[论文解读] A Comprehensive Survey on Deep Gait Recognition: Algorithms, Datasets and Challenges

Chuanfu Shen, Shiqi Yu+3 more|arXiv (Cornell University)|Jun 28, 2022

Gait Recognition and Analysis被引用 30

一句话总结

本论文提供了基于深度学习的步态识别的最新综述，提出一个二维分类法（深度表征与架构），回顾数据集，评估不同场景下的性能，并讨论隐私与安全问题。

ABSTRACT

Gait recognition aims to identify a person at a distance, serving as a promising solution for long-distance and less-cooperation pedestrian recognition. Recently, significant advancements in gait recognition have achieved inspiring success in many challenging scenarios by utilizing deep learning techniques. Against the backdrop that deep gait recognition has achieved almost perfect performance in laboratory datasets, much recent research has introduced new challenges for gait recognition, including robust deep representation modeling, in-the-wild gait recognition, and even recognition from new visual sensors such as infrared and depth cameras. Meanwhile, the increasing performance of gait recognition might also reveal concerns about biometrics security and privacy prevention for society. We provide a comprehensive survey on recent literature using deep learning and a discussion on the privacy and security of gait biometrics. This survey reviews the existing deep gait recognition methods through a novel view based on our proposed taxonomy. The proposed taxonomy differs from the conventional taxonomy of categorizing available gait recognition methods into the model- or appearance-based methods, while our taxonomic hierarchy considers deep gait recognition from two perspectives: deep representation learning and deep network architectures, illustrating the current approaches from both micro and macro levels. We also include up-to-date reviews of datasets and performance evaluations on diverse scenarios. Finally, we introduce privacy and security concerns on gait biometrics and discuss outstanding challenges and potential directions for future research.

研究动机与目标

• 从二维分类法（深度表征学习与神经网络架构）总结深度步态识别的进展。
• 回顾数据集并评估跨视角、野外、衣物变化和三维空间场景的基准进展。
• 讨论生物特征安全与隐私含义并概述尚待解决的挑战与未来方向。

提出的方法

• 提出一个针对深度表征学习和深度网络架构的新的二维分类法用于深度步态识别。
• 从微观（特征学习）和宏观（架构）角度对现有深度步态方法进行调查与分类。
• 提供四种场景：跨视角、野外、衣物变化和三维空间中的步态数据集和性能评估的最新综述。
• 讨论步态生物识别中的隐私和安全问题，并提出未来研究方向。

实验结果

研究问题

• RQ1 用于步态识别的当前深度表征学习技术有哪些？
• RQ2 神经网络架构（判别型与生成型）如何影响步态识别性能？
• RQ3 关键数据集有哪些，方法在跨视角、野外、衣物变化和三维空间场景中的表现如何？
• RQ4 哪些隐私和安全问题威胁步态生物识别，以及未来方向如何应对？

主要发现

• 该综述提供了关于深度步态识别方法、数据集和基准的最新目录。
• 提出了一种新分类法，通过深度表征学习和神经架构分析深度步态方法，提供超越传统基于模型或外观分类的宏观/微观视角。
• 在各场景的性能汇总中指出，深度模型在如 CASIA-B（在外观变化设置中的高准确率）和 GREW（户外大规模试验的 rank-1 超过 70%）等数据集上表现出强劲。
• 论文讨论了生物识别安全与隐私问题，强调步态生物识别中的挑战与未来潜在方向。