Image analysis – Applications – 3-d or stereo imaging analysis
Reexamination Certificate
2006-02-14
2006-02-14
Bali, Vikkram (Department: 2623)
Image analysis
Applications
3-d or stereo imaging analysis
Reexamination Certificate
active
06999612
ABSTRACT:
The present invention is directed to a method for recovering 3D scene structure and camera motion from image data obtained from a multi-image sequence, wherein a reference image of the sequence is taken by a camera at a reference perspective and one or more successive images of the sequence are taken at one or more successive different perspectives by translating and/or rotating the camera, the method comprising the steps of determining image data shifts for each successive image with respect to the reference image; constructing a shift data matrix that incorporates the image data shifts for each image, wherein a first vector corresponds to the 3D structure and a second vector corresponds to the size of the camera motion; dividing the successive images into windows; and determining the direction of camera motion and 3D structure from the first and second vector between the windows.
REFERENCES:
patent: 6614429 (2003-09-01), Zhang et al.
Aguiar et al., “Factorization as a Rank 1 Problem,” IEEE, pp. 178-184, 1999.
Wang et al., “A SVD Decomposition of Essential Matrix with Eight Solutions for the Relative Positions of Two Perspective Cameras,” IEEE, pp. 362-365, 2000.
Diamantaras et al., “Camera Motion Parameter Recovery Under Perspective Projection,” IEEE, pp. 807-810, 1996.
Kung et al., “An SVD Approach to Multi-Camera-Multi-Target 3D Motion-Shape Analysis,” IEEE, pp. 573-577, 1994.
Bergen et al., “Hierarchical Model-Based Motion Estimation,” ECCV, pp. 237-252, 1992.
Barron et al., “Systems and Experiment, Performance of Optical Flow Techniques,” International Journal of Computer Vision, pp. 43-47, 1994.
Brodsky et al., “Self-Calibration from Image Derivatives,” ICCV, pp. 83-89, 1998.
Burt et al., “The Laplacian Pyramid as a Compact Image Code,” IEEE Transactions on Communications, vol. Com. 2, No. 4, pp. 532-540, 1983.
Fermuller, “Passive Navigation as a Pattern Recognition Problem,” International Journal of Computer Vision, pp. 147-158, 1995.
Fermuller et al., “Direct Perception of Three-Dimensional Motion from Patterns of Visual Motion,” Science, vol. 270, pp. 1973-1976, 1995.
Hanna, “Direct multi-resolution estimation of ego-motion and structure from motion,” IEEE Motion Workshop, pp. 156-162, 1991.
Horn et al., “Determining Optical Flow,” Artificial Intelligence, pp. 185-203, 1981.
Irani, “Multi-Frame Optical Flow Estimation Using Subspace Constraints,” IEEE, pp. 626-633, 1999.
Irani et al., “Direct Recovery of Planar-Parallax from Multiple Frames,” Vision Algorithms—Pre-Proceedings, pp. 1-8, 1999.
Irani et al., “From Reference Frames to Reference Planes: Multi-view Parallax Geometry and Applications,” ECCV, pp. 829-845, 1998.
Irani et al., “Recovery of Ego-Motion Using Region Alignment,” IEEE, pp. 268-272, 1997.
Jepson et al., “Linear subspace methods for recovering translational direction,” in Spatial Vision in Humans and Robots, pp. 39-62, 1993.
Kumar et al., “Direct recovery of shape from multiple views: a parallax based approach,” IEEE, pp. 685-688, 1994.
Lucas et al., “An Iterative Image Registration Technique with an Application to Stereo Vision,” Proceedings of the Seventh International Joint Conference on Artificial Intelligence, vol. II, pp. 674-679, 1981.
Mandelbaum et al., “Correlation-Based Estimation of Ego-motion and Structure from Motion and Stereo,” IEEE, pp. 544-550, 1999.
Oliensis et al., “Structure from Motion using Points, Lines, and Intensities,” IEEE, pp. 599-605, 2000.
Oliensis et al., “Fast Algorithms for Projective Multi-Frame Structure from Motion,” IEEE, pp. 536-543, 1999.
Oliensis, “A Multi-Frame Structure-from-Motion Algorithm under Perspective Projection,” international Journal of Computer Vision, pp. 163-192, 1999.
Oliensis, “Multiframe Structure from Motion in Perspective,” IEEE, pp. 77-84, 1995.
Oliensis, “Structure from Linear or Planar Motions,” IEEE, pp. 335-342, 1996.
Oliensis, “A Linear Solution for Multiframe Structure from Motion,” IUW, pp. 1225-1231, 1994.
Oliensis, “Rigorous Bounds for Two-Frame Structure from Motion,” ECCV, pp. 184-195, 1995.
Sawhney, “3D Geometry From Planar Parallax,” IEEE, pp. 929-934, 1994.
Shashua et al., “Relative Affine Structure: Theory and Application to 3D Reconstruction From Perspective Views,” IEEE, pp. 483-489, 1994.
Stein et al., “Model-based Brightness Constraints: on Direct Estimation of Structure and Motion,” IEEE, pp. 400-406, 1997.
Sturm et al., “A Factorization Based Algorithm for Multi-Image Projective Structure and Motion,” ECCV, pp. 709-722, 1996.
Zelnik-Manor et al., “Multi-Frame Alignment of Planes,” IEEE, pp. 151-156, 1999.
Torr, “Geometric Motion Segmentation and Model Selection,” Phil. Trans. R. Soc. London A, pp. 1-17, 1996.
Torr, “Model Selection for Two View Geometry: A Review,” Microsoft Research paper.
Zelnik-Manor et al., “Multi-View Subspace Constraints on Homographies,” IEEE, 1999.
Kumar et al., “Shape recovery from multiple views: a parallax based approach,” David Sarnoff Research Center, pp. 947-955.
Hartley, “A linear method for reconstruction from lines and points,” GE-Corporate Research and Development.
Hanna et al., “Combining Stereo and Motion Analysis for Direct Estimation of Scene Structure,”, IEEE, pp. 357-365, 1993.
Cohen, “Dense Recovery of Planar-Parallax from Multiple Frames,” Thessi for the M.Sc. Degree of Meir Cohen, Weizmann Institute of Science, 1999.
Lucas et al., “Optical Navigation by the Method of Differences,” Computer Science Deparment of Carnegie-Mellon University.
Fermuller et al., “Global rigidity constraints in image displacement fields,” IEEE, pp. 245-250, 1995.
Bali Vikkram
NEC Laboratories America, Inc.
LandOfFree
Method for recovering 3D scene structure and camera motion... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method for recovering 3D scene structure and camera motion..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for recovering 3D scene structure and camera motion... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3643114