Publication: Learning and Recognizing Human Action from Skeleton Movement with Deep Residual Neural Networks
Loading...
Identifiers
Publication date
2017-07-11
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
The Institution Of Engineering And Technology
Impact
Export
Abstract
Automatic human action recognition is indispensable for almost artificial intelligent systems such as video surveillance, human-computer interfaces, video retrieval, etc. Despite a lot of progresses, recognizing actions in a unknown video is still a challenging task in computer vision. Recently, deep learning algorithms has proved its great potential in many vision-related recognition tasks. In this paper, we propose the use of Deep Residual Neural Networks (ResNets) to learn and recognize human action from skeleton data provided by Kinect sensor. Firstly, the body joint coordinates are transformed into 3D-arrays and saved in RGB images space. Five different deep learning models based on ResNet have been designed to extract image features and classify them into classes. Experiments are conducted on two public video datasets for human action recognition containing various challenges. The results show that our method achieves the state-of-the-art performance comparing with existing approaches
Description
This paper has been presented at 8th International Conference of Pattern Recognition Systems (ICPRS 2017).
Keywords
Action recognition, ResNet, Skeleton, Kinect
Bibliographic citation
Pham, H.H., Khoudour, L., Crouzil, A., Zegers, P. y Velastin, S.A. (2017). Learning and recognizing human action from Skeleton movement with deep residual neural networks. In 8th International Conference of Pattern Recognition Systems (ICPRS 2017).