Stpointgcn: Spatial Temporal Graph Convolutional Network for Multiple People Recognition Using Millimeter-Wave Radar
Chunyu Wang, Peixian Gong, Lihua Zhang
Abstract
Gait recognition is a new biometric technology, which aims to identify people by their walking posture. Compared with fingerprint recognition, face recognition and other technologies, gait recognition usually has the characteristics of long-distance non-contact and difficulty in camouflage. And compared with the camera-based method, using millimeter-wave radar for gait recognition is immune to light and weather conditions. Moreover, due to the non-invasive feature of millimeter-wave radar, we can design products without privacy risk. In this paper, we propose an end-to-end STPoint-GCN structure, which can extract and aggregate the features of sparse point clouds collected by millimeter-wave radar from the dimensions of space and time. In order to verify our method, we collect and disclose our own gait recognition dataset based on millimeter-wave radar. After comparing with the existing mainstream algorithms, we find that our method is superior to the existing mainstream methods for single-person scenarios and multi-person co-existing scenarios.