People-Aware mmWave Point Cloud Processing Algorithm

People-aware is a way of perceiving a person's iden-tity through their biometrics. Currently, it plays a very important role in identity verification in application scenarios such as smart homes and security checks. Compared to traditional person identification technologies, mm Wave based person sensing has the unique advantages of being non-contact, not affected by the environment, and highly private and confidential. The current direct output of person point cloud results from TI packaged sensors suffers from small quantities and unclear target contours, limiting various point cloud data recognition applications such as gait recognition, status recognition, etc. In this paper, we collect mm Wave datasets of people walking and propose an Optimise-CFAR target detection optimisation algorithm based on the signal processing process, which can effectively remove the number of edge noise points and thus improve the quality of the point cloud output, and process the point cloud data of people into time series with the help of a person identification model. After experimental analysis, we found that the optimised point cloud data was able to improve the average accuracy of person classification by 93%.