| | This Article | |
| |
| |
| | Share | |
| |
| |
| | Bibliographic References | |
| |
| |
| | Add to: | |
| |
 Digg
 Furl
 Spurl
 Blink
 Simpy
 Google
 Del.icio.us
 Y!MyWeb
| |
| | Search | |
| |
| |
| | |
Statistical Cue Integration in DAG Deformable Models
July 2003 (vol. 25 no. 7)
pp. 801-813
Abstract—Deformable models are a useful modeling paradigm in computer vision. A deformable model is a curve, a surface, or a volume, whose shape, position, and orientation are controlled through a set of parameters. They can represent manufactured objects, human faces and skeletons, and even bodies of fluid. With low-level computer vision and image processing techniques, such as optical flow, we extract relevant information from images. Then, we use this information to change the parameters of the model iteratively until we find a good approximation of the object in the images. When we have multiple computer vision algorithms providing distinct sources of information (cues), we have to deal with the difficult problem of combining these, sometimes conflicting contributions in a sensible way. In this paper, we introduce the use of a directed acyclic graph (dag) to describe the position and Jacobian of each point of deformable models. This representation is dynamic, flexible, and allows computational optimizations that would be difficult to do otherwise. We then describe a new method for statistical cue integration method for tracking deformable models that scales well with the dimension of the parameter space. We use affine forms and affine arithmetic to represent and propagate the cues and their regions of confidence. We show that we can apply the Lindeberg theorem to approximate each cue with a Gaussian distribution, and can use a maximum-likelihood estimator to integrate them. Finally, we demonstrate the technique at work in a 3D deformable face tracking system on monocular image sequences with thousands of frames.
[1] 801 K. Arras, An Introduction to Error Propagation: Derivation, Meaning, and Examples of Equation cy = fx cx fx Technical Report EPFL-ASL-TR-98-01 R3, EPFL, 1998.[2] J.L. Barron, D.J. Fleet, and S.S. Beauchemin, “Performance of Optical Flow Techniques,” Int'l J. Computer Vision, vol. 12, no. 1, pp. 43–77, 1994.[3] M.J. Black and Y. Yacoob, “Recognizing Facial Expressions in Image Sequences Using Local Parameterized Models of Image Motion,” Int'l J. Computer Vision, vol. 25, no. 1, pp. 23-48, Oct. 1997.[4] A. Blake and M. Isard, Active Contours: The Application of Techniques from Graphics, Vision, Control Theory and Statistics to Visual Tracking of Shapes in Motion. Springer Verlag, 1999.[5] V. Blanz and T. Vetter, "A Morphable Model for the Synthesis of 3D Faces," Proc. Siggraph 99, ACM Press, 1999, pp. 187-194.[6] M. Brand and R. Bhotika, Flexible Flow for 3D Nonrigid Tracking and Shape Recovery Proc. Computer Vision and Pattern Recognition, pp. 315-322, 2001.[7] C. Bräutigam, A Model-Free Voting Approach to Cue Integration PhD thesis, Dept. of Numerical Analysis and Computing Science, KTH (Royal Institute of Technology), 1998.[8] J. Canny, “A Computational Approach to Edge Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, no. 6, pp. 679-698, June 1986.[9] M. La Cascia, S. Sclaroff, and V. Athitsos, “Fast, Reliable Head Tracking under Varying Illumination: An Approach Based on Registration of Texture Mapped 3D Models,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 4, pp. 322-336, Apr. 2000.[10] K.L. Chung, A Course in Probability Theory, second ed. Academic Press, Inc., 1974.[11] T.F. Cootes, C.J. Taylor, D.H. Cooper, and J. Graham, "Active Shape Models—Their Training and Application," Computer Vision and Image Understanding, vol. 61, no. 1, pp. 38-59, Jan. 1995.[12] J. Craig, Introduction to Robotics: Mechanics and Control, Addison Wesley Longman, Reading, Mass., 1986.[13] L. de Figueiredo, Surface Intersection Using Affine Arithmetic Graphics Interface, pp. 168-175, 1996.[14] D. DeCarlo and D. Metaxas, Optical Flow Constraints on Deformable Models with Applications to Face Tracking Int'l J. Computer Vision, vol. 38, no. 2, pp. 99-127, July 2000.