Share Email Print
cover

Proceedings Paper

3D abnormal behavior recognition in power generation
Author(s): Zhenhua Wei; Xuesen Li; Jie Su; Jie Lin
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

So far most research of human behavior recognition focus on simple individual behavior, such as wave, crouch, jump and bend. This paper will focus on abnormal behavior with objects carrying in power generation. Such as using mobile communication device in main control room, taking helmet off during working and lying down in high place. Taking account of the color and shape are fixed, we adopted edge detecting by color tracking to recognize object in worker. This paper introduces a method, which using geometric character of skeleton and its angle to express sequence of three-dimensional human behavior data. Then adopting Semi-join critical step Hidden Markov Model, weighing probability of critical steps' output to reduce the computational complexity. Training model for every behavior, mean while select some skeleton frames from 3D behavior sample to form a critical step set. This set is a bridge linking 2D observation behavior with 3D human joints feature. The 3D reconstruction is not required during the 2D behavior recognition phase. In the beginning of recognition progress, finding the best match for every frame of 2D observed sample in 3D skeleton set. After that, 2D observed skeleton frames sample will be identified as a specifically 3D behavior by behavior-classifier. The effectiveness of the proposed algorithm is demonstrated with experiments in similar power generation environment.

Paper Details

Date Published: 20 May 2011
PDF: 6 pages
Proc. SPIE 8043, Three-Dimensional Imaging, Visualization, and Display 2011, 80430Y (20 May 2011); doi: 10.1117/12.883819
Show Author Affiliations
Zhenhua Wei, North China Electric Power Univ. (China)
Xuesen Li, North China Electric Power Univ. (China)
Jie Su, Harbin Univ. of Science and Technology (China)
Jie Lin, North China Electric Power Univ. (China)


Published in SPIE Proceedings Vol. 8043:
Three-Dimensional Imaging, Visualization, and Display 2011
Bahram Javidi; Jung-Young Son, Editor(s)

© SPIE. Terms of Use
Back to Top