Method and device for intelligent monitoring of rail transit line environment safety

Abstract

The present invention provides a method and device for intelligent monitoring of rail transit line environment safety, including: obtaining a large field of view image of the rail transit line environment through a camera as a matching template image; defining at least one dangerous area in the matching template image, and detecting the initial Feature points: Automatically detect the field of view feature points in the current monitoring field of view of the camera, based on the matching of the field of view feature points in the current monitoring field of view and the initial feature points in the template image, determine the mapping relationship between the current monitoring field of view of the camera and the template image, and use the mapping Relationship Map the dangerous area in the matching template image to the current monitoring field of view of the camera to generate the current monitoring dangerous area of ​​the camera; judge whether the state of the camera changes, if not, the camera uses the generated current monitoring dangerous area to detect foreign objects; if If yes, execute the above-mentioned steps of automatic identification of the bounded area.

Description

technical field [0001] The invention relates to the field of rail transit safety monitoring, in particular to an intelligent monitoring method and device for rail transit line environment safety. Background technique [0002] As the country's important infrastructure, the link between cities and the main artery of the national economy, railways play a vital role in improving transportation facilities, accelerating economic growth and improving people's living standards. Similarly, disasters in the course of railway operation cannot be ignored, otherwise it will cause heavy losses to state-owned assets and personal safety. [0003] Factors that endanger railway traffic safety mainly include natural disasters such as rain, snow, wind, floods, and earthquakes, as well as construction quality and man-made disasters such as line soft soil subsidence, line slope collapse, falling rocks and objects, and people and animals passing through, which seriously endanger Rail transport sa...

AI Technical Summary

Problems solved by technology

[0005] In the prior art, there are still many problems in the monitoring of foreign objects intruding in the track area. For example, when judging whether there is foreign object invasion by observing whether the infrared rays are blocked, the equipment is greatly affected by factors such as the environment and weather, and the practicability is not strong.

When the foreign body intrusion monitoring system based on stereo shooting is used for monitoring, due to the complexity of the algorithm, it is difficult to transplant the algorithm, and the real-time performance is not high. At the same time, the method has strict requirements on the system hardware configuration.

When binocular vision is used to detect intrusive foreign objects, the coverage of the camera is small, which is not suitable for wide application and can only be used on special road sections, and the feature matching algorithm is cumbersome, and the speed and accuracy are poor

[0006] The demand in the existing technology is that cameras are installed on many domestic lines to monitor line abnormalities, but most of these cameras require manual observation, with heavy workload and low efficiency, and serious missed reports

Although many scholars at home and abroad have researched and designed foreign object intrusion automatic alarm systems, these systems are basically based on fixed cameras, the monitoring area is fixed, and the requirements for the size of intruding foreign objects are relatively high. It is more difficult to achieve the expected application effect in complex areas

Images