Action Recognition Using 3D Histograms Of Texture And A Multi-Class Boosting Classifier
Keywords
Action recognition; boosting classifier; depth image; multi-class classification; texture feature
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.
Publication Date
10-1-2017
Publication Title
IEEE Transactions on Image Processing
Volume
26
Issue
10
Number of Pages
4648-4660
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/TIP.2017.2718189
Copyright Status
Unknown
Socpus ID
85021832532 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85021832532
STARS Citation
Zhang, Baochang; Yang, Yun; Chen, Chen; Yang, Linlin; and Han, Jungong, "Action Recognition Using 3D Histograms Of Texture And A Multi-Class Boosting Classifier" (2017). Scopus Export 2015-2019. 5907.
https://stars.library.ucf.edu/scopus2015/5907