The safe operation of urban rail transit is of great significance to guarantee the life and wealth of the appointed people and maintain social security and stability. Due to the rapid increase in operating mileage and the continuous expansion of the scale of the network, the pressure on the safe operation of urban rail transit is increasing. In train operation failures, obstacles have a huge impact on the safety of driving. In many places, there are cases of casualties and economic losses caused by obstacles intruding into the safety clearance. Some scholars put forward the concept of automatic driving for auxiliary driving. This paper proposed an obstacle detection system based on background subtraction, including four modules: image retrieval module, rail recognition module, image alignment module and obstacle detection module. The system can achieve 92.7% accuracy and 90.1% recall with obstacle and achieve 94.8% recall without obstacle. And the system can reach rates around 8 fps, process images in real time.
Subway Obstacle Detection System Based on Machine Vision
Lect. Notes Electrical Eng.
International Conference on Intelligent Transportation Engineering ; 2021 ; Beijing, China October 29, 2021 - October 31, 2021
2021 6th International Conference on Intelligent Transportation Engineering (ICITE 2021) ; Kapitel : 98 ; 1115-1122
2022-06-01
8 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Subway Obstacle Detection System Based on Machine Vision
British Library Conference Proceedings | 2022
|Subway platform door obstacle detection and early warning system based on machine vision technology
Europäisches Patentamt | 2020
|MACHINE VISION TECHNOLOGY-BASED OBSTACLE DETECTION AND EARLY-WARNING SYSTEM FOR SUBWAY PLATFORM DOOR
Europäisches Patentamt | 2020
|NFLOW-Based Arbitrary Subway Obstacle Detection Method
IEEE | 2022
|Subway Obstacle Detection System Based on Multi-sensor Data Fusion
British Library Conference Proceedings | 2022
|