Abstract
Gait recognition is emerging as a promising and innovative area within the field of computer vision, widely applied to remote person identification. Although existing gait recognition methods have achieved substantial success in controlled laboratory datasets, their performance often declines significantly when transitioning to wild this http URL argue that the performance gap can be primarily attributed to the spatio-temporal distribution inconsistencies present in wild datasets, where subjects appear at varying angles, positions, and distances across the frames. To achieve accurate gait recognition in the wild, we propose a skeleton-guided silhouette alignment strategy, which uses prior knowledge of the skeletons to perform affine transformations on the corresponding this http URL the best of our knowledge, this is the first study to explore the impact of data alignment on gait recognition. We conducted extensive experiments across multiple datasets and network architectures, and the results demonstrate the significant advantages of our proposed alignment this http URL, on the challenging Gait3D dataset, our method achieved an average performance improvement of 7.9% across all evaluated networks. Furthermore, our method achieves substantial improvements on cross-domain datasets, with accuracy improvements of up to 24.0%.
Abstract (translated)
步态识别作为计算机视觉领域中的一个有前景且创新的方向，被广泛应用于远程身份验证。尽管现有的步态识别方法在控制良好的实验室数据集中取得了显著的成功，但当这些算法迁移到实际环境时，它们的性能通常会大幅下降。我们认为这种表现差距主要是由于野外数据集中的空间-时间分布不一致所导致的问题，在这些环境中，人物以不同的角度、位置和距离出现在不同帧中。 为了在真实场景中实现准确的步态识别，我们提出了一种基于骨骼指导轮廓对齐策略的方法，这种方法利用骨架先验知识来执行仿射变换以调整对应图像。据我们所知，这是第一个探索数据对准影响步态识别的研究项目。我们在多个数据集和网络架构上进行了广泛的实验，并且结果展示了我们的对准方法具有显著的优势。 在极具挑战性的Gait3D数据集中，我们提出的方法实现了所有评估的网络性能平均提高了7.9%。此外，在跨域数据集上，我们的方法也获得了高达24.0%准确率提升的重大改进。
URL
https://arxiv.org/abs/2503.18830
