 7.2% F1-score drop compared to close-species transfer (Arabidopsis → maize), highlighting the need for trait-specific head adaptation in distant transfers. The proposed method improves lightweight feature extraction by merging transfer learning and attention head optimization, achieving a balanced compromise between performance and efficiency.

To address the need for automated sorting of synthetic diamonds based on quality in manufacturing enterprises, this study developed a dedicated dataset and an enhanced YOLOv8n model for synthetic diamonds detection and quality evaluation, named YOLOv8n-adamas. We redesigned the backbone network to improve feature extraction capabilities and introduced a dynamic detection head based on attention mechanisms to further enhance model performance. Experimental results show that on synthetic diamonds dataset, YOLOv8n-adamas achieved a 4.0% improvement in precision (P), a 2.7% increase in recall (R), and improvements of 1.5% and 1.3% in mean average precisions at 50% and 95% Intersection over Union (IoU) thresholds (mAP50 and mAP95) compared to YOLOv8. Furthermore, YOLOv8n-adamas also outperforms other commonly used, high-performing models in various metrics on this dataset, offering effective technical support for the automated quality-based sorting of synthetic diamonds.

Objective: Pedestrian detection is very important for the environment perception and safety action of intelligent robots and autonomous driving, and is the key to ensuring the safe action of intelligent robots and auto assisted driving. Methods: In response to the characteristics of pedestrian objects occupying a small image area, diverse poses, complex scenes and severe occlusion, this paper proposes an improved pedestrian object detection method based on the YOLOv7 model, which adopts the Convolutional Block Attention Module (CBAM) attention mechanism and Deformable ConvNets v2 (DCNv2) in the two Efficient Layer Aggregation Network (ELAN) modules of the backbone feature extraction network. In addition, the detection head is replaced with a Dynamic Head (DyHead) detector head with an attention mechanism; unnecessary background information around the pedestrian object is also effectively excluded, making the model learn more concentrated feature representations. Results: Compared with the original model, the log-average miss rate of the improved YOLOv7 model is significantly reduced in both the Citypersons dataset and the INRIA dataset. Conclusions: The improved YOLOv7 model proposed in this paper achieved good performance improvement in different pedestrian detection problems. The research in this paper has important reference significance for pedestrian detection in complex scenes such as small, occluded and overlapping objects.

To addresse the problem of poor detection accuracy or even false detection of wildlife caused by rainy environment at night. In this paper, a wildlife target detection algorithm based on improved YOLOX-s network is proposed. Our algorithm comprises the MobileViT-Pooling module, the Dynamic Head module, and the Focal-IoU module.First, the MobileViT-Pooling module is introduced.It is based on the MobileViT attention mechanism, which uses a spatial pooling operator with no parameters as a token mixer module to reduce the number of network parameters. This module performs feature extraction on three feature layers of the backbone network output respectively, senses the global information and strengthens the weight of the effective information. Second, the Dynamic Head module is used on the downstream task of network detection, which fuses the information of scale sensing, spatial sensing, and task sensing and improves the representation ability of the target detection head. Lastly, the Focal idea is utilized to improve the IoU loss function, which balances the learning of high and low quality IoU for the network. Experimental results reveal that our algorithm achieves a notable performance boost with mAP@0.5 reaching 87.8% (an improvement of 7.9%) and mAP@0.5:0.95 reaching 62.0% (an improvement of 5.3%). This advancement significantly augments the night-time wildlife detection accuracy under rainy conditions, concurrently diminishing false detections in such challenging environments.

In dense scenes, pedestrians often exhibit a variety of symmetrical features, such as symmetry in body contour, posture, clothing, and appearance. However, pedestrian detection poses challenges due to the mutual occlusion of pedestrians and the small scale of distant pedestrians in the image. To address these challenges, we propose a pedestrian detection algorithm tailored for dense scenarios called YOLO-RAD. In this algorithm, we integrate the concept of receiving field attention (RFA) into the Conv and C2f modules to enhance the feature extraction capability of the network. A self-designed four-layer adaptive spatial feature fusion (ASFF) module is introduced, and shallow pedestrian feature information is added to enhance the multi-scale feature fusion capability. Finally, we introduce a small-target dynamic head structure (DyHead-S) to enhance the capability of detecting small-scale pedestrians. Experimental results on WiderPerson and CrowdHuman, two challenging dense pedestrian datasets, show that compared with YOLOv8n, our YOLO-RAD algorithm has achieved significant improvement in detection performance, and the detection performance of mAP@0.5 has increased by 2.5% and 6%, respectively. The detection performance of mAP@0.5:0.95 was improved by 2.7% and 6.8%, respectively. Therefore, the algorithm can effectively improve the performance of pedestrian detection in dense scenes.

This study focuses on an equivalent model of Polyvinyl Butyral (PVB) laminated glass to simulate the Head Injury Criterion (HIC) when a pedestrian collides with a TRAM. To simulate the collision behavior that occurs when a pedestrian’s head collides with PVB laminated glass, a comparison was made between the results of the widely used PLC model for PVB laminated glass modeling and an actual dynamic head impact test. The material properties of the tempered glass and PVB film used in the PLC and equivalent models were obtained via four-point bending tests and tensile tests, respectively. The proposed equivalent model is developed by assigning the thickness, material properties, and positional information of each layer in the multilayer PLC model to the integration points of the shell element. The results of the equivalent analysis model were found to accurately simulate the collision behavior when compared with the results of both the dynamic head impact test and the PLC model. Moreover, the analysis cost improved to approximately 15% of that of the traditional PLC model.