Continuous-dilated temporal and inter-frame motion excitation feature learning for gait recognition

Abstract

The authors present global-interval and local-continuous feature extraction networks for gait recognition. Unlike conventional gait recognition methods focussing on the full gait cycle, the authors introduce a novel global- continuous-dilated temporal feature extraction (TFE) to extract continuous and interval motion features from the silhouette frames globally. Simultaneously, an inter-frame motion excitation (IME) module is proposed to enhance the unique motion expression of an individual, which remains unchanged regardless of clothing variations. The spatio-temporal features extracted from the TFE and IME modules are then weighted and concatenated by an adaptive aggregator network for recognition. Through the experiments over CASIA-B and mini-OUMVLP datasets, the proposed method has shown the comparable performance (as 98%, 95%, and 84.9% in the normal walking, carrying a bag or packbag, and wearing coats or jackets categories in CASIA-B, and 89% in mini-OUMVLP) to the other state-of-the-art approaches. Extensive experiments conducted on the CASIA-B and mini-OUMVLP datasets have demonstrated the comparable performance of our proposed method compared to other state-of-the-art approaches.