Action Recognition Using 3D Histograms of Texture and A Multi-Class Boosting Classifier

Zhang, Baochang, Yang, Yun, Chen, Chen, Yang, Linlin, Han, Jungong and Shao, Ling (2017) Action Recognition Using 3D Histograms of Texture and A Multi-Class Boosting Classifier. IEEE Transactions on Image Processing, 26 (10). pp. 4648-4660. ISSN 1057-7149

[img]
Preview
PDF (Accepted manuscript) - Submitted Version
Download (1MB) | Preview

Abstract

Human action recognition is an important yet challenging task. This paper presents a low-cost descriptor called 3D histograms of texture (3DHoTs) to extract discriminant features from a sequence of depth maps. 3DHoTs are derived from projecting depth frames onto three orthogonal Cartesian planes, i.e., the frontal, side, and top planes, and thus compactly characterize the salient information of a specific action, on which texture features are calculated to represent the action. Besides this fast feature descriptor, a new multi-class boosting classifier (MBC) is also proposed to efficiently exploit different kinds of features in a unified framework for action classification. Compared with the existing boosting frameworks, we add a new multi-class constraint into the objective function, which helps to maintain a better margin distribution by maximizing the mean of margin, whereas still minimizing the variance of margin. Experiments on the MSRAction3D, MSRGesture3D, MSRActivity3D, and UTD-MHAD data sets demonstrate that the proposed system combining 3DHoTs and MBC is superior to the state of the art.

Item Type: Article
Faculty \ School: Faculty of Science > School of Computing Sciences
Related URLs:
Depositing User: Pure Connector
Date Deposited: 28 Jul 2017 05:07
Last Modified: 22 Apr 2020 14:35
URI: https://ueaeprints.uea.ac.uk/id/eprint/64295
DOI: 10.1109/TIP.2017.2718189

Actions (login required)

View Item View Item