Abstract
Getting trapped in suboptimal local minima is a perennial problem in model based vision, especially in applications like monocular human body tracking where complex nonlinear parametric models are repeatedly fitted to ambiguous image data. We show that the trapping problem can be attacked by building ‘roadmaps’ of nearby minima linked by transition pathways — paths leading over low ‘cols’ or ‘passes’ in the cost surface, found by locating the transition state (codimension-1 saddle point) at the top of the pass and then sliding downhill to the next minimum. We know of no previous vision or optimization work on numerical methods for locating transition states, but such methods do exist in computational chemistry, where transitions are critical for predicting reaction parameters. We present two families of methods, originally derived in chemistry, but here generalized, clarified and adapted to the needs of model based vision: eigenvector tracking is a modified form of damped Newton minimization, while hypersurface sweeping sweeps a moving hypersurface through the space, tracking minima within it. Experiments on the challenging problem of estimating 3D human pose from monocular images show that our algorithms find nearby transition states and minima very efficiently, but also underline the disturbingly large number of minima that exist in this and similar model based vision problems.
Chapter PDF
Similar content being viewed by others
References
Y. Abashkin and N. Russo. Transition State Structures and Reaction Profiles from Constrained Optimization Procedure. Implementation in the Framework of Density Functional Theory. J. Chem. Phys., 1994.
Y. Abashkin, N. Russo, and M. Toscano. Transition States and Energy Barriers from Density Functional Studies: Representative Isomerization Reactions. International Journal of Quantum Chemistry, 1994.
G. T. Barkema. Event-Based Relaxation of Continuous Disordered Systems. Physical Review Letters, 77(21), 1996.
A. Barr. Global and Local Deformations of Solid Primitives. Computer Graphics, 18:21–30, 1984.
J. M. Bofill. Updated Hessian Matrix and the Restricted Step Method for Locating Transition Structures. Journal of Computational Chemistry, 15(1):1–11, 1994.
C. J. Cerjan and W. H. Miller. On Finding Transition States. J. Chem. Phys., 75(6), 1981.
T. Cham and J. Rehg. A Multiple Hypothesis Approach to Figure Tracking. In CVPR, volume 2, pages 239–245, 1999.
A. Chiusso, R. Brockett, and S. Soatto. Optimal structure from motion: Local ambiguities and global estimates. IJCV, 39(3):195–228, 2000.
K. Choo and D. Fleet. People Tracking Using Hybrid Monte Carlo Filtering. In ICCV, 2001.
G. M. Crippen and H. A. Scheraga. Minimization of Polypeptide Energy. XI. The Method of Gentlest Ascent. Archives of Biochemistry and Biophysics, 144:462–466, 1971.
P. Culot, G. Dive, V. H. Nguyen, and J. M. Ghuysen. A Quasi-Newton Algorithm for First-Order Saddle Point Location. Theoretica Chimica Acta, 82:189–205, 1992.
J. Deutscher, A. Blake, and I. Reid. Articulated Body Motion Capture by Annealed Particle Filtering. In CVPR, 2000.
R. Fletcher. Practical Methods of Optimization. In John Wiley, 1987.
D. Gavrila and L. Davis. 3-D Model Based Tracking of Humans in Action:A Multiview Approach. In CVPR, pages 73–80, 1996.
T. Helgaker. Transition-State Optimizations by Trust-Region Image Minimization. Chemical Physics Letters, 182(5), 1991.
G. Henkelman and H. Jonsson. A Dimer Method for Finding Saddle Points on High Dimensional Potential Surfaces Using Only First Derivatives. J. Chem. Phys., 111(15):7011–7022, 1999.
R. L. Hilderbrandt. Application of Newton-Raphson Optimization Techniques in Molecular Mechanics Calculations. Computers & Chemistry, 1:179–186, 1977.
F. Jensen. Locating Transition Structures by Mode Following: A Comparison of Six Methods on the Ar8 Lennard-Jones potential. J. Chem. Phys., 102(17):6706–6718, 1995.
P. Jorgensen, H. J. A. Jensen, and T. Helgaker. A Gradient Extremal Walking Algorithm. Theoretica Chimica Acta, 73:55–65, 1988.
J. MacCormick and M. Isard. Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracker. In ECCV, volume 2, pages 3–19, 2000.
D. Morris and J. Rehg. Singularity Analysis for Articulated Object Tracking. In CVPR, pages 289–296, 1998.
N. Mousseau and G. T. Berkema. Traveling Through Potential Energy Lanscapes of Desordered Materials: The Activation-Relaxation Technique. Physical Review E, 57(2), 1998.
L. J. Munro and D. J. Wales. Defect Migration in Crystalline Silicon. Physical Review B, 59(6):3969–3980, 1999.
J. Nichols, H. Taylor, P. Schmidt, and J. Simons. Walking on Potential Energy Surfaces. J. Chem. Phys., 92(1), 1990.
J. Oliensis. The Error Surface for Structure from Motion. Technical report, NECI, 2001.
R. Plankers and P. Fua. Articulated Soft Objects for Video-Based Body Modeling. In ICCV, pages 394–401, 2001.
J. Rehg and T. Kanade. Model-Based Tracking of Self Occluding Articulated Objects. In ICCV, pages 612–617, 1995.
R. Rosales and S. Sclaroff. Inferring Body Pose without Tracking Body Parts. In CVPR, pages 721–727, 2000.
E. M. Sevick, A. T. Bell, and D. N. Theodorou. A Chain of States Method for Investigating Infrequent Event Processes Occuring in Multistate, Multidimensional Systems. J. Chem. Phys., 98(4), 1993.
H. Sidenbladh, M. Black, and D. Fleet. Stochastic Tracking of 3D Human Figures Using 2D Image Motion. In ECCV, 2000.
J. Simons, P. Jorgensen, H. Taylor, and J. Ozmen. Walking on Potential Energy Surfaces. J. Phys. Chem., 87:2745–2753, 1983.
C. Sminchisescu. Consistency and Coupling in Human Model Likelihoods. In CFGR, 2002.
C. Sminchisescu and B. Triggs. A Robust Multiple Hypothesis Approach to Monocular Human Motion Tracking. Technical Report RR-4208, INRIA, 2001.
C. Sminchisescu and B. Triggs. Covariance-Scaled Sampling for Monocular 3D Body Tracking. In CVPR, 2001.
C. Sminchisescu and B. Triggs. Hyperdynamics Importance Sampling. In ECCV, 2002.
J. Q. Sun and K. Ruedenberg. Gradient Extremals and Stepest Descend Lines on Potential Energy Surfaces. J. Chem. Phys., 98(12), 1993.
B. Triggs, P. McLauchlan, R. Hartley, and A. Fitzgibbon. Bundle Adjustment-A Modern Synthesis. In Springer-Verlag, editor, Vision Algorithms: Theory and Practice, 2000.
S. Wachter and H. Nagel. Tracking Persons in Monocular Image Sequences. CVIU, 74(3):174–192, 1999.
D. J. Wales. Finding Sadle Points for Clusters. J. Chem. Phys., 91(11), 1989.
D. J. Wales and T. R. Walsh. Theoretical Study of the Water Pentamer. J. Chem. Phys., 105(16), 1996.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sminchisescu, C., Triggs, B. (2002). Building Roadmaps of Local Minima of Visual Models. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds) Computer Vision — ECCV 2002. ECCV 2002. Lecture Notes in Computer Science, vol 2350. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-47969-4_38
Download citation
DOI: https://doi.org/10.1007/3-540-47969-4_38
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43745-1
Online ISBN: 978-3-540-47969-7
eBook Packages: Springer Book Archive