Search Results (6)

With the development of smart agriculture, the precise identification of fruit tree trunks by orchard management robots has become a key technology for achieving autonomous navigation. To solve the issue of tree trunks being hard to see against their background in orchards, this study introduces PCC-YOLO (PENet, CoT-Net, and Coord-SE attention-based YOLOv8), a new trunk detection model based on YOLOv8. It improves the ability to identify features in low-contrast situations by using a pyramid enhancement network (PENet), a context transformer (CoT-Net) module, and a combined coordinate and channel attention mechanism. By introducing a pyramid enhancement network (PENet) into YOLOv8, the model’s feature extraction ability under low-contrast conditions is enhanced. A context transformer module (CoT-Net) is then used to strengthen global perception capabilities, and a combination of coordinate attention (Coord-Att) and SENetV2 is employed to optimize target localization accuracy. Experimental results show that PCC-YOLO achieves a mean average precision (mAP) of 82.6% on a self-built orchard dataset (5000 images) and a detection speed of 143.36 FPS, marking a 4.8% improvement over the performance of the baseline YOLOv8 model, while maintaining a low computational load (7.8 GFLOPs). The model demonstrates a superior balance of accuracy, speed, and computational cost compared to results for the baseline YOLOv8 and other common YOLO variants, offering an efficient solution for the real-time autonomous navigation of orchard management robots. Full article

As a principal insulating component in power transmission systems, the integrity of the insulator is of paramount importance for ensuring the safe and reliable operation of transmission lines. While the deployment of aerial photography technology has markedly enhanced the efficacy of power facility inspections, the intricate backgrounds, multifarious viewpoint alterations, and erratic lighting circumstances inherent in the captured images present novel challenges for the algorithmic detection of insulator defects. To address these issues, this study proposes an enhanced version of the YOLOV7 detection algorithm. The introduction of the contextual transformer network (CoTNet) structure and an EMA attention mechanism enhances the model’s capacity to perceive global contextual information in images and to model long-distance feature dependencies. Experiments based on a real aerial photography dataset demonstrate that the proposed algorithm outperforms the benchmark model in all key performance indicators, including accuracy, recall, and F1 score, which improved by 0.6%, 1.8%, and 0.8%, respectively. Additionally, the average precision (mAP@[0.5]) and mAP@[0.5:0.95] improved by 0.6% and 4.4%, respectively. The superiority of the algorithm in feature extraction and target localization is verified through Grad-CAM visual analysis, which provides a high-precision detection method for intelligent inspection of power transmission systems. Full article

In agriculture and forestry, pest detection is critical for increasing crop yields and reducing economic losses. However, traditional deep learning models face challenges in resource-constrained environments, such as insufficient accuracy, slow inference speed, and large model sizes, which hinder their practical application. To address these issues, this study proposes an improved YOLOv7-tiny model designed to deliver efficient, accurate, and lightweight pest detection solutions. The main improvements are as follows: 1. Lightweight Network Design: The backbone network is optimized by integrating GhostNet and Dynamic Region-Aware Convolution (DRConv) to enhance computational efficiency. 2. Feature Sharing Enhancement: The introduction of a Cross-layer Feature Sharing Network (CotNet Transformer) strengthens feature fusion and extraction capabilities. 3. Activation Function Optimization: The traditional ReLU activation function is replaced with the Gaussian Error Linear Unit (GELU) to improve nonlinear expression and classification performance. Experimental results demonstrate that the improved model surpasses YOLOv7-tiny in accuracy, inference speed, and model size, achieving a MAP@0.5 of 92.8%, reducing inference time to 4.0 milliseconds, and minimizing model size to just 4.8 MB. Additionally, compared to algorithms like Faster R-CNN, SSD, and RetinaNet, the improved model delivers superior detection performance. In conclusion, the improved YOLOv7-tiny provides an efficient and practical solution for intelligent pest detection in agriculture and forestry. Full article

Computer vision technology is increasingly being widely applied in automated industrial production. However, the accuracy of workpiece detection is the bottleneck in the field of computer vision detection technology. Herein, a new object detection and classification deep learning algorithm called CSW-Yolov7 is proposed based on the improvement of the Yolov7 deep learning network. Firstly, the CotNet Transformer structure was combined to guide the learning of dynamic attention matrices and enhance visual representation capabilities. Afterwards, the parameter-free attention mechanism SimAM was introduced, effectively enhancing the detection accuracy without increasing computational complexity. Finally, using WIoUv3 as the loss function effectively mitigated many negative influences during training, thereby improving the model’s accuracy faster. The experimental results manifested that the mAP@0.5 of CSW-Yolov7 reached 93.3%, outperforming other models. Further, this study also designed a polyhedral metal workpiece detection system. A large number of experiments were conducted in this system to verify the effectiveness and robustness of the proposed algorithm. Full article

A method for counting the number of citrus fruits based on the improved YOLOv5s algorithm combined with the DeepSort tracking algorithm is proposed to address the problem of the low accuracy of counting citrus fruits due to shading and lighting factors in videos taken in orchards. In order to improve the recognition of citrus fruits, the attention module CBAM is fused with the backbone part of the YOLOv5s network, and the Contextual Transformer self-attention module is incorporated into the backbone network; meanwhile, SIoU is used as the new loss function instead of GIoU to further improve the accuracy of detection and to better keep the model in real time. Then, it is combined with the DeepSort algorithm to realize the counting of citrus fruits. The experimental results demonstrated that the average recognition accuracy of the improved YOLOv5s algorithm for citrus fruits improved by 3.51% compared with the original algorithm, and the average multi-target tracking accuracy for citrus fruits combined with the DeepSort algorithm was 90.83%, indicating that the improved algorithm has a higher recognition accuracy and counting precision in a complex environment, and has a better real-time performance, which can effectively achieve the real-time detection and tracking counting of citrus fruits. However, the improved algorithm has a reduced real-time performance and has difficulty in distinguishing whether or not the fruit is ripe. Full article

Aimed at the problems of small object detection in high resolution remote sensing images, such as difficult detection, diverse scales, and dense distribution, this study proposes a new method, DCE_YOLOX, which is more focused on small objects. The method uses depthwise separable deconvolution for upsampling, which can effectively recover lost feature information and combines dilated convolution and CoTNet to extract local contextual features, which can make full use of the hidden semantic information. At the same time, EcaNet is added to the enhanced feature extraction network of the baseline model to make the model more focused on information-rich features; secondly, the network input resolution is optimized, which can avoid the impact of image scaling to a certain extent and improve the accuracy of small object detection. Finally, CSL is used to calculate the angular loss to achieve the rotated object detection of remote sensing images. The proposed method in this study achieves 83.9% accuracy and 76.7% accuracy for horizontal object detection and rotationally invariant object detection, respectively, in the DOTA remote sensing dataset; it even achieves 96% accuracy for rotationally invariant object detection in the HRSC2016 dataset. It can be concluded that our algorithm has a better focus on small objects, while it has an equally good focus on other objects and is well suited for applications in remote sensing, and it has certain reference significance for realizing the detection of small objects in remote sensing images. Full article