Extended Online HECOL Based Multi-camera Object Tracking

Author

Fan, Jingjing ; Lin, Qing ; Hu, Bo

Author_Institution

Dept. of Electron. Eng., Fudan Univ., Shanghai, China

fYear

2010

fDate

25-27 June 2010

Firstpage

1

Lastpage

4

Abstract

The tracking robustness can be improved greatly using multi-camera system because the overlapping field of view provides more information of the objects. However, traditional template matching based multi-camera object tracking suffers from the tracking errors brought by view point differences. To solve the problem, we propose the extended online HECOL (Homography and Epipolar-based Consistent Labeling) to communicate templates between different camera views which is no longer limited to the ground plane. We use the Structural Similarity Image Measurement (SSIM) as the criteria to match between different views. Besides, we applied the Gaussian model and Bayesian statistics to fuse different cameras´ tracking results of last moment. Experiments show that the proposed way of transferring different view points´ template reduces tracking error when occlusion and 3D rotation occur.

Keywords

Gaussian processes; cameras; computer vision; object detection; statistics; 3D rotation; Bayesian statistic; Gaussian model; camera tracking; homography and epipolar-based consistent labeling; multicamera object tracking; multicamera system; online HECOL; structural similarity image measurement; template matching; tracking error; tracking robustness; Cameras; Classification algorithms; Fuses; Geometry; Robustness; Streaming media; Tracking; Multi-template transition and matching; SSIM; correspondence confidence; extended HECOL;

fLanguage

English

Publisher

ieee

Conference_Titel

Electrical and Control Engineering (ICECE), 2010 International Conference on

Conference_Location

Wuhan

Print_ISBN

978-1-4244-6880-5

Type

conf

DOI

10.1109/iCECE.2010.8

Filename

5630676