Video Vehicle Tracking Based on Improved Mean-Shift Algorithm

Abstract:

Article Preview

An improved Mean-Shift-based Video vehicle tracking algorithm was proposed and which can improve the real-time and accuracy of the vehicle detection technology in the application. First, it eliminates the disturbance from unrelated background by mathematical morphology operation between a traffic image and the mask of fixed background area .Then the image sequences are simulated by absolute difference of adaptive threshold for detecting latent target. At last, clusters video frames with similar characteristics which are regarded of the invariant moments vectors by Mean Shift clustering algorithm. Experimental results shown that the improved algorithm has advantages of reducing king region of vehicle matching and vehicle complete occlusion.

Info:

Periodical:

Advanced Materials Research (Volumes 179-180)

Edited by:

Garry Zhu

Pages:

1408-1411

DOI:

10.4028/www.scientific.net/AMR.179-180.1408

Citation:

W. B. Chen et al., "Video Vehicle Tracking Based on Improved Mean-Shift Algorithm", Advanced Materials Research, Vols. 179-180, pp. 1408-1411, 2011

Online since:

January 2011

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.