A Human Half-Top Kinematic Motion Tracking System Based on Disparity Information of Stereo Camera

Youngouk Kim; Sewoong Jun

doi:10.4028/www.scientific.net/AMR.605-607.1391

Paper Titles

Fluid Field Analysis for Cyclone Separator Used on Grain Cleaning
p.1369

Impeller Finite Element Analysis of Extractable Explosion-Proof Contra-Rotating Axial Fan for Mine Local Ventilation FBDC
p.1372

A Linear Macro/Micro Platform Design Based on FEM Simulation
p.1379

The Effect of Electrode’s Material on Immobilization of Sulfite Oxidase Enzyme in Construction of Sulfite Biosensors
p.1387

A Human Half-Top Kinematic Motion Tracking System Based on Disparity Information of Stereo Camera
p.1391

Map Matching-Aided In-Motion SINS Initial Alignment
p.1395

Modeling and Design of 3D Visualization on Giant Magnetostrictive Actuator
p.1402

A DSP-Based Control System for Precision Variable Rate Fertilization
p.1408

Design of a Type of Cleaning Robot System
p.1415

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 605-607A Human Half-Top Kinematic Motion Tracking System...

A Human Half-Top Kinematic Motion Tracking System Based on Disparity Information of Stereo Camera

Abstract:

This paper presents a new real-time system to acquire motion information of human articulated objects such as arm and head. The system does not need any marker or device to wear on human body and adopted stereo camera to obtain robust system against for illumination and complex background without position initialization of articulated objects. We present a solution to estimate self-occluded body objects when human model behaves normal action towards the camera. The main idea of the solution is to apply a component labeling techniques on sliced disparity map, and found the arm position when the arm is located in front of basis distance of body and we could also found arm location when the arm is located on the basis distance with Morphological methods. From this approach, we can obtain the full body shape considering self-occlusion. It is simple and fast in comparison with other methods which satisfy real-time performance and accuracy of object tracking at the same time.

You might also be interested in these eBooks

Advanced Designs and Researches for Manufacturing

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 605-607)

Pages:

1391-1394

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.605-607.1391

Citation:

Cite this paper

Online since:

December 2012

Authors:

Youngouk Kim, Sewoong Jun

Keywords:

Disparity, Human Kinematic Tracking, Motion Estimation, Stereo Camera

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] E. Trucco and A. Verri, Introductory Techniques for 3-D Computer Vision, Prentice Hall, New Jersey, (1998).

Google Scholar

[2] T. Fong, I. Nourbakhsh and K. Dautenhahn, A survey of socially interactive robots, Robotics and Autonomous Systems, 42: 143-166, (2003).

DOI: 10.1016/s0921-8890(02)00372-x

Google Scholar

[3] M.K. Leung, Y.H. Yang, First Sight: A Human Body Ouline Labeling System., IEEE Trans. PAMI., 17(4): 359-377, (1995).

Google Scholar

[4] I. Kakadiaris, D. Metaxas, Model-based estimation of 3D human motion, IEEE PAMI, pp.1453-1459, (2000).

DOI: 10.1109/34.895978

Google Scholar

[5] A. F. Lerasle, G. River, et al, Human Body Limb Tracking by Monocular Vision, Scandinavian Conference, Volume 2, 20-27 Sept. 1999 Page(s): 716-721 vol. 2.

Google Scholar

[6] J. Yang, R. Stiefelhagen, U. Meier, and A. Waibel, Real-time face and facial feature tracking and applications, " in Proc. of AVSP, 98, pp.79-84, Terrigal, Australia, (1998).

Google Scholar

[7] Sewoong Jun, Stereo Camera based Human Motion Capture by using Expectation Maximization Algorithm, Dept. of Electrial and Electronics Engineering. The Graduate School of Yonsei Univ. (2006).

Google Scholar