Gait recognition is a promising biometrics identification technology that is widely used in criminal investigations, surveillance systems, social security, and other fields. Most existing methods of gait recognition are appearance-based methods that use silhouettes as the input of networks to acquire gait features. However, silhouettes will be lost fine-grained spatial information. In addition, the silhouette contains other information that is not related to gait, such as dress, backpack, etc., therefore, it cannot be treated as a pure “gait” recognition. At the same time, most methods do not take into account the complexity of background extraction in the context of dynamic changes. To solve the above mentioned problems, ShiftGait, a method based on skeletal features, is proposed, which extracts body posture from RGB images using 2D pose estimator and feeds the extracted skeletal sequences into graph convolutional network to acquire the features of skeletal sequences. Finally, the extracted features are used for classification. Experiments on the CASIA-B dataset indicates that our network is superior and more robust to dressing changes.
Read full abstract