TY - GEN
T1 - Multi-attributes gait identification by convolutional neural networks
AU - Yan, Chao
AU - Zhang, Bailing
AU - Coenen, Frans
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2016/2/16
Y1 - 2016/2/16
N2 - Gait as a biometric feature that can be measured remotely without physical contact and proximal sensing has attract significant attention. This paper proposes to use con-volutional neural networks (ConvNets) and multi-task learning model(MLT) to identify human gait and to predict multiple human attributes simultaneously. In comparison to previous approaches, two novelty in our convolutional approach can be summarised as (i)using ConvNets to learn rich features from the training set is more generic and requires minimal domain knowledge of the problem compared to hand-craft feature, (ii) to identify human gait and to predict other human attributes simultaneously can achieve improved performance for all task than standalone gait identification. Specifically, we first extract Gait Energy Image(GEI) from each walking period as the low level input for the ConvNets. Secondly, we train the ConvNets through back-propagation using a joint loss of each task. Finally, high-level feature is hierarchically extracted in ConvNets, which is shared by each task and used to identify human gait and to predict attribute. The approach was verified on CASIA gait database B, achieving over 95.88% accuracy for each task. To the authors' best knowledge, this is the first time multi-attributes gait identification being proposed.
AB - Gait as a biometric feature that can be measured remotely without physical contact and proximal sensing has attract significant attention. This paper proposes to use con-volutional neural networks (ConvNets) and multi-task learning model(MLT) to identify human gait and to predict multiple human attributes simultaneously. In comparison to previous approaches, two novelty in our convolutional approach can be summarised as (i)using ConvNets to learn rich features from the training set is more generic and requires minimal domain knowledge of the problem compared to hand-craft feature, (ii) to identify human gait and to predict other human attributes simultaneously can achieve improved performance for all task than standalone gait identification. Specifically, we first extract Gait Energy Image(GEI) from each walking period as the low level input for the ConvNets. Secondly, we train the ConvNets through back-propagation using a joint loss of each task. Finally, high-level feature is hierarchically extracted in ConvNets, which is shared by each task and used to identify human gait and to predict attribute. The approach was verified on CASIA gait database B, achieving over 95.88% accuracy for each task. To the authors' best knowledge, this is the first time multi-attributes gait identification being proposed.
KW - Convolutional neural network
KW - Deep learning
KW - Gait energy image
KW - Gait recognition
KW - Human gait identification
KW - Multi-task learning
UR - http://www.scopus.com/inward/record.url?scp=84966526512&partnerID=8YFLogxK
U2 - 10.1109/CISP.2015.7407957
DO - 10.1109/CISP.2015.7407957
M3 - Conference Proceeding
AN - SCOPUS:84966526512
T3 - Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015
SP - 642
EP - 647
BT - Proceedings - 2015 8th International Congress on Image and Signal Processing, CISP 2015
A2 - Wang, Lipo
A2 - Lin, Sen
A2 - Tao, Zhiyong
A2 - Zeng, Bing
A2 - Hui, Xiaowei
A2 - Shao, Liangshan
A2 - Liang, Jie
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 8th International Congress on Image and Signal Processing, CISP 2015
Y2 - 14 October 2015 through 16 October 2015
ER -