高速铁路线路环境异物入侵视频检测系统研制

Development of Video Detection System for Line Environment under 450 km/h Conditions

摘要:

针对智能高铁2.0体系中智能装备建设要求，研制了高速铁路线路环境视频检测系统。该系统采用高实时、双模态补偿技术进行动态成像，克服了高速运行条件下的运动模糊及开放式场景下的环境光干扰问题。基于Faster-RCNN（Faster Region-based Convolutional Neural Networks）和YOLO v8模型开发了异物入侵智能识别算法，实现了基于高速动车组平台的列车运行环境状态异常在线检测。研发了线路环境视频动态检测应用软件，实现了列车运行环境异常的动态实时监测和异常数据管理。试验验证表明，系统可满足最高450km/h运行条件下的线路环境高清成像和异物入侵检测，缺陷检出率≥90%。

Abstract:

Aiming at the requirements of intelligent equipment construction in the intelligent high-speed railway 2.0 system, a high-speed railway line environment video detection system was developed. The system uses high real-time and dual-mode compensation technology for dynamic imaging, which overcomes the problem of motion blur under high-speed operation conditions and ambient light interference in open scenes. An intelligent recognition algorithm for foreign object intrusion is developed based on the Faster-RCNN framework and YOLO v8, and the online detection of abnormal state of train operation environment based on high-speed electric multiple units platform is realized. The application software of video dynamic detection of line environment is developed, which realizes the dynamic real-time monitoring and abnormal data management of abnormal train operation environment. The experimental verification shows that the system can meet the high-definition imaging and foreign object intrusion detection of the line environment under the operating conditions of up to 450 km / h, and the accuracy of defect detection is ≥ 90 %.