[15] D. DeCarlo, D. Metaxas, and M. Stone, "An Anthropometric Face Model Using Variational Techniques," to be published in Proc. Siggraph 98, ACM Press, New York, 1998.[16] L. Egiziano, N. Femia, and G. Spagnuolo, New Approaches to the True Worst-Case Evaluation in Circuit Tolerance&Sensitivity Analysis: Part II Calculation of the Outer Solution Using Affine Arithmetic Proc. Sixth Workshop Computer in Power Electronics (COMPEL), 1998.[17] W. Feller, An Introduction to Probability Theory and Its Applications, vol. II. John Willey&Sons, 1971.[18] J.D. Foley et al., Computer Graphics: Principles and Practice, Second Edition in C, Addison-Wesley, Reading, Mass., 1995.[19] M. Gleicher and A. Witkin, Supperting Numerical Computations in Interactive Contexts Graphics Interface, pp. 138-145, 1993.[20] S. Goldenstein, Statistical Cue Estimation for Model-Based Shape and Motion Tracking PhD thesis, Univ. of Pennsylvania, 2002.[21] S. Goldenstein, C. Vogler, and D. Metaxas, Affine Arithmetic Based Estimation of Cue Distributions in Deformable Model Tracking Proc. Computer Vision and Pattern Recognition, pp. 1098-1105, 2001.[22] J. Gomes, L. Darsa, B. Costa, and L. Velho, Warping&Morphing of Graphical Objects. Morgan Kaufman, 1998.[23] N. Gordon, D. Salmond, and A. Smith, “Novel Approach to Nonlinear/Non-Gaussian Bayesian State Estimation,” IEE Proc. F, vol. 140, no. 2, pp. 107-113, 1993.[24] D. Heckerman, A Tutorial on Learning with Bayesian Networks Technical Report MSR-TR-95-06, Microsoft Research 1995.[25] R. Ierusalimschy, L.H. de Figueiredo, and W. Celes, Lua An Extensible Extension Language Software: Practice&Experience, vol. 26, no. 6, pp. 635-652, 1996.[26] M. Isard and A. Blake, “Condensation-Conditional Density Propagation for Visual Tracking,” Int'l J. Computer Vision, vol. 29, pp. 5-28, 1998.[27] G. Kamberova and M. Mintz, Minimax Rules under Zero-One Loss for a Restricted Location Parameter J. Statistical Planning and Inference, vol. 2, no. 79, pp. 205-221, 1999.[28] M. Kass, A. Witkin, and D. Terzopoulos, Snakes: Active Contour Models Int'l J. Computer Vision, vol. 1, pp. 321-331, 1988.[29] R. Mandelbaum, G. Kamberova, and M. Mintz, Stereo Depth Estimation: A Confidence Interval Approach Proc. Int'l Conf. Computer Vision, 1998.[30] P. Maybeck, Stochastic Models, Estimation, and Control. Academic Press, 1979.[31] F. Messine and A. Mahfoudi, Use of Affine Arithmetic in Interval Optimization Algorithms to Solve Multidimensional Scaling Problems Proc. IMACS/GAMM Int'l Symp. Scientific Computing, Computer Arithmetic and Validated Numerics, 1998.[32] R. Moore, Methods and Applications of Interval Analysis. SIAM, 1979.[33] H. Murase and S.K. Nayar, “Visual Learning and Recognition of 3-D Objects from Appearance,” Int'l J. Computer Vision, vol. 14, pp. 5-24, 1995.[34] F. Pighin, R. Szeliski, and D. Salesin, Resynthesizing Facial Animation through 3D Model-Based Tracking Proc. Int'l Conf. Computer Vision, pp. 143-150, 1999.[35] A.A.G. Requicha,“Representations for rigid solids: Theory, methods, and systems,” ACM Computing Surveys, vol. 12, no. 4, pp. 437-464, 1980.[36] D. Samaras, D. Metaxas, P. Fua, and Y.G. Leclerc, Variable Albedo Surface Reconstruction from Stereo and Shape from Shading Proc. Computer Vision and Pattern Recognition, pp. 480-487, 2000.[37] J. Shi and C. Tomasi, Good Features to Track Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 593-600, 1994.[38] J. Stolfi and L. Figueiredo, Self-Validated Numerical Methods and Applications Proc. 21st Colóoquio Brasileiro de Matemática, (21st Brazilian Mathematics Colloquium) IMPA, 1997.[39] C. Tomasi and T. Kanade, Detection and Tracking of Point Features Technical Report CMU-CS-91-132, School of Computer Science, Carnegie Mellon Univ., 1991.
Index Terms:
Statistical cue integration, deformable model tracking, affine arithmetic, face tracking, directed acyclic graphs, deformable model representation.
Citation:
Siome Klein Goldenstein, Christian Vogler, Dimitris Metaxas, "Statistical Cue Integration in DAG Deformable Models," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 7, pp. 801-813, July 2003, doi:10.1109/TPAMI.2003.1206510
Usage of this product signifies your acceptance of the
Terms of Use.
|
|
|
|
|
|
|
|
