A Spatio-temporal Synchronized Millimeter-Wave Radar and Visual Information Fusion Method

Abstract

The invention discloses a time-space synchronous millimeter-wave radar and visual information fusion method, which is mainly divided into three steps. The second step is to use the visual sensor to complete the running track detection of the moving train and the image position detection of the preceding same-track train based on the image processing technology. The third step is to integrate the millimeter-wave radar information and visual information based on the joint calibration method based on time-space synchronization to complete the accurate identification and positioning of the train in front of the same track. The method overcomes the problems of insufficient precision and low adaptability in the detection of a single sensor, realizes the real-time monitoring of the distance between the running train and the same-track train ahead, and improves the safety of train operation.

Description

technical field [0001] The invention relates to the field of millimeter-wave radar and visual measurement, and in particular to a method for measuring distance of orbital targets based on the fusion of millimeter-wave radar and visual information. Background technique [0002] In order to improve the safety of train operation in the rail transit operation system, it is necessary to monitor the distance between the train and the target in front of it in real time. Single sensor detection has a series of shortcomings such as insufficient precision and low adaptability. For example, the millimeter-wave radar sensor can achieve accurate output of the distance information of all the targets ahead, but because there is no more intuitive image information display, it cannot accurately identify the front targets. At the same time, because the millimeter-wave radar is highly sensitive to metals, so It is easy to be interfered by clutter, resulting in the situation that the target de...

AI Technical Summary

Problems solved by technology

Single sensor detection has a series of shortcomings such as insufficient precision and low adaptability

For example, the millimeter-wave radar sensor can accurately output the distance information of all targets ahead, but because there is no more intuitive image information display, it is impossible to accurately identify the targets ahead, and because the millimeter-wave radar is highly sensitive to metal, so It is easy to be interfered by clutter and cause the target detection position to shift and the target is not detected, which seriously affects the real-time performance and stability of target tracking; the real-time image information of the target in front can be obtained by using the camera, but for the capture of the target It is difficult to obtain the actual relative position information between the positioning and the target, so it is also difficult to meet the real-time position detection of the measured target in front

Images