Patent
1994-01-18
1996-04-23
Nguyen, Phu K.
G06F 1500
Patent
active
055111530
ABSTRACT:
A method and apparatus for generating three-dimensional, textured computer models from a series of video images of an object is disclosed. The invention operates by tracking a selected group of object features through a series of image frames and, based on changes in their relative positions, estimates parameters specifying camera focal length, translation and rotation, and the positions of the tracked features in the camera reference frame. After segmentation of the images into two-dimensional bounded regions that each correspond to a discrete surface component of the actual object, the texture contained in the various video frames is applied to these regions to produce a final three-dimensional model that is both geometrically and photometrically specified.
REFERENCES:
patent: 5214753 (1993-05-01), Lee et al.
patent: 5255352 (1993-10-01), Faulk
patent: 5257346 (1993-10-01), Hanson
patent: 5325470 (1994-06-01), Sumino et al.
patent: 5363476 (1994-11-01), Kurashige et al.
patent: 5369736 (1994-11-01), Kato et al.
Ayache et al., "Maintaining Representations of The Environment Of A Mobile Robot," 5 IEEE Trans. Robotics Automation 804 (1989).
Broida et al., "Recursive Estimation Of 3-D Motion From A Monocular Image Sequence," 26 IEEE Trans. Aerosp. Electron. Syst. 639 (1990).
Broida et al., "Estimation Of Object Motion Parameters From Noisy Images," 8 IEEE Trans. Pattern Analysis And Machine Intelligence 90 (1986).
Dickmanns et al., "Dynamic Monocular Machine Vision," 1 Machine Vision And Applications 223 (1988).
Faugeras et al., "Building Visual Maps By Combining Noisy Stereo Measurements," IEEE Conf. On Robotics And Automation 1433 (Apr. 1986).
Heel, "Temporally Integrated Surface Reconstruction," in ICCV '90 (1990).
Kumar et al., "A Non-Linear Optimization Algorithm For The Estimation Of Structure And Motion Parameters," IEEE Conf. On Computer Vision And Pattern Recognition 136 (Jun. 1989).
Longuet-Higgens, "A Computer Algorithm For Reconstructing A Scene From Two Projections," 293 Nature 61 (1981).
Matthies et al., "Kalman Filter-Based Algorithms For Estimating Depth From Image Sequences" 3 International Journal Of Computer Vision 209 (1989).
Poelman et al., "A Paraperspective Factorization Method For Shape And Motion Recovery," CMU-CS-92-208, School Of Computer Science (Oct. 1992).
Soatta et al., "Recursive Motion And Structure Estimation With Complete Error Characterization," IEEE Conference On Computer Vision And Pattern Recognition 428 (Jun. 1993).
Szeliski et al., "Recovering 3D Shape And Motion From Image Streams Using Non-Linear Least Squares," IEEE Conference On Computer Vision And Pattern Recognition 752 (Jun. 1993).
Excerpt from Brown, Introduction To Random Signal Analysis And Kalman Filtering (1983).
Excerpt from Gelb, ed., Applied Optimal Estimation (1974).
Horn, "Relative Orientation," 4 International Journal Of Computer Vision 59 (1990).
Szeliski et al., "Recovering 3D Shape And Motion From Image Streams Using Non-Linear Least Squares," CRL 93/3, Digital Equipment Corporation (Mar. 1993).
Weng et al., "Optimal Motion and Structure Estimation," 15 IEEE Trans. Pattern Analysis And Machine Intelligence 864 (1993).
Young et al., "3-D Motion Estimation Using A Sequence Of Noisy Stereo Images: Models, Estimation, and Uniqueness Results," 12 IEEE Trans. Pattern Analysis And Machine Intelligence 735 (1990).
Oliensis et al., "Incorporating Motion Error In Multi-Frame Structure From Motion," IEEE Workshop On Visual Motion 8 (Oct. 1991).
Sull et al, Segmentation, Matching and Estimation of Structure and Motion of Textured Piecewise Planar Surfaces, Visual Motion, 1991, IEEE Workshop, pp. 274-279.
Foley et al, "Computer Graphics: Principles and Practices," Addison-Wesley Publishing Co. (1990), pp. 230-241.
Duffy, N. D., "Computer Reconstruction of 2-D Photographs from Alternative Viewpoints," IEEE Colloq. (1990), No. 087: Electronic Images and Image Processing, pp. 1-4.
Kumar et al, "A Nonlinear Optimization Algorithm for the Estimation of Structure and Motion," Computer Vision and Pattern Recognition, 1989 (CVPR), pp. 136-143.
Ando, Hiroshi, "Dynamic Reconstruction of 3D Structure and 3D Motion," Visual Motion, IEEE Workshop, (1991), pp. 101-110.
Lee, Chi-Yin et al., "Structure from Motion: A Region Based Approach Using Affine Transformations and Movement Invariant," Robotics and Automation, 1993 IEEE International Conference, pp. 120-127.
Oliensis, J., et al, "Incorporating Motion Error in Multi-Frame Structure from Motion," IEEE Visual Workshop, 1991, pp. 8-13.
Tsai, Roger et al, "Uniqueness and Estimation of Three-Dimensional Motion Parameters of Rigid Objects with Curved Surfaces," Pattern Analysis and Machine Intelligence, vol. PAMI-6, No. 1, Jan. 1984, pp. 337-351.
Taylor, Camillo et al, "Structure and Motion In Two Dimensions from Multiple Images: A Least Squares Approach," Visual Motion, IEEE Workshop, 1991, pp. 242-248.
Wang, Han et al, "A Structure-from-motion Algorithm for Robot Vehicle Guidance", Intelligent Vehicles, 1992 Symposium Proceedings, pp. 30-35.
Azarbayejani Ali
Galyean Tinsley
Pentland Alex
Massachusetts Institute of Technology
Nguyen Phu K.
LandOfFree
Method and apparatus for three-dimensional, textured models from 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 and apparatus for three-dimensional, textured models from, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for three-dimensional, textured models from will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2315729