Planning the optimal set of views using the Max-Min principle
We present an approach to a typical task of active sensing, namely how to successively position the sensor in order to accomplish a given task. The approach is data driven since it is only the data that provides the information for planning the next views, and no a priori knowledge about the constituents of the scene is necessary. We applied our approach to the task of determining the 3-D coordinates of vertices of object silhouettes in the image under orthographic projection.
KeywordsElevation Angle Azimuth Angle Object Point Viewing Direction Orthographic Projection
Unable to display preview. Download preview PDF.
- J. Aloimonos and A. Bandyopadhyay, “Active Vision,” In Proc. of the IEEE 1 st Int. Conf. on Computer Vision, pp. 35–54, June 1987.Google Scholar
- R. Bajcsy, “Active Perception”, In Proc. of the IEEE, vol. 76, no.8, pp. 996–1005, August 1988.Google Scholar
- J. Maver, Planning the Next View Using the Max-Min Principle, University of Ljubljana, Faculty of EE and CS, Tech. report LRV-93-4, 1993.Google Scholar
- J. Maver and R. Bajcsy, “Occlusions as a Guide for Planning the Next View,” IEEE Trans. on Pattern Anal. and Machine Intell., vol. 15 no.5, pp. 417–433, 1993.Google Scholar
- D. Wilkes and J. K. Tsotsos, “Active Object Recognition,” In Proc. of the CVPR'92, pp. 136–141, 1992Google Scholar
- J. Y. Zheng, F. Kishino, Q. Chen, and S. Tsuji, “Active Camera Controlling for Manipulation,” In Proc. of the CVPR'91, pp. 413–418, 1991.Google Scholar