Abstract
The analysis of patterns of walking is an important area of research that has numerous applications in security, healthcare, sports and human-computer interaction. Lately, walking patterns have been regarded as a unique fingerprinting method for automatic person identification at a distance. In this work, we propose a novel gait recognition architecture called Gait Pyramid Transformer (GaitPT) that leverages pose estimation skeletons to capture unique walking patterns, without relying on appearance information. GaitPT adopts a hierarchical transformer architecture that effectively extracts both spatial and temporal features of movement in an anatomically consistent manner, guided by the structure of the human skeleton. Our results show that GaitPT achieves state-of-the-art performance compared to other skeleton-based gait recognition works, in both controlled and in-the-wild scenarios. GaitPT obtains 82.6% average accuracy on CASIA-B, surpassing other works by a margin of 6%. Moreover, it obtains 52.16% Rank-1 accuracy on GREW, outperforming both skeleton-based and appearance-based approaches.
Abstract (translated)
分析走路的模式是一个重要的研究领域,它在安全、医疗、体育和人机交互等领域有着广泛的应用。最近,走路的模式被视为一种独特的指纹识别方法,用于远程自动身份验证。在本研究中,我们提出了一种称为Gait Pyramid Transformer(GaitPT)的新步态识别架构,它利用姿态估计骨骼结构来捕获独特的走路模式,而不需要依赖外观信息。GaitPT采用Hierarchical Transformer架构,以结构一致的方式有效地提取运动的空间和时间特征,受人类骨骼结构的指导。我们的结果表明,GaitPT相比其他基于骨骼的步态识别工作在控制和野生场景下取得了最先进的性能。GaitPT在CASIA-B任务中的平均准确率为82.6%,比其他工作高出6%。此外,它在GREW任务中Rank-1的准确率为52.16%,超过了基于骨骼和外观的方法。
URL
https://arxiv.org/abs/2308.10623
