Skeleton Optical Spectra-Based Action Recognition Using Convolutional Neural Networks

Authors

Yonghong Hou, Tianjin University
Zhaoyang Li, Tianjin University
Pichao Wang, University of WollongongFollow
Wanqing Li, University of WollongongFollow

RIS ID

123241

Publication Details

Hou, Y., Li, Z., Wang, P. & Li, W. (2018). Skeleton Optical Spectra-Based Action Recognition Using Convolutional Neural Networks. IEEE Transactions on Circuits and Systems for Video Technology, 28 (3), 807-811.

Abstract

2016 IEEE. This letter presents an effective method to encode the spatiotemporal information of a skeleton sequence into color texture images, referred to as skeleton optical spectra, and employs convolutional neural networks (ConvNets) to learn the discriminative features for action recognition. Such spectrum representation makes it possible to use a standard ConvNet architecture to learn suitable 'dynamic' features from skeleton sequences without training millions of parameters afresh and it is especially valuable when there is insufficient annotated training video data. Specifically, the encoding consists of four steps: mapping of joint distribution, spectrum coding of joint trajectories, spectrum coding of body parts, and joint velocity weighted saturation and brightness. Experimental results on three widely used datasets have demonstrated the efficacy of the proposed method.