3D Action Recognition Using Multi-Temporal Skeleton Visualization
Keywords
3D action recognition; convolutional neural networks; skeleton data; visualization
Abstract
Action recognition using depth sequences plays important role in many fields, e.g., intelligent surveillance, content-based video retrieval. Real applications require robust and accurate action recognition method. In this paper, we propose a skeleton visualization method, which efficiently encodes the spatial-temporal information of skeleton joints into a set of color images. These images are served as inputs for convolutional neural networks to extract more discriminative deep features. To enhance the ability of deep features to capture global relationships, we extend the color images into multi-temporal version. Additionally, to solve the effect of view point changes, a spatial transform method is adopted as a preprocessing step. Extensive experiments on NTU RGB+D dataset and ICME2017 challenge show that our method can accurately distinguish similar actions and shows robustness to view variations.
Publication Date
9-5-2017
Publication Title
2017 IEEE International Conference on Multimedia and Expo Workshops, ICMEW 2017
Number of Pages
623-626
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICMEW.2017.8026280
Copyright Status
Unknown
Socpus ID
85031705320 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85031705320
STARS Citation
Liu, Mengyuan; Chen, Chen; Meng, Fanyang; and Liu, Hong, "3D Action Recognition Using Multi-Temporal Skeleton Visualization" (2017). Scopus Export 2015-2019. 7478.
https://stars.library.ucf.edu/scopus2015/7478