Point-convolution-based human skeletal pose estimation on millimetre wave frequency modulated continuous wave multiple-input multiple-output radar

Abstract

Compared with traditional approaches that used vision sensors which can provide a high-resolution representation of targets, millimetre-wave radar is robust to scene lighting and weather conditions, and has more applications. Current methods of human skeletal pose estimation can reconstruct targets, but they lose the spatial information or don't take the density of point cloud into consideration. We propose a skeletal pose estimation method that combines point convolution to extract features from the point cloud. By extracting the local information and density of each point in the point cloud of the target, the spatial location and structure information of the target can be obtained, and the accuracy of the pose estimation is increased. The extraction of point cloud features is based on point-by-point convolution, that is, different weights are applied to different features of each point, which also increases the nonlinear expression ability of the model. Experiments show that the proposed approach is effective. We offer more distinct skeletal joints and a lower mean absolute error, average localisation errors of 6.1 cm in X, 3.5 cm in Y and 3.3 cm in Z, respectively.