Abstract
A new paradigm, Random Sample Consensus (RANSAC), for fitting a model to experimental data is introduced. RANSAC is capable of interpreting/smoothing data containing a significant percentage of gross errors, and is thus ideally suited for applications in automated image analysis where interpretation is based on the data provided by error-prone feature detectors. A major portion of this paper describes the application of RANSAC to the Location Determination Problem (LDP): Given an image depicting a set of landmarks with known locations, determine that point in space from which the image was obtained. In response to a RANSAC requirement, new results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form. These results provide the basis for an automatic system that can solve the LDP under difficult viewing
- 1 Bolles, R.C., Quam, L.H., Fischler, M.A., and Wolf, H.C. The SRI road expert: Image to database correspondence. In Proc. Image Understanding Workshop, Pittsburgh, Pennsylvania, Nov., 1978,Google Scholar
- 2 Chrystal, G. Textbook of Algebra (Vol 1). Chelsea, New York, New York 1964, p. 415.Google Scholar
- 3 Church, E. Revised geometry of the aerial photograph. Bull. Aerial Photogrammetry. 15, 1945, Syracuse University.Google Scholar
- 4 Conte, S.D. Elementary Numerical Analysis. McGraw Hill, New York, 1965.Google Scholar
- 5 Dehn, E. Algebraic Equations. Dover, New York, 1960.Google Scholar
- 6 Duda, R.O., and Hart, P.E. Pattern Classification and Scene Analysis. Wiley-Interscience, New York, 1973.Google ScholarDigital Library
- 7 Gennery, D.B. Least-squares stereo-camera calibration. Stanford Artificial Intelligence Project Internal Memo, Stanford, CA 1975.Google Scholar
- 8 Keller, M. and Tewinkel, G.C. Space resection in photogrammetry. ESSA Tech. Rept C&GS 32, 1966, U.S. Coast and Geodetic Survey.Google Scholar
- 9 Rogers, D.P. and Adams, J.A. Mathematical Elements for Computer Graphics. McGraw Hill, New York, 1976. Google ScholarDigital Library
- 10 Sorensen, H.W. Least-squares estimation: from Gauss to Kalman. IEEE Spectrum (July 1970), 63-68.Google Scholar
- 11 Wolf, P.R. Elements of Photogrammetry. McGraw Hill, New York, 1974.Google Scholar
- 12 Wylie, C.R. Jr. Introduction to Projective Geometry. McGraw- Hill, New York, 1970.Google Scholar
Index Terms
- Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography
Recommendations
A Vision Based Position System for Robot Picking
ICECE '10: Proceedings of the 2010 International Conference on Electrical and Control EngineeringA machine vision system for robot picking is presented in this paper which is used in robot polishing line. An algorithm for matching work-pieces in a given plane is proposed, which includes camera calibration, image rectification, image preprocessing ...
Image Matching based on Co-Motion Statistics
3DPVT '04: Proceedings of the 3D Data Processing, Visualization, and Transmission, 2nd International SymposiumThis paper presents a method for matching partially overlapping image-pairs where the object of interest is in motion, even if the motion is discontinuous and in an unstructured environment. In a typical outdoor multi-camera surveillance system, an ...
Non-goal scene analysis for soccer video
The broadcast soccer video is usually recorded by one main camera, which is constantly gazing somewhere of playfield where a highlight event is happening. So the camera parameters and their variety have close relationship with semantic information of ...
Comments