Abstract
To increase the reliability of existing human motion tracking algorithms, we propose a method for imposing limits on the underlying hierarchical joint structures in a way that is true to life. Unlike most existing approaches, we explicitly represent dependencies between the various degrees of freedom and derive these limits from actual experimental data.
To this end, we use quaternions to represent individual 3 DOF joint rotations and Euler angles for 2 DOF rotations, which we have experimentally sampled using an optical motion capture system. Each set of valid positions is bounded by an implicit surface and we handle hierarchical dependencies by representing the space of valid configurations for a child joint as a function of the position of its parent joint.
This representation provides us with a metric in the space of rotations that readily lets us determine whether a posture is valid or not. As a result, it becomes easy to incorporate these sophisticated constraints into a motion tracking algorithm, using standard constrained optimization techniques. We demonstrate this by showing that doing so dramatically improves performance of an existing system when attempting to track complex and ambiguous upper body motions from low quality stereo data.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Gavrila, D.: The Visual Analysis of Human Movement: A Survey. Computer Vision and Image Understanding 73 (1999)
Moeslund, T., Granum, E.: Pose estimation of a human arm using kinematic constraints. In: Scandinavian Conference on Image Analysis, Bergen, Norway (2001)
Moeslund, T.: Computer Vision-Based Motion Capture of Body Language. PhD thesis, Aalborg University, Aalborg, Denmark (2003)
Rehg, J.M., Morris, D.D., Kanade, T.: Ambiguities in Visual Tracking of Articulated Objects using 2–D and 3–D Models. International Journal of Robotics Research 22, 393–418 (2003)
Bregler, C., Malik, J.: Tracking People with Twists and Exponential Maps. In: Conference on Computer Vision and Pattern Recognition, Santa Barbara, CA (1998)
Demirdjian, D.: Enforcing constraints for human body tracking. In: Workshop on Multi-Object Tracking (2003)
Sminchisescu, C., Triggs, B.: Estimating articulated human motion with covariance scaled sampling. International Journal of Robotics Research (2003)
Engin, A., Tümer, S.: Three-dimensional kinematic modeling of the human shoulder complex. Journal of Biomechanical Engineering 111, 113–121 (1989)
Herda, L., Urtasun, R., Hanson, A., Fua, P.: An automatic method for determining quaternion field boundaries for ball-and-socket joint limits. International Journal of Robotics Research 22, 419–436 (2003)
Shoemake, K.: Animating Rotation with Quaternion Curves. Computer Graphics, SIGGRAPH Proceedings 19, 245–254 (1985)
Baerlocher, P., Boulic, R.: An Inverse Kinematics Architecture for Enforcing an Arbitrary Number of Strict Priority Levels. The Visual Computer (2004)
Plänkers, R., Fua, P.: Articulated Soft Objects for Multi-View Shape and Motion Capture. IEEE Transactions on Pattern Analysis and Machine Intelligence (2003)
Hatze, H.: A three-dimensional multivariate model of passive human joint torques and articular boundaries. Clinical Biomechanics 12, 128–135 (1997)
Kodek, T., Munich, M.: Identifying Shoulder and Elbow Passive Moments and Muscle Contributions. In: International Conference on Intelligent Robots and Systems (2002)
Johnston, R., Smidt, G.: Measurement of hip joint motion during walking. Journal of Bone and Joint Surgery 51, 1083–1094 (1969)
Meskers, C., Vermeulen, H., de Groot, J., der Helm, F.V., Rozing, P.: 3d shoulder position measurements using a six-degree-of-freedom electromagnetic tracking device. Clinical Biomechanics 13, 280–292 (1998)
der Helm, F.V.: A standardized protocol for motion recordings of the shoulder. In: Conference of the International Shoulder Group, Masstritcht, Netherlands (1997)
Bao, H., Willems, P.: On the kinematic modelling and the parameter estimation of the human shoulder. Journal of Biomechanics 32, 943–950 (1999)
Maurel, W.: 3d modeling of the human upper limb including the biomechanics of joints, muscles and soft tissues (1998)
Wang, X., Maurin, M., Mazet, F., Maia, N.D.C., Voinot, K., Verriest, J., Fayet, M.: Three-dimensional modelling of the motion range of axial rotation of the upper arm. Journal of Biomechanics 31, 899–908 (1998)
Bobick, N.: Rotating objects using quaternions. Game Developer 2(26) (1998)
Watt, A., Watt, M.: Advanced animation and rendering techniques (1992)
Grassia, F.: Practical parameterization of rotations using the exponential map. Journal of Graphics Tools 3, 29–48 (1998)
Pervin, E., Webb, J.: Quaternions for computer vision and robotics. In: Conference on Computer Vision and Pattern Recognition, Washington, D.C., pp. 382–383 (1983)
Faugeras, O.: Three-Dimensional Computer Vision: a Geometric Viewpoint. MIT Press, Cambridge (1993)
Bloomenthal, J.: Calculation of reference frames along a space curve. In: Glassner, A. (ed.) Graphics Gems, pp. 567–571. Academic Press, Cambridge (1990)
Tsingos, N., Bittar, E., Gascuel, M.: Implicit surfaces for semi-automatic medical organs reconstruction. In: Computer Graphics International, Leeds, UK, pp. 3–15 (1995)
Lorensen, W., Cline, H.: Marching Cubes: A High Resolution 3D Surface Construction Algorithm. In: Computer Graphics, SIGGRAPH Proceedings, vol. 21, pp. 163–169 (1987)
Ranjan, V., Fournier, A.: Shape transformations using union of spheres. Technical Report TR-95-30, Department of Computer Science, University of British Columbia (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Herda, L., Urtasun, R., Fua, P. (2004). Hierarchical Implicit Surface Joint Limits to Constrain Video-Based Motion Capture. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3022. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24671-8_32
Download citation
DOI: https://doi.org/10.1007/978-3-540-24671-8_32
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21983-5
Online ISBN: 978-3-540-24671-8
eBook Packages: Springer Book Archive