GaitNet: An end-to-end network for gait based human identification. (December 2019)

• Record Type: Journal Article
• Authors: Song, Chunfeng; Huang, Yongzhen; Huang, Yan; Jia, Ning; Wang, Liang
• Is Part Of: Pattern recognition. Volume 96(2019:Dec.)
• Publication Date: 2019-12
• Subjects: Gait recognition -- Video-based human identification -- End-to-end CNN -- Joint learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2019.106988
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: We are the first to model human silhouette extraction and gait recognition in one framework in a unified end-to-end learning manner. We find that joint learning can lead to obvious performance enhancement over separate learning. We explore to add siamese loss for metric learning across the segmentation network and recognition network. We build a new outdoor gait database containing three challenging scenes. We provide extensive empirical evaluations in experiments and obtain the state-of-the-art results on three gait recognition datasets. Abstract: Gait recognition is one of the most important techniques for human identification at a distance. Most current gait recognition frameworks consist of several separate steps: silhouette segmentation, feature extraction, feature learning, and similarity measurement. These modules are mutually independent with each part fixed, resulting in a suboptimal performance in challenging conditions. In this paper, we integrate those steps into one framework, i.e., an end-to-end network for gait recognition, namedGaitNet . It is composed of two convolutional neural networks: one corresponds to gait segmentation, and the other corresponds to classification. The two networks are modeled in one joint learning procedure which can be trained jointly. This strategy greatly simplifies the traditional step-by-step manner and is thus much more efficient for practical applications. Moreover, joint learning can automatically adjust each part to fit the global optimal objective, leading to obvious performance improvement over separate learning. We evaluate our method on three large scale gait datasets, including CASIA-B, SZU RGB-D Gait and a newly built database with complex dynamic outdoor backgrounds. Extensive experimental results show that the proposed method is effective and achieves the state-of-the-art results. The code and data will be released upon request.