Abstract
Model-based localization, the task of estimating an object's pose from sensed and corresponding model features, is a fundamental task in machine vision. Exact constant time localization algorithms have been developed for the case where the sensed features and the model features are the same type. Still, it is not uncommon for the sensed features and the model features to be of different types, i.e., sensed data points may correspond to model faces or edges. Previous localization approaches have handled different model and sensed features of different types via sampling and synthesizing virtual features to reduce the problem of matching features of dissimilar types to the problem of matching features of similar types. Unfortunately, these approaches may be suboptimal because they introduce artificial errors. Other localization approaches have reformulated object localization as a nonlinear least squares problem where the error is between the sensed data and model features in image coordinates (the Euclidean image error metric). Unfortunately, all of the previous approaches which minimized the Euclidean image error metric relied on gradient descent methods to find the global minima, and gradient descent methods may suffer from problems of local minima. In this paper, we describe an exact, efficient solution to the nonlinear least squares minimization problem based upon resultants, linear algebra, and numerical techniques. On a SPARC 20, our localization algorithm runs in a few microseconds for rectilinear polygonal models, a few milliseconds for generic polygonal models, and one second for generalized polygonal models (models composed of linear edges and circular arcs).
Similar content being viewed by others
References
Anderson, E., Bai, Z., Bischof, C., Demmel, J., Dongarra, J., Du Croz, J., Greenbaum, A., Hammarling, S., and Sorensen, D., 1992. LAPACK User’s Guide, Release 1.0. SIAM: Philadelphia.
Ayache, N. and Faugeras, O.D. 1986. Hyper: A new approach for the recognition and positioning of two-dimensional objects. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(1):44-54.
Brocket, R. Least squares matching problems. In Linear Algebra and Its Applications.
Canny, J.F. 1990. Generalized characteristic polynomials. Journal of Symbolic Computation, 9:241-250.
Deriche, R. and Faugeras, O. 1990. Tracking line segments. Image and Vision Computing, 8:261-270.
Dixon, A.L. 1908. The eliminant of three quantics in two independent variables. In Proc. of London Mathematical Society, vol. 6, pp. 49- 69, 209-236.
Emiris, I.Z. and Rege, A. 1994. Monomial bases and polynomial system solving. In Proc. of Int. Symposium on Symbolic and Algebraic Computation, Oxford, pp. 114-122.
Eric, W., Grimson, L., and Lozano-Perez, T. 1984. Model-based recognition and localization from sparse range or tactile data. Int. Journal of Robotics Research, 3(3):3-35.
Eric, W. and Grimson, L. 1990. Object Recognition by Computer: The Role of Geometric Constraints. MIT Press: Cambridge, MA.
Faugeras, O.D. and Hebert, M. 1986. The representation, recognition, and locating of 3-D objects. International Journal of Robotics Research, 5(3):27-52.
Forsyth, D., Mundy, L., Zisserman, A., Heller, A., and Rothwell, C. 1991. Invariant descriptors fo 3-D object recognition and pose. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13:971-991.
Garbow, B.S., Boyle, J.M., Dongarra, J., and Moler, C.B. 1977. Matrix Eigensystem Routines-EISPACK Guide Extension, vol. 51 of Lecture Notes in Computer Science. Springer-Verlag: Berlin.
Golub, G.H. and Van Loan, C.F. 1989. Matrix Computations. John Hopkins Press: Baltimore.
Horn, B.K.P. 1989. Robot Vision. Seventh edition. McGraw-Hill.
Horn, B.K.P. 1991. Relative orientation revisited. Journal of Optical Society of America, 8(10):1630-1638.
Huttenlocher, D.P., Klanderman, G.A., and Rucklidge, W.J. 1993. Comparing images using the Hausdorff distance. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(9):850- 863.
Kalvin, A., Schonberg, E., Schwartz, J.T., and Sharir, M. 1986. Two-dimensional model-based boundary matching using footprints. Int. Journal of Robotics Research, 5(4):38-55.
Koller, D., Daniilidis, K., and Nagel, H.-H. 1993. Model-based object tracking in monocular image sequences of road traffic scenes. International Journal of Computer Vision, 10(3):257-281.
Kriegman, D.J. and Ponce, J. On recognizing and positioning curved 3D objects from image contours.
Macaulay, F.S. 1902. On some formula in elimination. In Proc. of London Mathematical Society, pp. 3-27.
Macaulay, F.S. 1964. The Algebraic Theory of Modular Systems. Stechert-Hafner Service Agency: New York.
Manocha, D. 1992. Algebraic and Numeric Techniques for Modeling and Robotics. Ph.D. Thesis, Department of Electrical Engineering and Computer Science, University of California, Berkeley.
Paulos, E. and Canny, J. 1993. Informed peg-in-hole insertion using optical sensors. In SPIE Conf. on Sensor Fusion VI, Boston, MA.
Ponce, J., Hoogs, A., and Kriegman, D.J. 1992. On using cad models to compute the pose of curved 3D objects. CVGIP: Image Understanding, 55(2):184-197.
Ponce, J. and Kriegman, D.J. 1992. Elimination theory and computer vision: Recognition and positioning of curved 3D objects from range, intensity, or contours. In Symbolic and Numerical Computation for Artificial Intelligence, pp. 123-146.
Salmon, G. 1885. Lessons Introductory to the Modern Higher Algebra. G.E. Stechert & Co.: New York.
Schwartz, J.T. and Sharir, M. 1987. Identification of partially obscured objects in three dimensions by matching noisy characteristic curves. Int. Journal of Robotics Research, 6(2):29-44.
Sullivan, S., Sandford, L., and Ponce, J. 1994. Using geometric distance fits for 3D object modelling and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(12):1183- 1196.
Van Der Waerden, B.L. 1950. Modern Algebra. Third edition. F. Ungar Publishing Co.: New York.
Wallack, A. 1995. Algorithms and techniques for manufacturing. Ph.D. Thesis, University of Californiaat Berkeley.
Wallack, A., Canny, J., and Manocha, D. 1993. Object localization using crossbeam sensing. In IEEE Int. Conf. on Robotics and Automation, vol. 1, pp. 692-699.
Wallack, A. and Canny, J. 1995. Object recognition and localization from scanning beam sensors. In IEEE Int. Conf. on Robotics and Automation.
Zhang, Z. and Faugeras, O. 1990. Building a 3D world model with a mobile robot: 3D line segment representation and integration. In Int. Conf. on Pattern Recognition, pp. 38-42.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Wallack, A., Manocha, D. Robust Algorithms for Object Localization. International Journal of Computer Vision 27, 243–262 (1998). https://doi.org/10.1023/A:1007918114326
Issue Date:
DOI: https://doi.org/10.1023/A:1007918114326