Human activity recognition from 3D data: A review

被引：381

作者：

Aggarwal, J. K. ^{[1
]}

Xia, Lu ^{[1
]}

机构：

[1] Univ Texas Austin, Austin, TX 78705 USA

来源：

PATTERN RECOGNITION LETTERS | 2014年 / 48卷

关键词：

Computer vision; Human activity recognition; 3D data; Depth image; RANGE IMAGES; OPTICAL-FLOW; STEREO; MOTION; TRACKING; SHAPE; VISION; DENSE; HISTOGRAMS; INVARIANT;

D O I：

10.1016/j.patrec.2014.04.011

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Human activity recognition has been an important area of computer vision research since the 1980s. Various approaches have been proposed with a great portion of them addressing this issue via conventional cameras. The past decade has witnessed a rapid development of 3D data acquisition techniques. This paper summarizes the major techniques in human activity recognition from 3D data with a focus on techniques that use depth data. Broad categories of algorithms are identified based upon the use of different features. The pros and cons of the algorithms in each category are analyzed and the possible direction of future research is indicated. (C) 2014 Elsevier B. V. All rights reserved.

引用

页码：70 / 80

页数：11

共 110 条

[71]

Masood S. Z., 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops), P422, DOI 10.1109/ICCVW.2011.6130272

[72]

Matsumoto Y., 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580), P499, DOI 10.1109/AFGR.2000.840680

[73]

Mitiche A., 2013, Computer vision analysis of image motion by variational methods

[74] People detection and tracking using stereo vision and color [J].