Object Detection of Rotated Bounding Boxes for Capacitors Detection Based on YOLOv5
(1.College of Electrical Engineering and Control Science, Nanjing Tech University, Nanjing 211816, China; 2.Changxing Huaqiang Electronics Co., Ltd., Huzhou 313119, China;)
Abstract
To solve the problem that classical YOLOv5 object detection algorithm can only achieve object localization with horizontal rectangular bounding boxes, this paper designs an object detection method of rotated bounding boxes for capacitors based on the YOLOv5s model. This method transforms the angle prediction problem from a regression problem to a classification problem by using circular smooth labels, and describes the loss function of angle prediction using binary cross-entropy loss. Additionally, the original training data is expanded through replication, rotation transformation, and stitching to improve the accuracy and generalization ability of the model. Experimental results on a real capacitors dataset show that the improved object detection algorithm of rotated bounding boxes for capacitors achieves an average accuracy of 83.5%. Compared with the original YOLOv5 model, the predicted object bounding boxes are more consistent with the actual rectangular contours of the capacitors.
Keywords
Object Detection; rotated bounding box; Deep Learning; capacitor
References
- [1] Dai Yuhan, Liu Chun, Zhou Peng, etc Application and research progress of energy storage technology in power systems under the dual carbon background [J]. Energy Storage Science and Technology, 2024, 13 (8): 2772-2774
- [2] Yuan Yuan, Zhao Pengju, Meng Wenjun, etc Improving the surface damage detection of conveyor belts using Faster R-CNN [J]. Mechanical Design and Manufacturing, 2025 (3): 199-203
- [3] Li Qi Research on Visual Inspection Method for Capacitor Surface Based on Deep Learning [D]. Tianjin: Tianjin University of Technology, 2022
- [4] SUN X H,GU J N,HUANG R. A Modified SSD Method for Electronic Components Fast Recognition [J].Optik,2020,205:163767.
- [5] Zeng Yao, Gao Faqin Surface defect detection algorithm for electronic components based on improved YOLOv5 [J]. Journal of Zhejiang University: Engineering Edition, 2023, 57 (3): 455-465
- [6] Huang Di Design of PTCR Defect Detection System Based on Machine Vision [D]. Wuhan: Huazhong University of Science and Technology, 2023
- [7] LU J,CHENG Y S. Research on Rapid Detection Algorithm of Electronic Components Based on Deep Learning [C]//2023 3rd International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON).Bangalore:IEEE,2023:1-4.
- [8] Che Yanbo Research on Object Detection in Visible Light Remote Sensing Images Based on Weakly Supervised Learning [D]. Harbin: Heilongjiang University, 2024
- [9] Liu Tao Research on Intelligent Sorting System for Industrial Robots Based on Machine Vision [D]. Guangzhou: South China University of Technology, 2023
- [10] GENG J,XU Z,ZHAO Z H. Rotated Object Detection of Remote Sensing Image Based on Binary Smooth Encoding and Ellipse-Like Focus Loss [J].IEEE Geoscience and Remote Sensing Letters,2022,19:1-5.
- [11] Wang Shuchen Research on Rotation Small Target Detection Algorithm Based on Aerial Images [D]. Chengdu: University of Electronic Science and Technology of China, 2024
- [12] Wang Zheng Research on Deep Learning based Aerial Image Object Detection Algorithm [D]. Huainan: Anhui University of Science and Technology, 2024
- [13] Gao Mingming, Li Yuanzhou, Ma Lei, etc YOLOv5-LR: A Remote Sensing Image Rotation Target Detection Model [J]. Infrared Technology, 2024, 46 (1): 43-51
- [14] Pei Yongtao, Zhang Mei, Su Changquan Optical Remote Sensing Image Object Detection Based on Rotating Box Representation [J]. Modern Computer, 2024, 30 (1): 34-39
- [15] Xie Xuan Research on Lightweight Remote Sensing Image Object Detection Algorithm Based on YOLOv8 [D]. Dongguan: Dongguan University of Technology, 2024
- [16] Zhou Li, Hui Fei, Zhang Jiayang, etc Remote sensing image vehicle detection based on RDB-YOLOv5 [J]. Journal of Chang'an University: Natural Science Edition, 2024, 44 (3): 149-160
- [17] Hu Kaixuan Ship Target Detection and Recognition in Satellite Images Based on CNN [D]. Dalian: Dalian University of Technology, 2022
- [18] Zhang Dabin, Wu Qin, Zhou Haojie Rotating object detection based on multi-scale perception enhancement [J]. Computer Science, 2025, 52 (6): 247-255
- [19] Wei Yaokun, Kang Yunjiang, Wang Danwei, etc Improved YOLOv5s Rotating Frame Industrial Parts Inspection Algorithm [J]. Advances in Laser and Optoelectronics, 2024, 61 (14): 155-164
Funding
National Natural Science Foundation of China (62303216); China Postdoctoral Fund (2023M731647)
About the authors
Zhang Zhihao (1994-), male, Han ethnicity, from Harbin, Heilongjiang Province, lecturer, PhD, research direction: machine vision and pattern recognition; Yang Xuejun (2002-), male, Hui ethnic, from Yangzhou, Jiangsu, is currently pursuing a master's degree in machine vision; Shen Mouquan (1980-), male, Han nationality, from Xinyang, Henan Province, professor, PhD, research direction: control theory and control engineering; Hu Jiwei (1987-), male, Han ethnicity, from Kaifeng, Henan Province, office director, bachelor's degree, research direction: electronic components; Ke Yun (1984-), female, Han nationality, from Huzhou, Zhejiang, engineer, research direction: electronic appliances; Li Chaochao (1985-), male, Han ethnicity, from Huzhou, Zhejiang, is an engineer with a research focus on electronic appliances.