Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China.
Sensors (Basel). 2023 Oct 22;23(20):8627. doi: 10.3390/s23208627.
Gait recognition aims to identify a person based on his unique walking pattern. Compared with silhouettes and skeletons, skinned multi-person linear (SMPL) models can simultaneously provide human pose and shape information and are robust to viewpoint and clothing variances. However, previous approaches have only considered SMPL parameters as a whole and are yet to explore their potential for gait recognition thoroughly. To address this problem, we concentrate on SMPL representations and propose a novel SMPL-based method named GaitSG for gait recognition, which takes SMPL parameters in the graph structure as input. Specifically, we represent the SMPL model as graph nodes and employ graph convolution techniques to effectively model the human model topology and generate discriminative gait features. Further, we utilize prior knowledge of the human body and elaborately design a novel part graph pooling block, PGPB, to encode viewpoint information explicitly. The PGPB also alleviates the physical distance-unaware limitation of the graph structure. Comprehensive experiments on public gait recognition datasets, Gait3D and CASIA-B, demonstrate that GaitSG can achieve better performance and faster convergence than existing model-based approaches. Specifically, compared with the baseline SMPLGait (3D only), our model achieves approximately twice the Rank-1 accuracy and requires three times fewer training iterations on Gait3D.
步态识别旨在根据人的独特行走模式来识别身份。与轮廓和骨骼相比，带皮肤的多人线性 (SMPL) 模型可以同时提供人体姿势和形状信息，并且对视角和服装变化具有很强的鲁棒性。然而，以前的方法仅将 SMPL 参数作为整体考虑，尚未彻底探索其在步态识别中的潜力。为了解决这个问题，我们专注于 SMPL 表示，并提出了一种名为 GaitSG 的新的基于 SMPL 的方法，用于步态识别，该方法将图结构中的 SMPL 参数作为输入。具体来说，我们将 SMPL 模型表示为图节点，并采用图卷积技术来有效地对人体模型拓扑进行建模，并生成具有区分性的步态特征。此外，我们利用人体的先验知识，精心设计了一种新颖的部分图池化块（PGPB），以显式地编码视角信息。PGPB 还减轻了图结构对物理距离不敏感的限制。在公共步态识别数据集 Gait3D 和 CASIA-B 上进行的综合实验表明，GaitSG 可以实现比现有基于模型的方法更好的性能和更快的收敛速度。具体来说，与基线 SMPLGait（仅 3D）相比，我们的模型在 Gait3D 上的 Rank-1 准确率提高了近两倍，并且所需的训练迭代次数减少了三倍。
