This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Reducing "Structure From Motion": A General Framework for Dynamic Vision Part 2: Implementation and Experimental Assessment
September 1998 (vol. 20 no. 9)
pp. 943-960

Abstract—A number of methods have been proposed in the literature for estimating scene-structure and ego-motion from a sequence of images using dynamical models. Despite the fact that all methods may be derived from a "natural" dynamical model within a unified framework, from an engineering perspective there are a number of trade-offs that lead to different strategies depending upon the applications and the goals one is targeting. We want to characterize and compare the properties of each model such that the engineer may choose the one best suited to the specific application. We analyze the properties of filters derived from each dynamical model under a variety of experimental conditions, assess the accuracy of the estimates, their robustness to measurement noise, sensitivity to initial conditions and visual angle, effects of the bas-relief ambiguity and occlusions, dependence upon the number of image measurements and their sampling rate.

[1] A. Azarbayejani and A. Pentland, "Recursive Estimation of Motion, Structure and Focal Length," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 6, pp. 562-575, June 1995.
[2] J. Barron, D. Fleet, and S. Beauchemin, "Performance of Optical Flow Techniques," Int'l J. of Computer Vision, vol. 12, no. 1, pp. 43-78, 1994.
[3] J. Bergen, R. Kumar, P. Anandan, and M. Irani, "Representation of Scenes From Collections of Images," Internal Report, Sarnoff Research Center, 1995.
[4] T. Broida, S. Chandrashekhar, and R. Chellappa, "Recursive 3D Motion Estimation From a Monocular Image Sequence," IEEE Trans. Aerospace and Electronic Systems, vol. 26, no. 4, pp. 639-656, 1990
[5] T. Broida and R. Chellappa, "Estimating the Kinematics and Structure of a Rigid Object From a Sequence of Monocular Frames," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 13, no. 6, pp. 497-513, June 1991.
[6] T. Broida and R. Chellappa, "Estimation of Object Motion Parameters From Noisy Images," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, no. 1, pp. 90-99, Jan. 1986.
[7] N Cui, J. Weng, and P. Cohen, "Recursive-Batch Estimation of Motion and Structure From Monocular Image Sequences," CVGIP-IMAC, vol. 59, no. 2, pp. 156-170.
[8] C. Fermüller and Y. Aloimonos, "Tracking Facilitates 3D Motion Estimation," Biological Cybernetics, vol. 67, pp. 259-268, 1992.
[9] D.B. Gennery, "Tracking Known 3-Dimensional Object," Proc. AAAI Second Nat'l Conf. Artificial Intelligence, pp. 13-17,Pittsburg, Penn., 1982.
[10] D. Heeger and A. Jepson, "Subspace Methods for Recovering Rigid Motion I: Algorithm and Implementation," Int'l J. Computer Vision, vol. 7, no. 2, 1992.
[11] J. Heel, "Direct Estimation of Structure and Motion From Multiple Frames," AI Memo 1190, Massachusetts Institute of Technology Artificial Intelligence Lab, Mar. 1990.
[12] A.H. Jazwinski, Stochastic Processes and Filtering Theory. Academic Press, 1970.
[13] T. Kailath., Linear Systems. Prentice Hall, 1980.
[14] H.C. Longuet-Higgins, "A Computer Algorithm for Reconstructing a Scene From Two Projections," Nature, vol. 293, pp. 133-135, 1981.
[15] B.D. Lucas and T. Kanade, "An Iterative Image Registration Technique With an Application to Stereo Vision," Proc. Seventh Int'l Joint Conf. Artificial Intelligence, 1981.
[16] L. Matthies, R. Szeliski, and T. Kanade, "Kalman Filter-Based Algorithms for Estimating Depth From Image Sequences," Int'l J. Computer Vision, 1989.
[17] P. McLauchlan, I. Reid, and D. Murray, "Recursive Affine Structure and Motion From Image Sequences," Proc. Third ECCV, 1994.
[18] R.M. Murray, Z. Li, and S.S. Sastry, A Mathematical Introduction to Robotic Manipulation. CRC Press, 1994.
[19] J. Oliensis and J. Inigo-Thomas, "Recursive Multi-Frame Structure From Motion Incorporating Motion Error," Proc. DARPA Image Understanding Workshop, 1992.
[20] P. Anandan, R. Kumar, and K. Hanna, "Shape Recovery From Multiple Views: A Parallax Based Approach," Proc. Image Understanding Workshop, 1994.
[21] D. Raviv and M. Herman, "A Unified Approach to Camera Fixation and Vision-Based Road Following," IEEE Trans. Systems, Man, and Cybernetics, vol. 24, no. 8, 1994.
[22] H.S. Sawhney, "Simplifying Motion and Structure Analysis Using Planar Parallax and Image Warping," Proc. Int'l Conf. Pattern Recognition, 1994.
[23] S. Soatto, "3D Structure From Visual Motion: Modeling, Representation and Observability," Automatica, vol. 33, no. 7, pp. 1,287-1,312, 1997.
[24] S. Soatto, R. Frezza, and P. Perona, "Structure From Visual Motion as a Nonlinear Observation Problem," Proc. IFAC Symp. Nonlinear Control Systems NOLCOS,Tahoe City, June 1995.
[25] S. Soatto, R. Frezza, and P. Perona, "Motion Estimation Via Dynamic Vision," IEEE Trans. Automatic Control, vol. 41, no. 3, 1996.
[26] S. Soatto and P. Perona, "Three Dimensional Transparent Structure Segmentation and Multiple 3D Motion Estimation From Monocular Perspective Image Sequences," IEEE Workshop on Motion of Nonrigid and Articulated Objects, pages 228-235,Austin, Tex., Nov. 1994. Los Alamitos, Calif.: IEEE CS Press.
[27] S. Soatto and P. Perona, "Recursive 3D Visual Motion Estimation Using Subspace Constraints," Int'l J. Computer Vision, vol. 22, no. 3, pp. 252-259, 1996.
[28] S. Soatto and P. Perona, "Reducing "Structure From Motion": A General Framework for Dynamic Vision Part 1: Modeling," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 9, pp. 933-942, Sept. 1998.
[29] M. Spetsakis and J. Aloimonos, "A Multi-Frame Approach to Visual Motion Perception," Int'l J. Computer Vision, vol. 6, no. 3, 1991.
[30] M.A. Taalebinezhaad, "Direct Recovery of Motion and Shape in the General Case by Fixation," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, no. 8, pp. 847-853, Aug. 1992.

Index Terms:
Computer vision, structure from motion (SFM), shape estimation, recursive filter, nonlinear implicit extended Kalman filter.
Citation:
Stefano Soatto, Pietro Perona, "Reducing "Structure From Motion": A General Framework for Dynamic Vision Part 2: Implementation and Experimental Assessment," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 20, no. 9, pp. 943-960, Sept. 1998, doi:10.1109/34.713361
Usage of this product signifies your acceptance of the Terms of Use.