An unsupervised approach for human activity detection and recognition

被引：0

作者：

Department of Electrical Engineering and Information, Systems, Graduate School of Engineering, The University of Tokyo, Hongo 7-3-1, Bunkyo-ku ^{[1
]}

Tokyo, Japan

不详 ^{[2
]}

CA, United States

机构：

[1] Department of Electrical Engineering and Information, Systems, Graduate School of Engineering, The University of Tokyo, Hongo 7-3-1, Bunkyo-ku, 113-8656, Tokyo

[2] Department of Radiology, University of California, Los Angeles, Los Angeles, 90095-7437, CA

来源：

Int. J. Simul. Syst. Sci. Technol. | / 5卷 / 42-49期

关键词：

Human activity detection; Human activity recognition; RGBD sensor; Unsupervised learning;

D O I：

10.5013/IJSSST.a.14.05.06

中图分类号：

学科分类号：

摘要：

Human activity recognition is an important ability in any system that supports human in performing their daily activities. However, current supervised approach in human activity recognition is difficult to be deployed in the natural human living environment where labeled observations are scarce. In this paper, we demonstrate the use of K-means clustering and simple template models to achieve human activity detection and recognition in an unsupervised manner. The features used are extracted from the skeleton data obtained from an inexpensive RGBD (RGB-Depth) sensor. Our results show an average detection performance of 80.4% precision and 83.8% recall. The availability of an unsupervised approach in human activity recognition will make possible the wide adoption of human activity recognition in the natural human living environment. © 2013, UK Simulation Society. All Rights Reserved.

引用

页码：42 / 49

页数：7

共 10 条

[1]

Aggarwal J.K., Ryoo M.S., Human activity analysis: A review, ACM Comput. Surv., 43, 3, (2011)

[2]

Zhang Z., Microsoft kinect sensor and its effect, IEEE Multimedia, 19, 2, pp. 4-10, (2012)

[3]

Ong W., Palafox L., Koseki T., Investigation of Feature Extraction for Unsupervised Learning in Human Activity Detection, Bulletin of Networking, Computing, Systems, and Software, North America, (2013)

[4]

Sung J., Ponce C., Selman B., Saxena A., Human Activity Detection from RGBD Images, Association for the Advancedment of Artificial Intelligence Workshop on Pattern, Activity and Intent Recognition (PAIR), pp. 47-55, (2011)

[5]

Wyatt D., Philipose M., Choudhury T., Unsupervised activity recognition using automatically mined common sense, Proceedings of the National Conference on Artificial Intelligence, 20, 1, (2005)

[6]

Stikic M., Larlus D., Ebert S., Schiele B., Weakly Supervised Recognition of Daily Life Activities with Wearbale Sensors, IEEE Transactions on Pattern Analysis and Machine Intelligence, 33, 12, pp. 2521-2537, (2011)

[7]

Huynh T., Fritz M., Schiele B., Discovery of Activity Patterns using Topic Models, International Conference on Ubiquitous Computing, pp. 10-19, (2008)

[8]

Song Y., Goncalves L., Perona P., Unsupervised learning of human motion, in Pattern Analysis and Machine Intelligence, IEEE Transactions On, 25, 7, pp. 814-827, (2003)

[9]

The Standard Framework for 3D Sensing, (2010)

[10]

Macqueen J., Some methods for classification and analysis of multivariate observations, Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1, 281-297, (1967)

← 1 →