Planning the optimal set of views using the Max-Min principle

  • Jasna Maver
  • Aleš Leonardis
  • Franc Solina
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 801)


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.


Elevation Angle Azimuth Angle Object Point Viewing Direction Orthographic Projection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    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
  2. [2]
    R. Bajcsy, “Active Perception”, In Proc. of the IEEE, vol. 76, no.8, pp. 996–1005, August 1988.Google Scholar
  3. [3]
    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
  4. [4]
    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
  5. [5]
    D. Wilkes and J. K. Tsotsos, “Active Object Recognition,” In Proc. of the CVPR'92, pp. 136–141, 1992Google Scholar
  6. [6]
    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

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Jasna Maver
    • 1
  • Aleš Leonardis
    • 1
  • Franc Solina
    • 1
  1. 1.Computer Vision Laboratory, Faculty of Electrical Engineering and Computer ScienceUniversity of LjubljanaLjubljanaSlovenia

Personalised recommendations