Human motion capturing can be regarded as an optimization problem where one searches for the pose that minimizes a previously defined error function based on some image features. Most approaches for solving this problem use iterative methods like gradient descent approaches. They work quite well as long as they do not get distracted by local optima. We introduce a novel approach for global optimization that is suitable for the tasks as they occur during human motion capturing. We call the method interacting simulated annealing since it is based on an interacting particle system that converges to the global optimum similar to simulated annealing. We provide a detailed mathematical discussion that includes convergence results and annealing properties. Moreover, we give two examples that demonstrate possible applications of the algorithm, namely a global optimization problem and a multi-view human motion capturing task including segmentation, prediction, and prior knowledge. A quantative error analysis also indicates the performance and the robustness of the interacting simulated annealing algorithm.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Ackley D. A Connectionist Machine for Genetic Hillclimbing. Kluwer, Boston, 1987.
Bäck T. and Schwefel H.-P. An overview of evolutionary algorithms for para-meter optimization. Evolutionary Computation, 1:1-24, 1993.
Bauer H. Probability Theory. de Gruyter, Baton Rouge, 1996.
Besl P. and McKay N. A Method for registration of 3-D Shapes. IEEE Trans-actions on Pattern Analysis and Machine Intelligence, 14(2):239-256, 1992.
Brox T., Rosenhahn B., Cremers D., and Seidel H.-P. High accuracy optical flow serves 3-D pose tracking: exploiting contour and flow based constraints. In A. Leonardis, H. Bischof, and A. Pinz, editors, European Conference on Computer Vision (ECCV), LNCS 3952, pp. 98-111. Springer, 2006.
Brox T., Rosenhahn B., Kersting U., and Cremers D., Nonparametric density estimation for human pose tracking. In Pattern Recognition (DAGM). LNCS 4174, pp. 546-555. Springer, 2006.
Bregler C., Malik J., and Pullen K. Twist based acquisition and tracking of animal and human kinematics. International Journal of Computer Vision, 56:179-194, 2004.
Brox T., Rosenhahn B., and Weickert J. Three-dimensional shape knowledge for joint image segmentation and pose estimation. In W. Kropatsch, R. Sablatnig, A. Hanbury, editors, Pattern Recognition (DAGM), LNCS 3663, pp. 109-116. Springer, 2005.
Deutscher J. and Reid I. Articulated body motion capture by stochastic search. International Journal of Computer Vision, 61(2):185-205, 2005.
Doucet A., deFreitas N., and Gordon N., editors. Sequential Monte Carlo Meth-ods in Practice. Statistics for Engineering and Information Science. Springer, New York, 2001.
Gall J., Potthoff J., Schnoerr C., Rosenhahn B., and Seidel H.-P. Interacting and annealing particle systems - mathematics and recipes. Journal of Mathematical Imaging and Vision, 2007, To appear.
Gall J., Rosenhahn B., Brox T., and Seidel H.-P. Learning for multi-view 3D tracking in the context of particle filters. In International Symposium on Visual Computing (ISVC), LNCS 4292, pp. 59-69. Springer, 2006.
Gall J., Rosenhahn B., and Seidel H.-P. Robust pose estimation with 3D tex-tured models. In IEEE Pacific-Rim Symposium on Image and Video Technology (PSIVT), LNCS 4319, pp. 84-95. Springer, 2006.
Geman S. and Geman D. Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6(6):721-741, 1984.
Gidas B. Topics in Contemporary Probability and Its Applications, Chapter 7: Metropolis-type Monte Carlo simulation algorithms and simulated annealing, pp. 159-232. Probability and Stochastics Series. CRC Press, Boca Raton, 1995.
Goldstein H. Classical Mechanics. Addison-Wesley, Reading, MA, second edi-tion, 1980.
Grest D., Herzog D., and Koch R. Human Model Fitting from Monocular Posture Images. In G. Greiner, J. Hornegger, H. Niemann, and M. Stamminger, editors, Vision, modelling and Visualization. Akademische Verlagsgesellschaft Aka, 2005.
Kirkpatrick S., Gelatt C. Jr. and Vecchi M. Optimization by simulated anneal- ing. Science, 220(4598):671-680, 1983.
DelMoral P. Feynman-Kac Formulae. Genealogical and Interacting Particle Systems with Applications. Probability and its Applications. Springer, New York, 2004.
Murray R.M., Li Z., and Sastry S.S. Mathematical Introduction to Robotic Manipulation. CRC Press, Baton Rouge, 1994.
Parzen E. On estimation of a probability density function and mode. Annals of Mathematical Statistics, 33:1065-1076, 1962.
Pennec X. and Ayache N. Uniform distribution, distance and expectation prob-lems for geometric features processing. Journal of Mathematical Imaging and Vision, 9(1):49-67, 1998.
Pennec X. Computing the mean of geometric features: Application to the mean rotation. Rapport de Recherche RR-3371, INRIA, Sophia Antipolis, France, March 1998.
Pennec X. Intrinsic statistics on Riemannian manifolds: basic tools for geometric measurements. Journal of Mathematical Imaging and Vision, 25(1):127-154, 2006.
Rosenhahn B., Brox T., Cremers D., and Seidel H.-P. A comparison of shape matching methods for contour based pose estimation. In R. Reulke, U. Eckhardt, B. Flach, U. Knauer, and K. Polthier, editors, 11th International Workshop on Combinatorial Image Analysis (IWCIA), LNCS 4040, pp. 263-276. Springer, 2006.
Rosenhahn B., Brox T., Kersting U., Smith A., Gurney J., and Klette R. A sys-tem for marker-less human motion estimation. Künstliche Intelligenz, 1:45-51, 2006.
Rosenhahn B., Brox T., and Weickert J. Three-dimensional shape knowledge for joint image segmentation and pose tracking. In International Journal of Computer Vision, 2006, To appear.
Rosenhahn B., Perwass C., and Sommer G. Pose Estimation of Free-form Con-tours. International Journal of Computer Vision, 62(3):267-289, 2005.
Rosenblatt F. Remarks on some nonparametric estimates of a density function. Annals of Mathematical Statistics, 27(3):832-837, 1956.
Szu H. and Hartley R. Fast simulated annealing. Physic Letter A, 122:157-162, 1987.
Theobalt C., Magnor M., Schueler P., and Seidel H.-P. Combining 2D fea-ture tracking and volume reconstruction for online video-based human motion capture. In 10th Pacific Conference on Computer Graphics and Applications, pp. 96-103. IEEE Computer Society, 2002.
Tsallis C. and Stariolo D.A. Generalized simulated annealing. Physica A, 233:395-406, 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer
About this chapter
Cite this chapter
Gall, J., Rosenhahn, B., Seidel, HP. (2008). An Introduction to Interacting Simulated Annealing. In: Rosenhahn, B., Klette, R., Metaxas, D. (eds) Human Motion. Computational Imaging and Vision, vol 36. Springer, Dordrecht. https://doi.org/10.1007/978-1-4020-6693-1_13
Download citation
DOI: https://doi.org/10.1007/978-1-4020-6693-1_13
Publisher Name: Springer, Dordrecht
Print ISBN: 978-1-4020-6692-4
Online ISBN: 978-1-4020-6693-1
eBook Packages: Computer ScienceComputer Science (R0)