Fine-Grained Spatial–Temporal Gait Recognition Network Based on Millimeter-Wave Radar Point Cloud

Radar-based gait recognition has gained wide attention recently for its ability to preserve privacy and adapt to low-light and poor weather scenarios. Among different forms of input data, radar point cloud is an appealing option as it captures not only the appearance signatures, but also motion signatures of the subject. For gait recognition, both appearance and motion are crucial signatures which can be represented by spatial features and temporal features respectively. However, the spatial-temporal features extracted by existing radar point cloud based methods are coarse-grained, leading to poor performance in realistic application. To enhance the spatial-temporal feature representation ability of radar point cloud based method, in this paper, we design a novel network to extract fine-grained spatial-temporal gait features from millimeter-wave (mmWave) radar point cloud. For fine-grained spatial feature extraction, we apply a dual-stream feature extraction (DSFE) module to finely exploit the 3D coordinates, intensity and velocity information within radar point cloud. After that, since each body part has its unique characteristics in gait task, we also propose a probability guided body-part partition (PGBP) module to split radar point cloud into fine-grained spatial body parts. For fine-grained temporal feature extraction, a local-global temporal feature extraction (LGTE) module is used to further capture the temporal patterns of each body part. To evaluate the effectiveness of proposed methods, we conduct extensive experiments with 90 subjects in various realistic settings, i.e., cross-view and cross-wearing-condition. The results demonstrate that our model achieves significant improvement over existing radar-based gait recognition methods.