Detection method of obstacles in the dangerous area of electric locomotive driving based on MSE-YOLOv4-Tiny. (1st November 2022)

• Record Type: Journal Article
• Authors: Wang, Wenshan; Wang, Shuang; Guo, Yongcun; Zhao, Yanqiu; Tong, Jiale; Yang, Tun
• Is Part Of: Measurement science & technology. Volume 33:Number 11(2022)
• Publication Date: 2022-11-01
• Subjects: computer vision -- YOLOv4-Tiny algorithm -- detection scale -- attention mechanism -- Spatial Pyramid Pooling; Physical measurements -- Periodicals; Scientific apparatus and instruments -- Periodicals; Equipment and Supplies -- Periodicals; Science -- instrumentation -- Periodicals; Technology -- instrumentation -- Periodicals; Mesures physiques -- Périodiques; Physical measurements; Scientific apparatus and instruments; Periodicals; 502.87
• DOI: 10.1088/1361-6501/ac82db
• Languages: English
• ISSNs: 0957-0233

Abstract

Abstract: Aiming at the problems of error warning, low detection efficiency and inability to meet the requirements of lightweight deployment in current track obstacle detection algorithms based on computer vision, a detection method of obstacles in the dangerous area of electric locomotive driving based on improved YOLOv4-Tiny (MSE-YOLOv4-Tiny) was proposed. An obstacle image dataset was constructed to provide a testing environment for various target detection algorithms. The method of perspective transformation, sliding window and least square cubic polynomial was used to fit the track line. By finding the area where the track was located and extending a certain distance to the outside of the track, the dangerous area of the electric locomotive running was obtained. A three-scale detection structure was formed by increasing the shallow detection scale in the detection layer, so as to improve the detection accuracy of the network for smaller targets, such as stones. An improved SKNet (ECA_SKNet) attention mechanism module was added to the output ends of the three scales of the backbone network, and the weight was reassigned to realize feature reconstruction, thus further improving the detection accuracy of the target. By adding the Spatial Pyramid Pooling module, the local and global features of the image were fused to improve the accuracy of localization and detection accuracy of the network. A comparative experiment was carried out on the dataset constructed in this paper. The experimental results show that the problem of false warnings caused by taking the target in the safe area as an obstacle can be effectively solved by dividing the danger area of electric locomotive driving. Compared with the original YOLOv4-Tiny algorithm, the MSE-YOLOv4-Tiny algorithm has a 3.80% increase in mean average precision while maintaining a higher detection speed and a smaller model memory. It has better detection performance and can be used for autonomous driving electric locomotive obstacle detection to provide technical support.