research-article

Image Description and 3-D Reconstruction From Image Trajectories of Rotational Motion

Authors:

A. R. HansonAuthors Info & Claims

IEEE Transactions on Pattern Analysis and Machine Intelligence, Volume 15, Issue 9

Pages 885 - 898

https://doi.org/10.1109/34.232075

Published: 01 September 1993 Publication History

Abstract

A new technique for reconstructing the 3-D structure and motion of a scene undergoing relative rotational motion with respect to the camera is discussed. Given image correspondences of point features tracked over many frames, a two-stage technique for reconstruction is presented. A grouping algorithm that exploits spatio-temporal constraints of the common motion to achieve a reliable description of discrete point correspondences as curved trajectories in the image plane is developed. In contrast, trajectories fitted to points independent of each other lead to arbitrary image descriptions and very inaccurate 3-D parameters. A new closed-form solution, under perspective projection, for the 3-D motion and location of points from the computed image trajectories is also presented. Both stages are applied to real image sequences with good results. This approach represents a first step in a longer-term research effort examining the role of explicit spatio-temporal organization in the interpretation of scenes from dynamic images.

References

[1]

{1} G. Adiv, "Determining 3-D motion and structure from optical flows generated by several moving objects," IEEE Trans. Pattern Anal. Machine Intell., vol. 7, no. 4, pp. 384-401, 1985.

Digital Library

[2]

{2} G. Adiv, "Interpreting optical flow," Ph.D. thesis, Univ. Massachusetts, Amherst, MA, 1985.

[3]

{3} G. Adiv, "Inherent ambiguities in recovering 3-D information from a noisy flow field," IEEE Trans. Patt. Anal. Machine Intell., vol. 11, no. 5, pp. 477-489, 1989.

Digital Library

[4]

{4} J. K. Aggarwal and N. Nandhakumar, "On the computation of motion from sequence of images--Review," Tech. Rep. TR-88-2-47, Univ. Texas, Austin, 1988.

[5]

{5} P. Anandan, "A computational framework and an algorithm for the measurement of visual motion," Int. J. Comput. Vision, vol. 2, no. 3, pp. 283-310, 1989.

[6]

{6} M. Boldt, R. Weiss, and E. Riseman, "Token-based extraction of straight lines," IEEE Trans. Syst. Man Cybern., vol. 19, no. 6, pp. 1581-1594, 1989.

[7]

{7} F. L. Bookstein, "Fitting conic sections to scattered data," Comput. Graphics Image Processing, vol. 9, pp. 56-71, 1979.

[8]

{8} T. J. Broida and R. Chellappa, "Experiments and uniqueness results on object structure and kinematics from a sequence of monocular images," in Proc. IEEE Workshop Visual Motion, 1989, pp. 21-30.

[9]

{9} D. S. Chen, "A data-driven intermediate level feature extraction algorithm," IEEE Trans. Patt. Anal. Machine Intell., vol. 11, no. 7, pp. 749-758, 1989.

Digital Library

[10]

{10} R. T. Collins and R. Weiss, "An efficient and accurate method for computing vanishing points," in Proc. Topical Mtg. Opt. Soc. Amer. Image Understanding, 1989, pp. 92-94.

[11]

{11} K. Daniilidis and H. H. Nagel, "Analytical results on error sensitivity of motion estimation from two views," in Proc. 1st Euro. Conf. Comput. Vision, 1990, pp. 199-208.

Digital Library

[12]

{12} O. D. Faugeras, F. Lustman, and G. Toscani, "Motion and structure from motion from point and line matches," in IEEE First Int. Conf. Comput. Vision, 1987, pp. 25-34.

[13]

{13} D. Forsyth, J. L. Mundy, A. Zisserman, and C. M. Brown, "Projectively invariant representations using implicit aglebraic curves," in Proc. 1st Euro. Conf. Comput. Vision, 1990, pp. 427-436.

Digital Library

[14]

{14} B. K. P. Horn, "Relative orientation," Int. J. Comput. Vision, vol. 4, no. 1, pp. 59-78, 1990.

Digital Library

[15]

{15} R. A. Jaenicke, "Structure from limited motion of complex objects," in Proc. IEEE Workshop Visual Motion, 1989, pp. 256-263.

[16]

{16} R. Kumar and A. Hanson, "Robust determination of camera location and orientation," in Proc. IEEE Workshop Interpretation 3-D Scenes, 1989, pp. 52-60.

[17]

{17} R. Kumar and A. Hanson, "Sensitivity of the pose refinement problem to accurate estimation of camera parameters," in Proc. 3nd Int. Conf. Comput. Vision, 1990, pp. 365-369.

[18]

{18} Y. G. Leclerc, "Constructing simple stable descriptions for image partitioning," Int. J. Comput. Vision, vol. 3, no. 1, pp. 73-102, 1989.

[19]

{19} R. K. Lenz and R. Y. Tsai, "Tecniques for calibration of the scale factor and image center for high accuracy 3D machine vision metrology," IEEE Trans. Patt. Anal. Machine Intell., vol. 10, no. 5, pp. 713-719, 1988.

Digital Library

[20]

{20} D. H. Marimont, "Inferring spatial structure from feature correspondence," Ph.D. thesis, Stanford Univ., Stanford, CA, 1986.

Digital Library

[21]

{21} J. Porrill, "Fitting ellipses and predicting confidence envelopes using a bias corrected Kalman filter," Image Vision Comput., vol. 8, pp. 37-41, 1990.

Digital Library

[22]

{22} K. S. Roberts, "A new representation for a line," In Proc. Comput. Vision Patt. Recogn. Conf., 1988, pp. 635-640.

[23]

{23} P. D. Sampson, "Fitting conic sections to very scattered date," Comput. Graphics Image Processing, 1982, pp. 97-108.

