Real-time vehicle identification and tracking during agricultural master-slave follow-up operation using improved YOLO v4 and binocular positioning

• Published in: Proceedings of the Institution of Mechanical Engineers. Part C, Journal of mechanical engineering science Journal of mechanical engineering science, 2023-03, Vol.237 (6), p.1393-1404
• Main Authors: Wang, Liang, Li, Lingmin, Wang, Hao, Zhu, Shaohua, Zhai, Zhiqiang, Zhu, Zhongxiang
• Format: Article
• Language: English
• Subjects: Agricultural equipment; Agricultural vehicles; Algorithms; Binocular vision; Object recognition; Real time; Straight lines; Target detection; Tracking; Vehicle identification
• ISSN: 0954-4062; 2041-2983
• DOI: 10.1177/09544062221130928

The identification and positioning of a master is essential for the master-slave cooperative operation of agricultural machinery. This study aimed to develop an agricultural vehicle dynamic identification and tracking method for agricultural master-slave follow-up operation using improved YOLO v4 and binocular positioning. The regular pruning algorithm was used to trim the original YOLO v4 channel to achieve a fast and accurate identification of master vehicle. The principle of binocular vision positioning was used to calculate the position of the master. The method (IYO-BPO) proposed in this study fused target detection and binocular vision positioning together, which was used to identify and track the master vehicle in real time. To evaluate the performance of the developed method, RTK-GPS and a gyroscope were installed on the master vehicle to obtain the reference position and heading angle. Identification and tracking experiments of both the linear and S-shaped movement of the master were conducted. The RMS errors were 0.067 m, 0.203 m, and 2.602° in terms of the longitudinal, lateral, and heading angle deviation, respectively, when the master moved along a straight line. The results show that the master vehicle could be identified and tracked by the IYO-BPO correctly and effectively.