Title: Urban traffic vehicle trajectory tracking control method based on binocular vision

Authors: Zhiting Liu

Addresses: School of Automotive Engineering, Hunan Communication Polytechnic, Changsha, 410132, China

Abstract: To improve the effectiveness of vehicle trajectory tracking control and reduce tracking false alarms, this paper proposes a binocular vision based urban traffic vehicle trajectory tracking control method. Firstly, use binocular stereo vision technology to obtain image information from different perspectives and obtain depth information of traffic vehicle trajectory images; secondly, calculate the similarity of vehicle trajectory tracking targets based on motion characteristics and obtain the similarity distance of target matching; then, the relaxation factor term is introduced to construct the control objective function, and the control increment is obtained based on the constraint conditions; finally, solve the incremental sequence of control variables to complete the tracking control of the desired trajectory. The results show that the tracking false detection rate under the proposed method does not exceed 0.22%, and the control time is within 12 seconds, demonstrating good universality and applicability.

Keywords: forward distribution addition; dynamic grid generation algorithm; XGBoost; data mining.

DOI: 10.1504/IJMIC.2024.144029

International Journal of Modelling, Identification and Control, 2024 Vol.45 No.4, pp.211 - 217

Received: 19 Feb 2024
Accepted: 05 Jun 2024
Published online: 21 Jan 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article