In this paper we analyze the problem of matching partially obscured, noise-corrupted images of composite scenes in two and three dimensions. We describe efficient methods for smoothing the noisy data and for matching portions of the observed object boundaries (or of characteristic curves lying on bounding surfaces of 3-D objects) to prestored models. We also report initial experiments showing the efficacy of this procedure.
Get full access to this article
View all access options for this article.
References
1.
Ayache, N., et al. 1984 (Montreal). Automatic handling of overlapping workpieces. Int. Conf Pattern Recognition.
2.
Ballard, D., and Brown, C.1982. Computer vision. Englewood Cliffs, N.J.: Prentice-Hall.
3.
Bastuscheck, C.M. et al. 1986. Object recognition by three-dimensional curve matching. Int. J. Intell. Systems. Vol. 1. 1986. 105-132.
4.
Bastuscheck, M., and Schwartz, J.T.1984(June). Preliminary implementation of a ratio depth sensor. Tech. Rept. 124. New York: New York University, Computer Science Department, Courant Institute of Mathematical Sciences.
5.
Bolles, R., and Gain, R.1982. Recognizing and locating partially visible objects: the local feature-focus method. Int. J. Robotics Res.1:57-82.
6.
Bolles, R., Horaud, P., and Hannah, M.1984. 3DPO: A three-dimensional part orientation system. In Robotics Research, the First International Symposium, eds. M. Brady and R. Paul, pp. 413-424. Cambridge: MIT Press.
7.
Chazelle, B.1982. A theorem on polygon cutting with applications. Proc. 23rd IEEE Symp. on the Foundations of ComputerScience, pp. 339-349.
8.
Grimson, W., and Lozano-Pérez, T.1984. Model-based recognition and localization from sparse range or tactile data. Int. J. Robotics Res.3:3-35.
9.
Grimson, W., and Lozano-Pérez, T.1985 (St. Louis). Recognition and localization of overlapping parts from sparse data in two and three dimensions. IEEE Int. Conf. Robotics and Automation, pp. 61 -66.
10.
Kalvin, A., et al. 1985. Two dimensional model based boundary matching using footprints. Tech. Rept. 162. New York: New York University, Computer Science Department, Courant Institute of Mathematical Sciences and Int. J. Robotics Research5(4): 38-55.
11.
Koch, M., and Kashyap, R.1985 (St. Louis). A vision system to identify occluded industrial parts. IEEE Int. Conf. Robotics and Automation, pp. 55-60.
12.
Lee, D.T., and Preparata, F.P.1984. Euclidean shortest paths in the presence of rectilinear barriers. Networks14:393-410.
13.
Papadimitriou, C.H.1984(July). An algorithm for shortest path motion in three dimensions. Preprint. Palo Alto, Calif.: Stanford University, Computer Science Department.
14.
Reif, J.H., and Storer, J.A.1985(April). Shortest paths in Euclidean space with polyhedral obstacles. Tech. Rept. CS-85-121. Waltham, Mass.: Brandeis University, Computer Science Department.
15.
Schwartz, J.T.1983(March). Structured light sensors for 3-D robot vision. Tech. Rept. 65. New York: New York University, Computer Science Department, Courant Institute of Mathematical Sciences.
16.
Schwartz, J.T. and Sharir, M.1984(April). Some remarks on robot vision. Tech. Rept. 119. New York: New York University, Computer Science Department, Courant Institute of Mathematical Sciences.
17.
Sharir, M., and Schorr, A.1984. On shortest paths in polyhedral spaces. Proc. 16th ACM Symp. on Theory ofComputing, pp. 144-153.
18.
Tunney, J., Mudge, T., and Volz, R.1985 (St. Louis). Recognizing partially hidden objects. IEEE Int. Conf. Robotics and Automation, pp. 48-54.
19.
Wolfson, H. et al. 1986(Feb.). Identification of partially obscured objects in two and three dimensions by matching of noisy characteristic curves. Tech. Rept. 205. New York: New York University, Courant Institute of Mathematical Sciences Robotics Report 65.
