Abstract
Gait recognition aims at identifying individual-specific walking patterns, which is highly dependent on the observation of the different periodic movements of each body part. However, most existing methods treat each part equally and neglect the data redundancy due to the high sampling rate of gait sequences. In this work, we propose a fine-grained motion representation network (GaitFM) to improve gait recognition performance in three aspects. First, a fine-grained part sequence learning (FPSL) module is designed to explore part-independent spatio-temporal representations. Secondly, a frame-wise compression strategy, called local motion aggregation (LMA), is used to enhance motion variations. Finally, a weighted generalized mean pooling (WGeM) layer works to adaptively keep more discriminative information in the spatial downsampling. Experiments on two public datasets, CASIA-B and OUMVLP, show that our approach reaches state-of-the-art performances. On the CASIA-B dataset, our method achieves rank-1 accuracies of 98.0%, 95.7% and 87.9% for normal walking, walking with a bag and walking with a coat, respectively. On the OUMVLP dataset, our method achieved a rank-1 accuracy of 90.5%.
Abstract (translated)
URL
https://arxiv.org/abs/2209.08470
