Cited By
View all- Traver VPla F(2008)Motion Analysis with the Radon Transform on Log-Polar ImagesJournal of Mathematical Imaging and Vision10.1007/s10851-007-0046-130:2(147-165)Online publication date: 1-Feb-2008
Integration of Geometric Elements, Euclidean Relations, and Motion Curves for Parametric Shape and Motion Estimation
Pages 1960 - 1976
Abstract
This paper presents an approach to shape and motion estimation that integrates heterogeneous knowledge into a unique model-based framework. We describe the observed scenes in terms of structured geometric elements (points, line segments, rectangles, 3D corners) sharing explicitly Euclidean relationships (orthogonality, parallelism, colinearity, coplanarity). Camera trajectories are represented with adaptative models which account for the regularity of usual camera motions.Two different strategies of automatic model building lead us to reduced models for shape and motion estimation with a minimal number of parameters. These models increase the robustness to noise and occlusions, improve the reconstruction, and provide a high-level representation of the observed scene. The parameters are optimally computed within a sequential Bayesian estimation procedure that gives accurate and reliable results on synthetic and real video imagery.
References
[1]
A.V. Aho, J.E. Hopcroft, and J.D. Ullman, Data Structures and Algorithms. Addison-Wesley, 1983.
[2]
K. Astrom and F. Kahl, “Motion Estimation in Image Sequences Using the Deformation of Apparent Contours,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 2, pp. 114-127, Feb. 1999.
[3]
P. Balbiani, V. Dugat, L.F. nas del Cerro, and A. Lopez, Elements de Geometrie Mecanique. Hermes, 1994.
[4]
P.L. Bazin, “A Parametric Scene Reduction Algorithm from Geometric Relations,” SPIE 45th Ann. Proc. Vision Geometry IX, Aug. 2000.
[5]
P.L. Bazin and J.M. Vézien, “Tracking Geometric Primitives in Video Streams,” Proc. Fourth Irish Machine Vision and Image Processing Conf., pp. 43-50, Sept. 2000.
[6]
P.-L. Bazin and J.-M. Vézien, “Shape and Motion Estimation from Geometry and Motion Modeling,” IEICE Trans. Information and Systems, special issue on machine vision applications, Dec. 2001.
[7]
P.-L. Bazin and J.-M. Vézien, “Motion Curves for Parametric Shape and Motion Estimation,” Proc. Seventh European Conf. Computer Vision, May 2002.
[8]
D. Bondyfalat and S. Bougnoux, “Imposing Euclidean Constraints during Self-Calibration Process,” Proc. SMILE Workshop, pp. 224-235, June 1998.
[9]
Multidimensional System Theory. N.K. Bose, ed. D. Reidel Publishing Company, 1985.
[10]
B. Caprile and V. Torre, “Using Vanishing Points for Camera Calibration,” Int'l J. Computer Vision, vol. 4, pp. 127-140, 1990.
[11]
A. Chiuso, P. Favaro, H. Jin, and S. Soatto, “3-D Motion and Structure from 2-D Motion Causally Integrated over Time: Implementation,” Proc. European Conf. Computer Vision, June 2000.
[12]
D. Cox, J. Little, and D. O'Shea, Ideals, Varieties and Algorithms. Springer-Verlag, 1992.
[13]
P.E. Debevec, C.J. Taylor, and J. Malik, “Modeling and Rendering Architecture from Photographs: A Hybrid Geometry- and Image-Based Approach,” Proc. SIGGRAPH 96 Conf., 1996.
[14]
R. Deriche, “Using Canny's Criteria to Derive a Recursively Implemented Optimal Edge Detector,” Int'l J. Computer Vision, pp. 167-187, 1987.
[15]
R. Deriche and O. Faugeras, “Tracking Line Segments,” Image and Vision Computing, vol. 8, no. 4, pp. 261-270, Nov. 1990.
[16]
A. Dick, P. Torr, and R. Cipolla, “A Bayesian Estimation of Building Shape Using MCMC,” Proc. Seventh European Conf. Computer Vision, May 2002.
[17]
S. Donikian and G. Hegron, “Constraint Management in a Declarative Design Method for 3D Scene Sketch Modeling,” Proc. First Workshop Principles and Practice of Constraint Programming, pp. 427-443, 1993.
[18]
O. Faugeras, Three-Dimensional Computer Vision, a Geometric Viewpoint. MIT Press, 1993.
[19]
A.W. Fitzgibbon and A. Zisserman, “Automatic Camera Recovery for Closed or Open Image Sequences,” Proc. European Conf. Computer Vision, pp. 311-326, June 1998.
[20]
E. Grossmann and J. Santos-Victor, “Dual Representation for Vision-Based 3D Reconstruction,” Proc. British Machine Vision Conf., Sept. 2000.
[21]
R.M. Haralick, “Propagating Covariance in Computer Vision,” Performance Characterization in Computer Vision, Kluwer Academic, 2000.
[22]
R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision. Cambridge Univ. Press, 2000.
[23]
R.I. Hartley, “Euclidian Reconstruction from Uncalibrated Views,” Proc. DARPA-ESPRIT Workshop Application of Invariants in Computer Vision, Oct. 1993.
