Multiple Image Based Human Joint Angle Computation

Abstract:

This paper presents a new computation method for human joint angle. A human structure is modelled as an articulated rigid body kinematics in single video stream. Every input image consists of a rotating articulated segment with a different 3D angle. Angle computation for a human joint is achieved by several steps. First we compute internal as well as external parameters of a camera using feature points of fixed environment using nonlinear programming. We set an image as a reference image frame for 3D scene analysis for a rotating articulated segment. Then we compute angles of rotation and a center of rotation of the segment for each input frames using corresponding feature points as well as computed camera parameters using nonlinear programming. With computed angles of rotation and a center of rotation, we can perform volumetric reconstruction of an articulated human body in 3D. Basic idea for volumetric reconstruction is regarding separate 3D reconstruction for each articulated body segment. Volume reconstruction in 3D for a rotating segment is done by modifying transformation relation of world-to-camera to adjust an angle of rotation of a rotated segment as if there were no rotation for the segment. Our experimental results for a single rotating segment show our method works well.

• Periodical: Applied Mechanics and Materials (Volume 865)
• Pages: 547-553
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.865.547
• Online since: June 2017
• Authors: Ji Hun Park*
• Keywords: 3D Scene Reconstruction, Camera Calibration, Human Joint Angle Computation

References

[1] R. Hartley, A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, 2nd., (2004).

[2] M. Pollefeys, R. Koch, L. V. Gool, Self-calibration and metric reconstruction inspite of varying and unknown intrinsic camera parameters, Int. J. Comput. Vis. 32(1) (1999) 7-25.

DOI: 10.1109/iccv.1998.710705

[3] T. Moons, L. van Gool, M. Vergauwen, 3d reconstruction from multiple images, part I: Principles, Found. Trend. Comput. Graph. Vis. 4 (2008) 287-404.

[4] Z. Zhang, A flexible new technique for camera calibration, IEEE Trans. Patt. Anal. Mach. Intell. 22 (2000) 1330-1334.

DOI: 10.1109/34.888718

[5] J. Park, S. Park, Improvement on zhang's camera calibration, Appl. Mech. Mater. 479-480 (2013) 170-173.

[6] S. Seitz, B. Curless, J. Diebel, S. D, R. Szeliski, A comparison and evaluation of multi-view stereo reconstruction algorithm, in: Computer Vision and Pattern Recognition, (2006), pp.519-528.

DOI: 10.1109/cvpr.2006.19

[7] T. Fromherz, M. Bichsel, Shape from multiple cues: Integrating local brightness information, in ICYCS, (1995).

[8] K. Kutulakos, S. Seitz, A theory of shape by space carving, IJCV 38 (2000), pp.199-218.

[9] O. Faugeras, E. Bras-Mehlman, J. D. Boissonnat, Representing stereo data with the delaunay triangulation, Artif. Intell. 44 (1990) 41-87.

DOI: 10.1016/0004-3702(90)90098-k

[10] A. Laurentini, The visual hull concept for silhouette-based image understanding, IEEE Trans. PAMI, 16 (1994) 150-162.

DOI: 10.1109/34.273735

[11] J. Yan, M. Pollefeys, A factorization-based approach to articulated motion reconstruction, in: IEEE Conference on Compter Vision and Pattern Recognition, Sandiego, California, (2005).

DOI: 10.1109/cvpr.2005.28

[12] J. Yan, M. Pollefeys, A general framework for motion segmentation: independent, articulated, rigid, non-rigid, degenerate and non-degenerate, in: 4th European Conference on Compter Vision, Cambridge, UK, (2006).

DOI: 10.1007/11744085_8

[13] P. Tresadern, I. Reid, Articulated structure from motion by factorization, in: IEEE Conference on Compter Vision and Pattern Recognition, Sandiego, California, (2005).

DOI: 10.1109/cvpr.2005.75

[14] R. Vidal, R. Hartley, Motion segmentation with missing data using power factorization and gpca, in: IEEE Conference on Compter Vision and Pattern Recognition, Washington D.C., (2004).

DOI: 10.1109/cvpr.2004.1315180

[15] J. Park, S. Kim, Kinematics and constrained joint design using quaternion, in: CISST, (2002).

[16] L. S. Lasdon, A. D. Warren, A. Jain, M. Ratner, Design and testing of a generalized reduced gradient code for nonlinear programming, ACM Trans. Math. Software, 4 (1978) 34-50.

DOI: 10.1145/355769.355773