Vision-Based obstacle detection in dangerous region of coal mine driverless rail electric locomotives

• Published in: Measurement : journal of the International Measurement Confederation 2025-01, Vol.239, p.115514, Article 115514
• Main Authors: Yang, Tun, Guo, Yongcun, Li, Deyong, Wang, Shuang
• Format: Article
• Language: English
• Subjects: Dangerous region; Driverless rail electric locomotive; Regional obstacle detection; Underground coal mine
• ISSN: 0263-2241
• DOI: 10.1016/j.measurement.2024.115514

•Deep learning-based obstacle detection of driverless electric locomotives in underground coal mine.•An obstacle detection model called YOLO-Region was proposed.•The dangerous region was defined based on pixel coordinate points.•The model realized accurate regional obstacle detection in real time. In order to solve the problem of inaccurate obstacle detection as well as frequent start-stops caused by oversensitive obstacle detection in existing driverless rail electric locomotives in underground coal mines, the YOLO-Region model is proposed to realize regional obstacle detection. First, the model backbone uses InceptionNeXt block and the developed New Spatial Pyramid Pooling (NSPP) module; the model neck extends the FPN+PAN architecture; the model head uses improved task-specific context decoupling (Impro-TSCODE) head. In addition, repulsion loss is introduced to improve the detection ability of partially occluded targets. The experimental results show that the YOLO-Region achieves competitive detection performance with mAP of 98.0 % and an average detection speed of 94.5 FPS. Second, a vision-based method for defining dangerous region based on pixel coordinate points is developed and integrated into YOLO-Region, which allows the model to detect obstacles only within a specific region, thereby reducing frequent start-stops of driverless electric locomotives.