A method for target detection based on one-dimensional distance image recording and background contrast

Abstract

The invention discloses a method for detecting a target based on one-dimensional range image recording background comparison, the steps include: radar collects a one-dimensional range image sequence when there is no target, and calculates the variance; collects and processes the signal to obtain the current frame one-dimensional range image sequence; The radar executes the CFAR detection algorithm, performs angle estimation, and outputs point cloud data; calculates the variance of the one-dimensional range image sequence of the current frame, and performs correlation calculation between the one-dimensional range image sequence of the current frame and the stored one-dimensional range image sequence; Compared with the threshold, when the correlation is greater than the threshold and the variance of the one-dimensional range image sequence of the current frame is smaller than the variance of the one-dimensional range image sequence of the empty scene, and the radar does not detect point cloud data, it is determined that there is no target; otherwise, it is determined that there is Target. The invention not only removes environmental interference, but also retains effective target information, can stably detect vehicles entering at a large angle, and enhances the detection ability of other weak targets such as people; it is easy to use and has strong applicability.

Description

technical field [0001] The invention belongs to the technical field of vehicle traffic systems, in particular to a method for detecting targets based on one-dimensional range image recording background comparison. [0002] technical background [0003] With the development and progress of science and technology, the parking system is becoming more and more intelligent. In parking systems, access control management is critical. At present, the radar sensor of the barrier gate is often used to identify the vehicles entering and exiting, and cooperate with the gate machine to control the lifting rod of the barrier gate, so as to control the orderly entry and exit of vehicles. [0004] However, when the vehicle enters at a large angle, if figure 1 As shown, because the large flat metal surface on the side of the vehicle refracts most of the useful signals, the signal returned to the radar is too weak, causing the radar to fail to accurately detect the target, which is judged by...

AI Technical Summary

Problems solved by technology

The radar missed detection may cause the gate machine to control the barrier bar to drop, and in severe cases, the barrier bar will smash the car.

[0005] The existing technology usually starts from the accuracy of radar point cloud data for vehicle missed detection, so as to avoid radar missed detection, the calculation complexity is large, and the effect is not obvious

Images