Human Motion Reconstruction Based on Multi-view Video

Author

Qinkun Xiao ; Dan Luo ; Qinhan Xiao

Author_Institution

Dept. of Electron. & Inf. Eng., Xi´an Technol. Univ., Xi´an, China

Volume

2

fYear

2013

fDate

26-27 Aug. 2013

Firstpage

23

Lastpage

26

Abstract

In this paper, the key technologies of human motion reconstruction based on multi-view video are discussed. A more robust motion reconstruction method with markers is presented, which includes camera calibration, markers extraction, markers tracking and 3D reconstruction. In the procedure of markers tracking, we propose a novel multi-view tracking algorithm. This algorithm is made up of two steps, one is binocular stereo vision tracking which combines the Extended Kalman Filter with the smooth of markers´ trajectory, and another is multi-view data fusion. The effectiveness of this method is verified by experiments.

Keywords

Kalman filters; calibration; cameras; feature extraction; image motion analysis; image reconstruction; object tracking; sensor fusion; stereo image processing; video signal processing; 3D reconstruction; binocular stereo vision tracking; camera calibration; extended Kalman filter; human motion reconstruction; marker trajectory; markers extraction; markers tracking; multiview data fusion; multiview tracking algorithm; multiview video; Calibration; Cameras; Image color analysis; Image reconstruction; Stereo vision; Three-dimensional displays; Tracking; camera calibration; motion reconstruction; motion tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2013 5th International Conference on

Conference_Location

Hangzhou

Print_ISBN

978-0-7695-5011-4

Type

conf

DOI

10.1109/IHMSC.2013.153

Filename

6642681