TY - GEN
T1 - Gait Recognition using Identity-Aware Adversarial Data Augmentation
AU - Yoshino, Koki
AU - Nakashima, Kazuto
AU - Ahn, Jeongho
AU - Iwashita, Yumi
AU - Kurazume, Ryo
N1 - Funding Information:
*This work was partially supported by JSPS KAKENHI Grant Number JP20H00230 1Koki Yoshino and Jeongho Ahn are with Graduate School of Information Science and Electrical Engineering, Kyushu University, Japan. {yoshino, ahn}@irvs.ait.kyushu-u.ac.jp 2Kazuto Nakashima and Ryo Kurazume are with Faculty of Information Science and Electrical Engineering, Kyushu University, Japan. k [email protected], [email protected] 3Yumi Iwashita is with Jet Propulsion Laboratory, California Institute of Technology, USA. [email protected]
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Gait recognition is a non-contact person identification method that utilizes cameras installed at a distance. However, gait images contain person-agnostic elements (covariates) such as clothing, and the removal of covariates is important for identification with high performance. Disentanglement representation learning, which separates gait-dependent information such as posture from covariates by unsupervised learning, has been attracting attention as a method to remove covariates. However, because the amount of gait data is negligible compared to other computer vision tasks, such as image recognition, the separation performance of existing methods is insufficient. In this study, we propose a gait recognition method to improve the separation performance, which augments the training data by adversarial generation based on identity features, separated by disentanglement representation learning. The proposed method first separates gait-dependent features (pose features) and appearance-related covariate features (style features) from gait videos based on disentanglement representation learning. Then, synthesized gait images are generated by exchanging pose features between gait images of the person under different walking conditions, followed by adding them to the training data. The experiments indicate that our method can improve the separation performance, and generate high-quality gait images that are effective for data augmentation.
AB - Gait recognition is a non-contact person identification method that utilizes cameras installed at a distance. However, gait images contain person-agnostic elements (covariates) such as clothing, and the removal of covariates is important for identification with high performance. Disentanglement representation learning, which separates gait-dependent information such as posture from covariates by unsupervised learning, has been attracting attention as a method to remove covariates. However, because the amount of gait data is negligible compared to other computer vision tasks, such as image recognition, the separation performance of existing methods is insufficient. In this study, we propose a gait recognition method to improve the separation performance, which augments the training data by adversarial generation based on identity features, separated by disentanglement representation learning. The proposed method first separates gait-dependent features (pose features) and appearance-related covariate features (style features) from gait videos based on disentanglement representation learning. Then, synthesized gait images are generated by exchanging pose features between gait images of the person under different walking conditions, followed by adding them to the training data. The experiments indicate that our method can improve the separation performance, and generate high-quality gait images that are effective for data augmentation.
UR - http://www.scopus.com/inward/record.url?scp=85126254991&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85126254991&partnerID=8YFLogxK
U2 - 10.1109/SII52469.2022.9708776
DO - 10.1109/SII52469.2022.9708776
M3 - Conference contribution
AN - SCOPUS:85126254991
T3 - 2022 IEEE/SICE International Symposium on System Integration, SII 2022
SP - 596
EP - 601
BT - 2022 IEEE/SICE International Symposium on System Integration, SII 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE/SICE International Symposium on System Integration, SII 2022
Y2 - 9 January 2022 through 12 January 2022
ER -