Advertisement

Determining 3-D structure of scene from image sequences obtained by horizontal and vertical moving camera

  • Masanobu Yamamoto
Motion And Depth Analysis
Part of the Lecture Notes in Computer Science book series (LNCS, volume 301)

Abstract

The stereo vision is one of the simplest methods for acquiring three-dimensional (3-D) information. A problem then is that sometimes it is difficult to establish a correspondence between the left and the right images, in such cases as (1) multiple correspondence, (2) occlusion, (3) position reversals, and (4) horizontal edge. This paper proposes a method to determine the three-dimensional structure of the scene from the sequences of images obtained by the moving camera. As the first step, a two-dimensional image is constructed from the sequence of images, in which the apparent locus of motion is represented as segments. The correspondence problem in this step is simplified as the detection of segments on the synthetic image. By examining the relations among the detected segments, the occlusions can be detected, and the correspondence can be established where the positional reversals happen. By moving the camera not only in one direction, but also in orthogonal directions, the unique correspondence can be established, independently from the direction of the edge. An input system was constructed, which can accept a large number of motion stereo image sequence with a high speed, and some complex three-dimensional structures of the scenes were actually determined.

Keywords

View Point Stereo Image Stereo Vision Synthetic Image Horizontal Edge 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    S.T. Barnard and W.D Thompson. Disparity analysis of images. IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.PAMI-2,no.4:333–340, 1981.Google Scholar
  2. [2]
    R.C. Bolles and H.H. Baker. Epipolar-plane image analysis; a technique for analyzing motion sequences. In Proc. of 3rd ISRR, pages 192–199, 1985.Google Scholar
  3. [3]
    W.E.L. Grimson. Computational experiments with a feature based stereo algorithm. IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.PAMI-7,no.1:17–34, 1985.Google Scholar
  4. [4]
    K. Ikeuchi. Determining depth map from a pair of needle maps by apair of photometric stereo systems with region matching. Trans. of Institute of Electronics and Communication Engineers of Japan, vol.J68-D,no.10:1761–1768, 1985.Google Scholar
  5. [5]
    T. Itoh and A. Ishii. Stereo vision correspondence processing by three-view-stereo. In Proc. of 29th Conv. of Information Processing Society of Japan, pages 2M-3, 1984.Google Scholar
  6. [6]
    J.F Jarvis. Automatic visual inspection of glass-metal seals. In Proc. of 4th IJCPR, pages 961–965, 1978.Google Scholar
  7. [7]
    T. Kaneko. Three-dimensional measurement using quasi-static rotation of an object. Technical Report PRL-85-22, Institute of Electronics and Communication Engineers of Japan, 1985.Google Scholar
  8. [8]
    B.D. Lucas and T. Kanade. An iterative image registration technique with an application to stereo vision. In Proc. of 7th IJCAI, pages 674–679, 1981.Google Scholar
  9. [9]
    H.P. Moravec. Visual mapping by a robot rover. In Proc. of 6th IJCAI, pages 598–600, 1979.Google Scholar
  10. [10]
    T. Ohmori and I. Morishita. Object detection using multi-view stereo images. Trans. of SICE, vol.18,no.7:716–722, 1982.Google Scholar
  11. [11]
    Y. Ohta and K. Ikeda. On the three-view stereo. In Proc. of 29th National Confference of Information Processing Society of Japan, pages 2M-4, 1984.Google Scholar
  12. [12]
    Y. Ohta and T. Kanade. Stereo by intra-and inter-scan line search using dynamic programming. IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.PAMI-7,no.2:139–154, 1985.Google Scholar
  13. [13]
    Y. Ohta, Y. Masai, and K. Ikeda. Interval matching method of stereo images using dynamic programing. Trans. of Institute of Electronics and Communication Engineers of Japan, vol.J68-D,no.4:554–561, 1985.Google Scholar
  14. [14]
    K.F. Prazdny. Determining the instantaneous direction of motion from optical flow generated by a curvilinearrly moving observer. Computer Graphics and Image Processing, vol.17:238–248, 1981.Google Scholar
  15. [15]
    Y. Sasaki and T. Furukawa. A synthesis algorithm of arbitrary intermediate viewing angle images from several pairs of stereograms. Trans. of Institute of Electronics and Communication Engineers of Japan, vol.J63-D,no.9:813–814, 1980.Google Scholar
  16. [16]
    F. Tomita. Stereo matching based on region boundary segments. Technical Report CV-38-1, Information Processing Society of Japan, 1985.Google Scholar
  17. [17]
    M. Yachida. Recognition of three-dimensional object using multi-view stereo images. Nikkei Mechanical, vol.157:82–91, 1984.Google Scholar
  18. [18]
    M. Yamamoto. Determining three-dimensional structure by visualized locus method. In Proc. of National Confference of Institute of Electronics and Communication Engineers of Japan, pages S18-12, 1981.Google Scholar
  19. [19]
    M. Yamamoto. Motion analysis by visualized locus method. Trans. of Information Processing Society of Japan, vol.22,no.5:442–449, 1981.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1988

Authors and Affiliations

  • Masanobu Yamamoto
    • 1
  1. 1.Computer Vision Section, Electrotechnical LaboratoryJAPAN

Personalised recommendations