Real-Time Person Tracking Based on Data Field

Authors:
Shuliang Wang;Juebo Wu;Feng Cheng;Hong Jin
Affiliations:
International School of Software, Wuhan University, Wuhan, China 430079 and State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China ...;State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China 430079;International School of Software, Wuhan University, Wuhan, China 430079;International School of Software, Wuhan University, Wuhan, China 430079
Venue:
ADMA '08 Proceedings of the 4th international conference on Advanced Data Mining and Applications
Year:
2008

Citing 5
Cited 0

Data clustering: a review

ACM Computing Surveys (CSUR)
W4: Real-Time Surveillance of People and Their Activities

IEEE Transactions on Pattern Analysis and Machine Intelligence
Data mining: concepts and techniques

Data mining: concepts and techniques
Tracking People with Twists and Exponential Maps

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
A master-slave system to acquire biometric imagery of humans at distance

IWVS '03 First ACM SIGMM international workshop on Video surveillance

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a novel approach of data field is proposed to discover the action pattern of real-time person tracking, and potential function is presented to find out the power of a person with suspicious action. Firstly, a data field on the first feature is used to find the individual attributes, associated with the velocity, direction changing frequency and appearance frequency respectively. Secondly, the common characteristic of each attribute is obtained by the data field on the main feature from the data field created before. Thirdly, the weighted Euclidean distance classifier is used to identify whether a person is a suspect or not. Finally, the results of the experiment show that the proposed way is feasible and effective in action mining.