Junjie Hu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Junjie Hu has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Jian-Hong Zhu
School of Electrical Engineering and Automation, Nantong University, Nantong 226019, China
1 shared publication - Juping Gu
Suzhou University of Science and Technology
1 shared publication - Ling Jiang
School of Information Science and Technology, Nantong University, Nantong 226019, China
1 shared publication - Lurui Fang
School of Advanced Technology, Xian Jiaotong-Liverpool University (XJTLU), Suzhou, Jiangsu, China
1 shared publication - Xinsong Zhang
School of Electrical Engineering and Automation, Nantong University, Nantong 226019, China
1 shared publication - Yiming Xu
School of Electrical Engineering and Automation, Nantong University, Nantong 226019, China
1 shared publication
Latest Publications
- Open Access
Research on Object Detection of Overhead Transmission Lines Based on Optimized YOLOv5s
Object detection of overhead transmission lines is a solution for promoting inspection efficiency for power companies. However, aerial images contain many complex backgrounds and small objects, and traditional algorithms are incompetent in the identification of details of power transmission lines accurately. To address this problem, this paper develops an object detection method based on optimized You Only Look Once v5-small (YOLOv5s). This method is designed to be engineering-friendly, with the objective of maximal detection accuracy and computation simplicity. Firstly, to improve the detecting accuracy of small objects, a larger scale detection layer and jump connections are added to the network. Secondly, a self-attention mechanism is adopted to merge the feature relationships between spatial and channel dimensions, which could suppress the interference of complex backgrounds and boost the salience of objects. In addition, a small object enhanced Complete Intersection over Union (CIoU) is put forward as the loss function of the bounding box regression. This loss function could increase the derived loss for small objects automatically, thereby improving the detection of small objects. Furthermore, based on the scaling factors of batch-normalization layers, a pruning method is adopted to reduce the parameters and achieve a lightweight method. Finally, case studies are fulfilled by comparing the proposed method with classic YOLOv5s, which demonstrate that the detection accuracy is increased by 4%, the model size is reduced by 58%, and the detection speed is raised by 3.3%.
Open AccessResearch on Object Detection of Overhead Transmission Lines Based on Optimized YOLOv5s
Object detection of overhead transmission lines is a solution for promoting inspection efficiency for power companies. However, aerial images contain many complex backgrounds and small objects, and traditional algorithms are incompetent in the identification of details of power transmission lines accurately. To address this problem, this paper develops an object detection method based on optimized You Only Look Once v5-small (YOLOv5s). This method is designed to be engineering-friendly, with the objective of maximal detection accuracy and computation simplicity. Firstly, to improve the detecting accuracy of small objects, a larger scale detection layer and jump connections are added to the network. Secondly, a self-attention mechanism is adopted to merge the feature relationships between spatial and channel dimensions, which could suppress the interference of complex backgrounds and boost the salience of objects. In addition, a small object enhanced Complete Intersection over Union (CIoU) is put forward as the loss function of the bounding box regression. This loss function could increase the derived loss for small objects automatically, thereby improving the detection of small objects. Furthermore, based on the scaling factors of batch-normalization layers, a pruning method is adopted to reduce the parameters and achieve a lightweight method. Finally, case studies are fulfilled by comparing the proposed method with classic YOLOv5s, which demonstrate that the detection accuracy is increased by 4%, the model size is reduced by 58%, and the detection speed is raised by 3.3%.