Target detection method based on one-dimensional range profile recording background contrast

Abstract

The invention discloses a target detection method based on one-dimensional range profile recording background contrast, which comprises the following steps: a radar collects a one-dimensional range profile sequence when no target exists, and calculates variance; signals are acquired and processed to obtain a one-dimensional range profile sequence of the current frame; the radar executes a CFAR detection algorithm, performs angle estimation and outputs point cloud data; the variance of the one-dimensional range profile sequence of the current frame is calculated, and correlation calculation is performed on the one-dimensional range profile sequence of the current frame and the stored one-dimensional range profile sequence; the correlation result is compared with a threshold value, and when the correlation is larger than the threshold value, the variance of the one-dimensional range profile sequence of the current frame is smaller than the variance of the one-dimensional range profile sequence of the empty scene, and the radar does not detect the point cloud data, it is judged that no target exists; otherwise, it is judged that a target exists. According to the method, environmental interference is removed, effective target information is reserved, a vehicle entering from a large angle can be stably detected, and the capability of detecting other weak targets such as people and the like is enhanced; the use is simple and the applicability is strong.

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