JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE) ›› 2010, Vol. 40 ›› Issue (2): 19-23.

• Articles • Previous Articles     Next Articles

Crowd object detection and classification based on a chaotic dynamic model

QIAO Wei1, WANG Hui-yuan1,2, WU Xiao-juan1, LIU Peng-wei1   

  1. 1. School of Information Science and Engineering, Shandong University, Jinan 250100, China;
    2. IEETA, Universidade de Aveiro, Aveiro, 3810-193, Portugal
  • Received:2009-03-18 Online:2010-04-16 Published:2009-03-18

Abstract:

Multi-object detection and tracking is an arduous task for traditional methods, and  objects in crowds are more difficult to deal with. In this paper,segmentation and detection to video crowd flow was realized by a chaotic dynamics based method. The crowd moving system was treated as a chaotic dynamic system, and object in  crowds were treated as particles, whose flow is tracked by flow map. As a result, the finite time Lyapunov exponent (FTLE) field was obtained. After morphological processing, region extraction and classification can be achieved. Experimental results indicate the effectiveness of the proposed approach.

Key words:  crowd object detection, finite time Lyapunov exponent, contour extraction

[1] ZUO Junyan, ZHANG Jianguo, ZHONG Tao. Connection algorithm of bone tissue based on canny edge detection [J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2015, 45(3): 65-72.
[2] CONG Kui-Rong, HAN Jie, CHANG Fa-Liang. Goods contour detection and positioning by a vision robot [J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2010, 40(1): 15-18.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!