A General Framework and Key Technology for Intelligent Railway Video Recognition Platform

The development of railway integrated video monitoring system has experienced analog TV monitoring, digital video monitoring and network monitoring. But it still stays in the application of supervision and control. This paper focuses on the development of the Intelligent Railway Video Recognition(IRVR), and designs a general framework for IRVR platform. Firstly, the necessity of IRVR platform is stated form value of staff, technology and standard operation, which is based on the current situation and requirements analysis of railway video monitoring. Secondly, a general framework for IRVR platform is designed to deal with the actual problems. Thirdly, object detection algorithm flow for IRVR platform is proposed based on the analysis of key technology, especially revolve around deep learning. Finally, the experimental environment is built to verify the feasibility of the object detection algorithm for IRVR platform.