[24]
X. Hu and N. Ahuja, “Motion and Structure Estimation Using Long Sequence Motion Models,” Image and Vision Computing, vol. 11, no. 9, pp. 549-569, Nov. 1993.
[25]
I. Infantino, R. Cipolla, and A. Chella, “Reconstruction of Architectural Scenes from Uncalibrated Photos and Maps,” Proc. IAPR Workshop Machine Vision Applications, pp. 427-430, Nov. 2000.
[26]
F. Kahl and A. Heyden, “Auto-Calibration and Euclidean Reconstruction from Continuous Motion,” Proc. Eighth Int'l Conf. Computer Vision, July 2001.
[27]
K. Kanatani, “Model Selection for Structure and Motion Recovery from Multiple Images,” Model Selection Criteria for Geometric Inference, Springer, 2000.
[28]
K. Kanatani and C. Matsunaga, “Geometric MDL and Its Media Applications,” Proc. Workshop Information-Based Induction Sciences, pp. 45-50, July 2000.
[29]
G. Kwaiter, V. Gaildrat, and R. Caubet, “Modelling with Constraints: A Bibliographical Survey,” Proc. Int'l Conf. Information Visualization, pp. 211-220, July 1998.
[30]
M. Leyton, “A Generative Theory of Shape,” Lecture Notes Computer Science, vol. 2145, 2001.
[31]
S.J. Maybank and P. Sturm, “Minimum Description Length and the Inference of Scene Structure from Images,” Proc. IEE Colloquium Applications of Statistics to Pattern Recognition, 1999.
[32]
J.M. McCarthy, Introduction to Theoretical Kinematics. MIT Press, 1990.
[33]
D.D. Morris, K. Kanatani, and T. Kanade, “Uncertainty Modeling for Optimal Structure from Motion,” Proc. Conf. Vision Algorithms: Theory and Practice, Sept. 1999.
[34]
M. Pollefeys, R. Koch, and L.V. Gool, “Self-Calibration and Metric Reconstruction in Spite of Varying and Unknown Internal Camera Parameters,” Proc. Int'l Conf. Computer Vision, pp. 90-95, 1998.
[35]
W. Press, W. Vetterling, S. Teukolsky, and B. Flannery, Numerical Recipes in C, second ed. Cambridge Univ. Press, 1993.
[36]
D. Robertson and R. Cipolla, “An Interactive System for Constraint-Based Modelling,” Proc. British Machine Vision Conf., pp. 536-545, 2000.
[37]
D. Robertson and R. Cipolla, “Building Architectural Models from Many Views Using Map Constraints,” Proc. Seventh European Conf. Computer Vision, May 2002.
[38]
C. Rother and S. Carlsson, “Linear Multi View Reconstruction and Camera Recovery Using a Reference Plane,” Int'l J. Computer Vision, vol. 49, no. 2, pp. 117-141, 2002.
[39]
G. Sparr, “Euclidean and Affine Structure/Motion for Uncalibrated Cameras from Affine Shape and Subsidiary Information,” Proc. SMILE Workshop, pp. 187-207, June 1998.
[40]
P. Torr, “Bayesian Model Estimation and Selection for Epipolar Geometry and Generic Manifold Fitting,” Int'l J. Computer Vision, vol. 50, no. 1, 2000.
[41]
P.H.S. Torr, “Model Selection for Structure and Motion Recovery from Multiple Images,” Data Segmentation and Model Selection for Computer Vision, Springer, 2000.
[42]
B. Triggs, P. McLauchlan, R. Hartley, and A. Fitzgibbon, “Bundle Adjustment— A Modern Synthesis,” Proc. Conf. Vision Algorithms: Theory and Practice, Sept. 1999.
Index Terms
- Integration of Geometric Elements, Euclidean Relations, and Motion Curves for Parametric Shape and Motion Estimation
Recommendations
Motion Curves for Parametric Shape and Motion Estimation
ECCV '02: Proceedings of the 7th European Conference on Computer Vision-Part IIThis paper presents a novel approach to camera motion parametrization for the structure and motion problem. In a model-based framework, the hypothesis of (relatively) continuous and smooth sensor motion enables to reformulate the motion recovery problem ...
Model-based estimation of 3D human motion with occlusion based on active multi-viewpoint selection
CVPR '96: Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)Dept. of Comput. & Inf. Sci., Pennsylvania Univ., Philadelphia, PA, USA Abstract: We present a new method for the 3D model-based tracking of human body parts. To mitigate the difficulties arising due to occlusion among body parts, we employ multiple ...
Integration of Motion Fields through Shape
CVPR '05: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02Structure from motion from single flow fields has been studied intensively, but the integration of information from multiple flow field has not received much attention. Here we address this problem by enforcing constraints on the shape (surface normals) ...
Comments
Information & Contributors
Information
Published In
Copyright © 2005.
Publisher
IEEE Computer Society
United States
Publication History
Published: 01 December 2005
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 25 Oct 2024
Other Metrics
Citations
Cited By
View all- Traver VPla F(2008)Motion Analysis with the Radon Transform on Log-Polar ImagesJournal of Mathematical Imaging and Vision10.1007/s10851-007-0046-130:2(147-165)Online publication date: 1-Feb-2008