Research on Visual Detection of Intruding Foreign Objects in Rail Transit

DOI: https://doi.org/10.62517/jcte.202406413

Author(s)

Hu Bo, Liu Peiwen

Affiliation(s)

College of Automation, Guangxi University of Science and Technology, Liuzhou, Guangxi, China

Abstract

Foreign object intrusion detection is one of the important means to ensure the safe operation of rail transit. The distance measurement of the intruding foreign object is conducive to reminding the train crew to take corresponding measures in time. This paper proposes a distance detection algorithm for intruding foreign objects based on monocular vision. Firstly, corner detection and threshold segmentation methods are used to obtain the image coordinates of a black-and-white checkerboard. Secondly, regression analysis is employed to establish a conversion model between image coordinates and world coordinates. Finally, an object detection algorithm based on the YOLOv10 network is used for image recognition to obtain the coordinates of the intruding foreign objects in the image coordinate system. The distance information of the intruding objects is detected. Experimental validation shows that the distance of the intruding objects has an error range of -5 to +6 cm in the X-axis direction and -9 to +16 cm in the Y-axis direction, demonstrating high accuracy.

Keywords

Coordinate Transformation; Distance Measurement; Regression Analysis; Threshold Segmentation

References

[1] Wang Tianyu, Peng Zaiyun, Liang Xiuhui, et al. Design of automatic monitoring System for Urban Rail Transit based on multi-eye Machine vision [J]. Automation and Instrumentation. 2023, 38(12):1-5. [2] Wang Hui, Jiang Zhufeng, Wu Yujie, et al. Rapid Detection of foreign body penetration in Railway based on Deep Learning [J]. Journal of Railway Science and Engineering. 2024, 21(5):2086-2098. [3] Li Zhengzhong, Liu Shuang, PeiHuiran, et al. Research on Prevention and control measures of safety risks in protected areas of urban rail transit lines [J]. Modern Urban Rail Transit. 2024(3):113-117. [4] Xu Shixiong, Yuan Zhenhuan, Cao Qiuting, et al. Design and implementation of CMOS single-line laser ranging system based on MCU [J]. Modern Information Technology, 2024, 8(21):1-5+10. [5] Liu Xin, Yang Haima, Zhang Liang, et al. Main echo overlap and coping method of single-photon laser ranging system [J]. Applied Laser, 2024, 44(08):82-92. [6] Ju Meiyu, Xu Junior College, Xu Huan. A method of radar range estimation based on relative entropy [J]. Data Acquisition and Processing, 2024, 39(06):1326-1332. [7] He Junyao, Wang Wensheng, Han Yihang. Design of floating garbage detection and positioning system based on YOLOv8 and binocular ranging algorithm [J]. Modern Electronic Technology, 2024, 47 (20): 1-7. [8] Liu Zhen, Dong Shaojiang, Luo Jiayuan, et al. Fire detection and ranging method based on binocular vision and improved YOLOv8n [J]. Journal of Shaanxi University of Science and Technology, 2025, 43(01):152-160. [9] Weizhu Zhu, Zurong Cui, Lei Chen, et al. Robust monocular vision-based monitoring system for multi-target displacement measurement of bridges under complex backgrounds, Mechanical Systems and Signal Processing, 2025, 225:112242. [10] Ao Wang, Hui Chen, Lihao Liu , et al. YOLOv10: Real-Time End-to-End Object Detection[J]. 2024.