GaitSet: Regarding Gait as a Set for Cross-View Gait Recognition

By Hanqing Chao, Yiwei He, Junping Zhang, Jianfeng Feng. AAAI Conference on Artificial Intelligence, 2018

679 citations recorded by the source corpus.

As a unique biometric feature that can be recognized at a distance, gait has broad applications in crime prevention, forensic identification and social security. To portray a gait, existing gait recognition methods utilize either a gait template, where temporal information is hard to preserve, or a gait sequence, which must keep unnecessary sequential constraints and thus loses the flexibility of gait recognition. In this paper we present a novel perspective, where a gait is regarded as a set consisting of independent frames. We propose a new network named GaitSet to learn identity information from the set. Based on the set perspective, our method is immune to permutation of frames, and can naturally integrate frames from different videos which have been filmed under different scenarios, such as diverse viewing angles, different clothes/carrying conditions. Experiments show that under normal walking conditions, our single-model method achieves an average rank-1 accuracy of 95.0% on the CASIA-B gait dataset and an 87.1% accuracy on the OU-MVLP gait dataset. These results represent new state-of-the-art recognition accuracy. On various complex scenarios, our model exhibits a significant level of robustness. It achieves accuracies of 87.2% and 70.4% on CASIA-B under bag-carrying and coat-wearing walking conditions, respectively. These outperform the existing best methods by a large margin. The method presented can also achieve a satisfactory accuracy with a small number of frames in a test sample, e.g., 82.5% on CASIA-B with only 7 frames. The source code has been released at https://github.com/AbnerHqC/GaitSet.

Subfields: Biomedical Engineering, Endocrinology, Diabetes and Metabolism

View Paper: https://www.semanticscholar.org/paper/e5cf53498bcc848e6909c3255afd6082754415ba

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

Citations in the corpus

A model-based gait recognition method with body pose and human prior knowledge (2020, background): “In addition, Chao et al. [10] regard gait as a set consisting of independent silhouettes rather than a continuous silhou-ettes (Wu et al. [9] ).”
GaitPart: Temporal Part-Based Model for Gait Recognition (2020, methodology): “And GaitSet[5] assumed that the appearance of a silhouette has contained its position information and thus regarded gait as a set to extract temporal information.”
Gait Recognition via Effective Global-Local Feature Representation and Local Temporal Aggregation (2020, methodology): “Therefore, some researchers first extract gait features at the frame-level gait image instead of GEI and then conduct operations to generate gait templates [3, 27, 5].”
iLGaCo: Incremental Learning of Gait Covariate Factors (2020, methodology): “Existing gait methods fall into two typical categories: model-based methods [23, 24] and appearance-based methods [3, 6, 21, 26, 42].”
Gaitgraph: Graph Convolutional Network for Skeleton-Based Gait Recognition (2021, methodology): “While most approaches [1,2,5] use the whole shape as input, recent methods [3] focus on specific body parts.”