Obstacle extraction method based on camera data of train AEB system

Abstract

The invention discloses an obstacle extraction method based on camera data of a train AEB system. The obstacle extraction method comprises the following steps: S1, acquiring an RGB color image in realtime; s2, performing graying, denoising and enhancement processing on the RGB color image; s3, carrying out image track positioning and obstacle crossing detection; s4, carrying out the primary detection of a central obstacle; s5, establishing a detection window; s6, carrying out secondary detection on the middle obstacle; and S7, calibrating the actual distance of the obstacle. An image sequenceon a track in front of a train advancing route is obtained through a monocular camera mounted in front of the train. A simple search algorithm and image morphology processing are used for positioninga rail and detecting a cross-over obstacle. A Canny edge operator extraction mode is used to carry out initial detection on an obstacle arranged in an orbit. A detection window is established, a graylevel co-occurrence matrix method is adopted to carry out secondary detection on a centrally-arranged obstacle, and finally, an IPM model is utilized to calibrate the distance between a train and theobstacle, so that data extraction of the obstacle is realized, and finally, automatic emergency braking of the train is realized.

Description

technical field [0001] The invention belongs to the technical field of train operation safety assurance systems, and in particular relates to an obstacle extraction method based on camera data of a train AEB system. Background technique [0002] Railway transportation is the main mode of transportation in my country. With the significant increase in the volume of railway passenger and cargo transportation, the number of trains receiving and departing from stations and the amount of shunting operations have also increased, which puts forward higher-level requirements for the safety and reliability of trains. . Different from the visibility of the braking range of traditional road vehicles, the average speed of trains in my country is as high as 200km / h, and the maximum speed can reach 480km / h. High-speed driving puts forward high requirements for emergency braking of sudden track intrusions. It is difficult to find obstacles ahead in time only relying on the traditional drive...

AI Technical Summary

Problems solved by technology

This solution is only suitable for short-distance obstacle detection when the train is running at low speed, and cannot play a prominent role in the long-distance obstacle recognition and emergency braking of the train.

Images