This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Pose and Motion Recovery from Feature Correspondences and a Digital Terrain Map
September 2006 (vol. 28 no. 9)
pp. 1404-1417
A novel algorithm for pose and motion estimation using corresponding features and a Digital Terrain Map is proposed. Using a Digital Terrain (or Digital Elevation) Map (DTM/DEM) as a global reference enables the elimination of the ambiguity present in vision-based algorithms for motion recovery. As a consequence, the absolute position and orientation of a camera can be recovered with respect to the external reference frame. In order to do this, the DTM is used to formulate a constraint between corresponding features in two consecutive frames. Explicit reconstruction of the 3D world is not required. When considering a number of feature points, the resulting constraints can be solved using nonlinear optimization in terms of position, orientation, and motion. Such a procedure requires an initial guess of these parameters, which can be obtained from dead-reckoning or any other source. The feasibility of the algorithm is established through extensive experimentation. Performance is compared with a state-of-the-art alternative algorithm, which intermediately reconstructs the 3D structure and then registers it to the DTM. A clear advantage for the novel algorithm is demonstrated in variety of scenarios.

[1] “USGS Geographic Data Download Page,” http://edc. usgs.govgeodata/, 2005.
[2] P. Anandan, K. Hanna, and R. Kumar, “Shape Recovery from Multiple Views: A Parallax Based Approach,” Proc. IEEE Int'l Conf. Pattern Recognition, vol. A, pp. 685-688, 1994.
[3] W. Baker and R. Clem, “Terrain Contour Matching [TERCOM] Primer,” Technical Report ASP-TR-77-61, Aeronautical Systems Division, Wright-Patterson AFB, Aug. 1977.
[4] J.L. Barron and R. Eagleson, “Recursive Estimation of Time-Varying Motion and Structure Parameters,” Pattern Recognition, vol. 29, no. 5, pp. 797-818, 1996.
[5] D. Boozer and J. Fellerhoff, “Terrain-Aided Navigation Test Results in the AFTI/F-16 Aircraft,” J. Inst. Navigation, vol. 35, no. 2, pp. 161-175, 1988.
[6] J.Y. Bouguet,“Pyramidal Implementation of the Lucas Kanade Feature Tracker, Description of the Algorithm,” technical report, Intel Research Lab, 1999.
[7] D. Burschka and G. Hager, “V-GPS (SLAM): Vision-Based Inertial System for Mobile Robots,” Proc. IEEE Int'l Conf. Robotics and Automation, vol. I, pp. 409-415, 2004.
[8] R. Chellappa, G. Qian, and S. Srinivasan, “Structure from Motion: Sparse versus Dense Correspondence Methods,” Proc. IEEE Int'l Conf. Image Processing, pp. 492-499, 1999.
[9] Y. Chen and G. Medioni, “Object Modelling by Registration of Multiple Range Images,” Image and Vision Computing, vol. 10, no. 3, pp. 145-155, 1992.
[10] A. Chiuso, R. Brockett, and S. Soatto, “Optimal Structure from Motion: Local Ambiguities and Global Estimates,” Int'l J. Comp. Vision, vol. 39, no. 3, pp. 195-228, 2000.
[11] A. Chiuso, P. Favaro, H. Jin, and S. Soatto, “MFM: 3-D Motion from 2-D Motion Causally Integrated over Time,” Proc. European Conf. Comp. Vision, 2000.
[12] D. DeMenthon and L. Davis, “Model-Based Object Pose in 25 Lines of Code,” Int'l J. of Computer Vision, vol. 15, no. 1-2, pp. 123-141, 1995.
[13] R. Haralick, H. Joo, C. Lee, X. Zhuang, V. Vaidy, and M. Kim, “Pose Estimation from Corresponding Point Data,” IEEE Trans. Systems, Man, and Cybernetics, vol. 19, no. 6, pp. 1426-1446, 1989.
[14] R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision. Cambridge Univ. Press, 2000.
[15] D. Heeger and A. Jepson, “Subspace Methods for Recovering Rigid Motion I: Algorithm and Implementation,” Int'l J. Computer Vision, vol. 7, pp. 95-117, 1992.
[16] Y. Hel-Or and M. Werman, “Absolute Orientation from Uncertain Point Data: A Unified Approach,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 77-82, 1992.
[17] Understanding Robust and Exploratory Data Analysis, D. Hoaglin, F. Mosteller, and J. Tukey, eds. John Wiley & Sons, 1983.
[18] S.. Hsu, S. Samarasekera, R. Kumar, and H. Sawhney, “Pose Estimation, Model Refinement, and Enhanced Visualization Using Video,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 448-495, 2000.
[19] M. Irani, B. Rousso, and S. Peleg, “Robust Recovery of Ego-Motion,” Proc. Conf. Computer Analysis Images and Patterns, pp. 371-378, 1993.
[20] D. Jacobs and R. Basri, “3-D to 2-D Pose Determination with Regions,” Int'l J. Computer Vision, vol. 34, no. 2-3, pp. 123-145, 1999.
[21] R. Lerner, H. Rotstein, and E. Rivlin, “Error Analysis of an Algorithm for Pose and Motion Recovery from Correspondence and a Digital Terrain Map,” in preparation.
