High-speed rail overhead line system foreign matter detection system and method based on FPGA and horizon segmentation

Abstract

The invention discloses a high-speed rail overhead line system foreign matter detection system and method based on FPGA and horizon segmentation. The system comprises a video acquisition module, an image storage module, a horizon segmentation module and a target detection module. The video acquisition module is used for acquiring a high-speed railway overhead line system monitoring video in real time along with a vehicle; the horizon segmentation module realizes rapid adaptive horizon segmentation by using an improved maximum between-cluster variance method and an intelligent iterative algorithm, and inputs the part above the horizon as a detection area into the target detection module; and the target detection module detects possible foreign matters in the picture transmitted by the horizon segmentation module by using a target detection neural network. The modules run on a vehicle-mounted FPGA terminal to achieve accelerated calculation. According to the invention, foreign matters onthe contact network can be rapidly and accurately detected, the actual requirements of railway departments are met, and the operation safety of high-speed railways can be effectively guaranteed.

Description

technical field [0001] The invention relates to the field of detection of foreign matter hanging on the catenary of high-speed railways, and specifically relates to image processing methods such as FPGA accelerated operation and deep learning. Background technique [0002] The catenary of the high-speed railway is a device for supplying power to electric locomotives. If foreign objects (commonly such as plastic bags, kites and other light objects) are attached, it will affect the power supply to the train, thus threatening the normal operation of the high-speed railway. At present, my country mainly collects and stores catenary video images along the railway through on-board cameras such as EMU driver control information analysis systems, but because it does not have the function of detecting and identifying foreign objects, it is necessary for inspectors to manually observe video image data Check whether foreign matter is attached to the catenary. This detection method is ti...

AI Technical Summary

Problems solved by technology

[0005] In order to overcome the time-consuming and labor-intensive deficiency of manual observation and surveillance video inspection of foreign objects, the present invention proposes a high-speed rail catenary foreign object detection system and method based on FPGA and horizon segmentation

Images