System and method for reconstructing surface elements of solid objects in a three-dimensional scene from a plurality of two dimensional images of the scene

作者: Amnon Shashua

DOI:

关键词: Fundamental matrix (computer vision)Artificial intelligenceComputer visionEuclidean geometryMathematicsImage plane

摘要: An arrangement for generating reconstructon information to facilitate reconstruction of three-dimensional features objects in a scene based on two-dimensional images the taken from plurality locations. The includes elements including an epipole means, homography means and depth value means. identifies location epipoles, that is, coordinates each image plane, which were recorded, point intersection line interconnecting centers projection recorders record images. uses epipoles respective selected reference points generate relates all Finally generated by at least one other point, than points, generate, representative distance relative recorders. Using values number projections planes, as determined images, (Euclidean) structures can be determined.

参考文章(8)
Olivier D. Faugeras, What can be seen in three dimensions with an uncalibrated stereo rig european conference on computer vision. pp. 563- 578 ,(1992) , 10.1007/3-540-55426-2_61
David S. Burnett, A 3-D acoustic infinite element based on an oblate spheroidal multipole expansion Journal of the Acoustical Society of America. ,vol. 102, pp. 678- ,(1996) , 10.1121/1.419883
Dennis R. Smalley, Paul F. Jacobs, Joseph W. Allison, Jan Richter, Craig Matthew Childers, Charles W. Hull, Method of making a three-dimensional object by stereolithography ,(1989)
R. Hartley, R. Gupta, T. Chang, Stereo from uncalibrated cameras computer vision and pattern recognition. pp. 761- 764 ,(1992) , 10.1109/CVPR.1992.223179
A. Shashua, Projective structure from uncalibrated images: structure from motion and recognition IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 16, pp. 778- 790 ,(1994) , 10.1109/34.308472