[22] R. Lerner, P. Rotstein, and E. Rivlin, “Error Analysis for a Navigation Algorithm Based on Optical-Flow and a Digital Terrain Map,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 604-610, 2004.
[23] Y. Liu, T. Huang, and O. Faugeras, “Determination of Camera Location from 2-D to 3-D Line and Point Correspondences,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 1, pp. 28-37, Jan. 1990.
[24] H.C. Longuet-Higgins, “A Computer Algorithm for Reconstructing a Scene from Two Projections,” Readings in Computer Vision: Issues, Problems, Principles, and Paradigms, M.A. Fischler and O. Firschein, eds., pp. 61-62, Los Altos, Calif.: Kaufmann, 1987.
[25] C. Lu, G. Hager, and E. Mjolsness, “Fast and Globally Convergent Pose Estimation from Video Images,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 6, pp. 610-622, June 2000.
[26] 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, pp. 674-679, 1981.
[27] D. Nister, “A Minimal Solution to the Generalised 3-Point Pose Problem,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 560-567, 2004.
[28] J. Oliensis, “A Multi-Frame Structure from Motion Algorithm under Perspective,” Int'l J. Computer Vision, vol. 34, no. 2, pp. 163-192, 1999.
[29] J. Oliensis, “A Critique of Structure-from-Motion Algorithms,” Computer Vision and Image Understanding, vol. 80, pp. 172-214, 2000.
[30] J. Oliensis, “Exact Two-Image Structure from Motion,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, pp. 1618-1633, 2002.
[31] J. Rodriguez and J.K. Aggarwal, “Matching Aerial Images to 3-D Terrain Maps,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 12, no. 12, pp. 1138-1149, Dec. 1990.
[32] S. Seitz and C. Dyer, “Complete Scene Structure from Four Point Correspondences,“ Proc. IEEE Int. Conf. Computer Vision, pp. 330-337, 1995.
[33] I. Shimshoni, R. Basri, and E. Rivlin, “A Geometric Interpretation of Weak-Perspective Motion,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 3, pp. 252-257, Mar. 1999.
[34] H. Shum, Q. Ke, and Z. Zhang, “Efficient Bundle Adjustment with Key Frames: A Hierarchical Approach to Multi-Frame Structure from Motion,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 538-543, 1999.
[35] D.G. Sim, R.H. Park, R.C. Kim, S.U. Lee, and I.C. Kim, “Integrated Position Estimation Using Aerial Image Sequences,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 1, pp. 1-18, Jan. 2002.
[36] D. Simon, “Fast and Accurate Shape-Based Registration,” Technical Report CMU-RI-TR-96-45, Robotics Inst., Carnegie Mellon Univ., Dec. 1996.
[37] S. Srinivasan, “Extracting Structure from Optical Flow Using the Fast Error Search Technique,” Int'l J. Computer Vision, vol. 37, no. 3, pp. 203-230, 2000.
[38] P. Sturm and B. Triggs, “A Factorization Based Algorithm for Multi-Image Projective Structure and Motion,” Proc. European Conf. Computer Vision, pp. 709-720, 1996.
[39] H. Takeda, C. Facchinetti, and J. Latombe, “Planning the Motion of a Mobile Robot in a Sensory Uncertainty Field,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 10, pp. 1002-1017, Oct. 1994.
[40] T. Tan, K. Baker, and G. Sullivan, “3D Structure and Motion Estimation from 2D Image Sequences,” Image and Vision Computing, vol. 11, pp. 203-210, 1993.
[41] C. Taylor and D. Kriegman, “Structure and Motion from Line Segments in Multiple Images,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, pp. 1021-1032, 1995.
[42] B. Triggs, P. McLauchlan, R. Hartley, and A. Fitzgibbon, “Bundle Adjustment— A Modern Synthesis,” W. Triggs, A. Zisserman, and R. Szeliski, eds., Vision Algorithms: Theory and Practice, pp. 298-375, Springer Verlag, 2000.
[43] J. Weng, T. Huang, and N. Ahuja, “Motion and Structure from Two Perspective Views: Algorithms, Error Analysis, and Error Estimation,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 11, no. 5, pp. 451-476, May 1989.
[44] T. Wu, R. Chellappa, and Q. Zheng, “Experiments on Estimating Egomotion and Structure Parameters Using Long Monocular Image Sequences,” Int'l J. Computer Vision, vol. 15, no. 1-2, pp. 77-103, 1995.
[45] Z. Zhang, “Motion and Structure from Two Perspective Views: From Essential Parameters to Euclidean Motion through the Fundamental Matrix,” J. Optical Soc. of Am., vol. 14, no. 11, pp. 2938-2950, 1997.

Index Terms:
Pose estimation, vision-based navigation, DTM, structure from motion.
Citation:
Ronen Lerner, Ehud Rivlin, H?ctor P. Rotstein, "Pose and Motion Recovery from Feature Correspondences and a Digital Terrain Map," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 9, pp. 1404-1417, Sept. 2006, doi:10.1109/TPAMI.2006.192
Usage of this product signifies your acceptance of the Terms of Use.