Pose Determination of a Three-Dimensional Object Using Triangle Pairs
|
A procedure is presented to estimate the unconstrained three-dimensional location and orientation of an object with a known shape when it is visible in a single image. Using a generalized Hough transform, all six parameters of the object position are estimated from the distribution of values determined by matching triples of points on the object to possibly corresponding triples in the image. Most likely candidates for location are found, and then the remaining rotational parameters are evaluated. Two solutions are generally admitted to the distribution by every match of triangles. The number of possible matches is reduced by checking a simple geometric relation among triples. Even with partial occlusion, experiments indicate that the procedure is very reliably accurate, although optimization can further improve estimates of the parameters.
[1] 634D. H. Ballard, "Generalizing the Hough transform to detect arbitrary shapes,"Pattern Recognition, vol. 13, pp. 111-222, 1981.
[2] R. A. Brooks, "Model-based three-dimensional interpretations of two-dimensional images,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-5, pp. 140-150, 1983.
[3] L. S. Davis, "Hierarchical generalized Hough transforms and line-segment based generalized Hough transforms,"Pattern Recognition, vol. 15, pp. 277-285, 1982.
[4] M. A. Fischler and R. C. Bolles, "Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography,"Commun. ACM, vol. 24, no. 6, pp. 381-395, 1981.
[5] J.D. Foley and A. Van Dam,Fundamentals of Interactive Computer Graphics(The System Programming Series). Reading, MA: Addison-Wesley, 1982.
[6] H. Freeman and L. S. Davis, "A corner-finding algorithm for chain-coded curves,"IEEE Trans. Comput., vol. C-26, pp. 297-303, 1977.
[7] S. Ganapathy, "Decomposition of transformation matrices for robot vision," inProc. Int. Conf. Robotics Automat., 1984.
[8] D. Harwood, M. Subbarao, H. Hakalahti, and L. S. Davis, "A new class of edge-preserving smoothing filters," CAR-TR-59, Cen. for Automation Res., Univ. Maryland, College Park, 1984.
[9] Y. Hung, P.-S. Yeh, and D. Harwood, "Passive ranging to known planar point sets," CAR-TR-65, Cen. for Automation Res., Univ. Maryland, College Park, 1984.
[10] Y. Hung, P.-S. Yeh, and D. Harwood, "Computing the coordinates of a quadrangle with known shape,"Comput. Vision, Graphics, Image Processing, 1985.
[11] L. G. Roberts, "Machine perception of three-dimensional solids," in J. T. Tippettet al., Eds.,Optical and Electro-Optical Information Processing. Cambridge, MA: M.I.T. Press, 1965, pp. 159-197.
[12] T. Silberberg, D. Harwood, and L. Davis, "Object recognition using oriented model points,"Comput. vision, Graphics, ImageProcessing, vol. 35, pp. 47-71, 1986.
[13] G. Stockman and J. C. Esteva, "Use of geometrical constraints and clustering to determine 3D object pose," inProc. 7th Int. Conf. Pattern Recognition, Montreal, Canada, 1984, pp. 742-744.
Index Terms:
3D object pose determination; picture processing; pattern recognition; triangle pairs; Hough transform; pattern recognition; picture processing; transforms
Citation:
S. Linnainmaa, D. Harwood, L.S. Davis, "Pose Determination of a Three-Dimensional Object Using Triangle Pairs," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, no. 5, pp. 634-647, Sept. 1988, doi:10.1109/34.6772
PURCHASE ARTICLE: $19
IEEE Xplore Subscribers
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb