Gait recognition method based on dual-branch feature fusion of Swin transformer-CNN

In the daily supervision of customs and air ports, it is necessary to identify the pathological gait of key passengers and suspected smuggling passengers. In this paper, a two-branch gait recognition framework combining global and local feature extraction is introduced. The framework includes a global extraction branch, which uses Swin transformer for feature extraction. A local extraction branch that uses 3DCNN and the CBAM module to enhance local information extraction. The experimental results show that our approach significantly improves the performance of walk recognition and achieves higher accuracy on two data sets that are widely used in most cases.