Moving multi-object tracking algorithm based on wavelet clustering and frame difference

Author

Zeng, Li ; Xu, Lida

Author_Institution

Inst. of Comput. Technol., Grad. Univ. of Chinese Acad. of Sci., Beijing, China

fYear

2009

fDate

11-14 Oct. 2009

Firstpage

3646

Lastpage

3650

Abstract

The paper presents an approach to motion objects tracking by combining parallel wavelet clustering with frame difference, which satisfies certain requirements of rapid moving objects detection. By utilizing multi-resolution property of wavelet clustering analysis based on adjacent frame difference results, we can identify arbitrary shape moving objects at different degree of accuracy. Experiment results show that good accuracy of proposed algorithm can be obtained at speeds close to real-time. Applications in real world are also presented which further demonstrated the efficiency and effectiveness of the proposed method.

Keywords

computer vision; image segmentation; object detection; pattern clustering; tracking; wavelet transforms; adjacent frame difference; computer vision; motion objects segmention process; multiobject tracking algorithm; multiresolution property; parallel wavelet clustering analysis; Clustering algorithms; Computer vision; Image motion analysis; Motion analysis; Motion detection; Object detection; Optical computing; Optical noise; Optical sensors; Radar tracking; Moving Object Tracking; Wavelet Clustering;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2009. SMC 2009. IEEE International Conference on

Conference_Location

San Antonio, TX

ISSN

1062-922X

Print_ISBN

978-1-4244-2793-2

Electronic_ISBN

1062-922X

Type

conf

DOI

10.1109/ICSMC.2009.5346864

Filename

5346864