Person counting and tracking method based on millimeter wave radar

Abstract

The invention discloses a person counting and tracking method based on a millimeter wave radar. The process of processing each frame of data of the millimeter wave radar comprises the following steps of: (S1) processing an echo signal of a current frame, and obtaining a target point cloud matrix of the current frame; (S2) carrying out clustering analysis on the target point cloud matrix to obtain target object clusters corresponding to each target object; and (S3) enabling the state types of the target object clusters to comprise suspicious, determined, static and leaving states, determining the ID and the state of each target object cluster in the current frame on the basis of the data of the previous frame, and calculating the number of newly added target objects converted from the suspicious state to the determined state and the number of leaving target objects converted from the determined state to the leaving state. According to the method, the suspicious state and the static state of the target and the credibility concept are added, the problem that the target disappears after being static is solved, meanwhile, false detection is reduced, and the detection reliability is improved.

Description

technical field [0001] The invention relates to the field of design sensors, in particular to a method for counting and tracking people based on millimeter wave radar. Background technique [0002] With the development of science and technology, the demand for intelligent detection and personnel safety protection in factories and cities is also increasing. An important part of the realization of smart factories and smart cities is the detection of personnel and the statistics of the number of people. [0003] Millimeter-wave radar can penetrate rain, snow, and fog, and can detect stably both indoors and outdoors, and the millimeter-wave band is highly sensitive to small movements of people, which is an effective means for personnel detection and people counting. [0004] Current people counting methods include: passive infrared detectors (PIR), optical cameras, lidar, etc. Passive infrared detectors detect by sensing the difference in temperature between moving objects and...

AI Technical Summary

Problems solved by technology

[0006] (1) Passive infrared detectors are greatly affected by light and temperature outdoors, which are prone to false detections, and have a small range and low sensitivity for motion detection

[0007] (2) The camera will be affected by factors such as shadows, occlusions, light, and the environment. The algorithm requirements are complex and may cause privacy issues.

[0008] (3) The range of lidar will be attenuated under strong outdoor light, and the software algorithm is complex and the amount of calculation is large

[0009] (4) When the millimeter-wave radar detects the target, when the target is still, it cannot be detected, and the personnel count is wrong

And usually a density-based clustering algorithm is used, which requires a large amount of calculation

Noise interference is also easy to cause false detection

Images