Visual perception strategies for 3D reconstruction
We propose in this paper an active vision approach for performing the 3D reconstruction of static scenes. The perception-action cycles are handled at various levels: from the definition of perception strategies for scene exploration downto the automatic generation of camera motions using visual servoing. To perform the reconstruction we use a structure from controlled motion method which allows a robust estimation of primitive parameters. As this method is based on particular camera motions, perceptual strategies able to appropriately perform a succession of such individual primitive reconstructions are proposed in order to recover the complete spatial structure of complex scenes. Two algorithms are proposed to ensure the exploration of the scene. The former is an incremental reconstruction algorithm based on the use of a prediction/verification scheme managed using decision theory and Bayes Nets. It allows the visual system to get a complete high level description of the observed part of the scene. The latter, based on the computation of new viewpointsC ensures the complete reconstruction of the scene.
Unable to display preview. Download preview PDF.
- 1.G. Adiv. Inherent ambiguities in recovering 3D motion and structure from a noisy flow field. IEEE Trans. on PAMI, 11(5):477–489, May 1989.Google Scholar
- 2.Y. Aloimonos. Purposive and qualitative active vision. In ICPR'90, pp. 346–360, Atlantic City, June 1990.Google Scholar
- 7.F. Chaumette, S. Boukir, P. Bouthemy, D. Juvin. Structure from controlled motion. IEEE Trans. on PAMI, 18(5):492–504, May 1996.Google Scholar
- 8.C. Connoly. The determination of next best views. In IEEE Int. Conf. an Robotics and Automation, pp. 432–435, St Louis, March 1985.Google Scholar
- 9.C.K. Cowan, P.D. Kovesi. Automatic sensor placement from vision task requirements. IEEE Trans. on PAMI, 10(3):407–416, May 1988.Google Scholar
- 10.D. Djian, P. Probert, and P. Rives. Active sensing using bayes nets. In Proc. of Int. Conf. an Advanced Robotics, ICAR'95, pp. 895–902, Sant Feliu de Guixols, Spain, September 1995.Google Scholar
- 12.B. Espiau, P. Rives. Closed-loop recursive estimation of 3D features for a mobile vision system. In IEEE Int. Conf. on Robotics and Automation, pp. 1436–1443, Raleigh, April 1987.Google Scholar
- 14.E. Marchand. Stratégies de perception par vision active pour la reconstruction et l'exploration de scènes statiques. PhD thesis, Université de Rennes 1, June 1996.Google Scholar
- 15.E. Marchand, F. Chaumette. Controlled camera motions for scene reconstruction and exploration. In CVPR'96, pp. 169–176, San Francisco, June 1996.Google Scholar
- 16.E. Marchand, F. Chaumette, A. Rizzo. Using the task function approach to avoid robot joint limits and kinematic singularities in visual servoing. In IROS'96, pp. 1083–1090, Osaka, Japan, November 1996.Google Scholar
- 18.J. Pearl. Probabilistic reasoning in intelligent systems: Networks of plausible inference. Morgan Kaufmann Publisher Inc., San Mateo, California, 1988.Google Scholar
- 22.B. Triggs, C. Laugier. Automatic camera placement for robot vision. In IEEE Int. Conf. an Robotics and Automation, pp. 1732–1738, Nagoya, Japon, May 1995.Google Scholar
- 23.L.E. Wixson. Viewpoint selection for visual search. In CVPR'94, pp. 800–805, Seattle, June 1994.Google Scholar