A model-based gait recognition method with body pose and human prior knowledge

Liao，Rijun1,3; Yu，Shiqi2,3; An，Weizhi1,3; Huang，Yongzhen4,5

2020-02-01

10.1016/j.patcog.2019.107069

PATTERN RECOGNITION   影响因子和分区

0031-3203

1873-5142

We propose in this paper a novel model-based gait recognition method, PoseGait. Gait recognition is a challenging and attractive task in biometrics. Early approaches to gait recognition were mainly appearance-based. The appearance-based features are usually extracted from human body silhouettes, which are easy to compute and have shown to be efficient for recognition tasks. Nevertheless silhouettes shape is not invariant to changes in clothing, and can be subject to drastic variations, due to illumination changes or other external factors. An alternative to silhouette-based features are model-based features. However, they are very challenging to acquire especially for low image resolution. In contrast to previous approaches, our model PoseGait exploits human 3D pose estimated from images by Convolutional Neural Network as the input feature for gait recognition. The 3D pose, defined by the 3D coordinates of joints of the human body, is invariant to view changes and other external factors of variation. We design spatio-temporal features from the 3D pose to improve the recognition rate. Our method is evaluated on two large datasets, CASIA B and CASIA E. The experimental results show that the proposed method can achieve state-of-the-art performance and is robust to view and clothing variations.

Gait recognition Human body pose Spatio-temporal feature

SCI ; EI

英语

ESI高被引

通讯

Science Foundation of Shenzhen[20170504160426188]

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic

WOS:000497600300005

ELSEVIER SCI LTD

20194007493197

Gait analysis ; Hosiery manufacture ; Image resolution ; Large dataset ; Neural networks

Biomechanics, Bionics and Biomimetics:461.3 ; Textile Products and Processing:819.5

ENGINEERING

2-s2.0-85072769994

Scopus

1.College of Computer Science and Software EngineeringShenzhen University,China
2.Department of Computer Science and EngineeringSouthern University of Science and Technology,China
3.Shenzhen Institute of Artificial Intelligence and Robotics for Society,Shenzhen,China
4.National Laboratory of Pattern RecognitionInstitute of AutomationChinese Academy of Sciences,China
5.Watrix technology limited co. ltd,China

Liao，Rijun,Yu，Shiqi,An，Weizhi,et al. A model-based gait recognition method with body pose and human prior knowledge[J]. PATTERN RECOGNITION,2020,98.

Liao，Rijun,Yu，Shiqi,An，Weizhi,&Huang，Yongzhen.(2020).A model-based gait recognition method with body pose and human prior knowledge.PATTERN RECOGNITION,98.

Liao，Rijun,et al."A model-based gait recognition method with body pose and human prior knowledge".PATTERN RECOGNITION 98(2020).