Static and dynamic features analysis from human skeletons for gait recognition

Li，Ziqiong1; Yu，Shiqi2; Reyes，Edel B.Garcia3; Shan，Caifeng4,5; Li，Yan Ran5

10.1109/IJCB52358.2021.9484378

2021-08-04

2474-9680

978-1-6654-3781-3

2021 IEEE International Joint Conference on Biometrics, IJCB 2021

1-7

4-7 Aug. 2021

Shenzhen, China

Gait recognition is an effective way to identify a person due to its non-contact and long-distance acquisition. In addition, the length of human limbs and the motion pattern of human from human skeletons have been proved to be effective features for gait recognition. However, the length of human limbs and motion pattern are calculated through human prior knowledge, more important or detailed information may be missing. Our method proposes to obtain the dynamic information and static information from human skeletons through disentanglement learning. In the experiments, it has been shown that the features extracted by our method are effective.

Conferences Dynamics Feature extraction Skeleton Gait recognition

其他

英语

EI

20213410818348

Biometrics ; Gait analysis ; Time and motion study

Bioengineering and Biology:461

2-s2.0-85113299761

Scopus

1.Shenzhen University,College of Computer Science and Software Engineering,China
2.Southern University of Science and Technology,Department of Computer Science and Engineering,China
3.Shenzhen Institute of Artificial Intelligence and Robotics for Society,China
4.Shandong University of Science and Technology,Qingdao,China
5.Artificial Intelligence Research,CAS (CAS-AIR),Beijing,China

Li，Ziqiong,Yu，Shiqi,Reyes，Edel B.Garcia,et al. Static and dynamic features analysis from human skeletons for gait recognition[C],2021:1-7.