[24]

{24} H. S. Sawhney and J. Oliensis, "Description and interpretation of rotational motion from images trajectories," Tech. Rep. COINS TR 89-90, Univ. Mass., Amherst, MA, 1989.

Digital Library

[25]

{25} H. Shariat, "The motion problem: How to use more than two frames," Ph.D. thesis, Univ. of Southern California, Los Angeles, 1986.

[26]

{26} M. E. Spetsakis and J. Aloimonos, "Optimal computing of structure from motion using point correspondences in two frames," in Proc. 2nd Int. Conf. Comput. Vision, 1988, pp. 449-453.

[27]

{27} K. A. Stevens, "Computation of locally parallel structure," Biolog. Cybern., vol. 29, pp. 19-28, 1978.

Digital Library

[28]

{28} J. Todd, "Visual information about rigid and non-rigid motion: A geometric analysis," J. Experimental Psychol.: Human Perception Performance , vol. 8, no. 2, pp. 238-252, 1982.

[29]

{29} R. Y. Tsai and T. S. Huang, "Uniqueness and estimation of 3D motion parameters and surface structures of rigid objects," in Image Understanding 1984 (W. Richards and S. Ullman, Eds.). New Jersey: Ablex, 1984, pp. 135-171.

[30]

{30} J. A. Webb and J. K. Aggarwal, "Structure from motion of rigid and jointed objects," Artificial Intell., vol. 19, pp. 107-130, 1982.

Digital Library

[31]

{31} J. Weng, N. Ahuja, and T. S. Huang, "Optimal motion and structure estimation," in Proc. Comput. Vision Patt. Recogn. Conf., 1989, pp. 144-152.

[32]

{32} J. Weng, T. S. Huang, and N. Ahuja, "3D motion estimation understanding and prediction from noisy image sequences," IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-9, no. 3, pp. 370-389, 1987.

Digital Library

[33]

{33} J. Weng, T. S. Huang, and N. Ahuja, "Motion and structure from two perspective views: Algorithms, error analysis, and error estimation," IEEE Trans. Patt. Anal. Machine Intell., vol. 11, no. 5, pp. 451-476, 1989.

Digital Library

[34]

{34} W. H. Press, B. P. Flannery, S. A. Teukolsky, and W. T. Vetterling, Numerical Recipes in C. Cambridge, UK: Cambridge University Press, 1986.

[35]

{35} L. R. Williams and A. R. Hanson, "Translating optical flow into token matches and depth from looming, in Proc. 2nd Int. Conf. Comput. Vision, 1988, pp. 441-448.

Cited By

Lei ZLin Y(2018)3D Shape Inferencing and Modeling for Video RetrievalJournal of Visual Communication and Image Representation10.1006/jvci.1999.041811:1(41-57)Online publication date: 26-Dec-2018
https://dl.acm.org/doi/10.1006/jvci.1999.0418
Jiang GQuan LTsui H(2004)Circular Motion Geometry Using Minimal DataIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2004.426:6(721-731)Online publication date: 1-Jun-2004
https://dl.acm.org/doi/10.1109/TPAMI.2004.4
Jiang GTsui HQuan LZisserman A(2002)Single Axis Geometry by Fitting ConicsProceedings of the 7th European Conference on Computer Vision-Part I10.5555/645315.649193(537-550)Online publication date: 28-May-2002
https://dl.acm.org/doi/10.5555/645315.649193

Image Description and 3-D Reconstruction From Image Trajectories of Rotational Motion
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
  2. Computer graphics
    1. Animation
2. Networks
  1. Network protocols

Recommendations

Rotational and translational motion estimation and selective reconstruction in digital image sequences
ICASSP '99: Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 06

This paper addresses the problem of motion estimation and selective reconstruction of objects undergoing rotational motion composed with translational motion. The goal is to derive the motion parameters belonging to the multiple moving objects, i.e. the ...
Motion and structure from multiple cues; image motion, shading flow, and stereo disparity

We investigate the recovery of 3-D motion and structure from the stereo images of a stationary environment. A Kalman filter-based framework is proposed for the reconstruction of 3-D structure from multiple visual cues, through the integration of image ...
Image Description and 3D Interpretation From Image Trajectories Under

Comments

Information & Contributors

Information

Published In

cover image IEEE Transactions on Pattern Analysis and Machine Intelligence

IEEE Transactions on Pattern Analysis and Machine Intelligence Volume 15, Issue 9

September 1993

125 pages

ISSN:0162-8828

Issue’s Table of Contents

Copyright © Copyright © 1993 IEEE. All Rights Reserved.

Publisher

IEEE Computer Society

United States

Publication History

Published: 01 September 1993

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 10 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Lei ZLin Y(2018)3D Shape Inferencing and Modeling for Video RetrievalJournal of Visual Communication and Image Representation10.1006/jvci.1999.041811:1(41-57)Online publication date: 26-Dec-2018
https://dl.acm.org/doi/10.1006/jvci.1999.0418
Jiang GQuan LTsui H(2004)Circular Motion Geometry Using Minimal DataIEEE Transactions on Pattern Analysis and Machine Intelligence10.1109/TPAMI.2004.426:6(721-731)Online publication date: 1-Jun-2004
https://dl.acm.org/doi/10.1109/TPAMI.2004.4
Jiang GTsui HQuan LZisserman A(2002)Single Axis Geometry by Fitting ConicsProceedings of the 7th European Conference on Computer Vision-Part I10.5555/645315.649193(537-550)Online publication date: 28-May-2002
https://dl.acm.org/doi/10.5555/645315.649193

View Options

View options

Media

Figures

Other

Tables

View Issue’s Table of Contents