Occlusion detection in early vision
- 4 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 126-132
- https://doi.org/10.1109/iccv.1990.139509
Abstract
The authors show that occlusion can be detected by early visual processes derived directly from the image data. Two methods are demonstrated. The first method is based on detecting binocular rivalry during binocular fixation. The feasibility of this technique also supports the hypothesis that stereo fusion and rivalry coexist in human vision. Stereo fusion gives rise to smooth disparity whereas rivalry signals depth discontinuity. The second method uses focal information that results from a change in depth of field. This method does not involve changes of viewpoint and hence avoids the correspondence problem. These two methods together with cues from motion, as has been suggested elsewhere, form robust occlusion detection in early visual processing.Keywords
This publication has 16 references indexed in Scilit:
- Stereoscopic Depth: Its Relation to Image Segmentation, Grouping, and the Recognition of Occluded ObjectsPerception, 1989
- A New Sense for Depth of FieldPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1987
- A new class of similarity measures for robust image registrationComputer Vision, Graphics, and Image Processing, 1984
- Local Shading AnalysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1984
- The Shape of Smooth Objects and the Way Contours EndPerception, 1982
- Recovery of the three-dimensional shape of an object from a single viewArtificial Intelligence, 1981
- Interpreting line drawings as three-dimensional surfacesArtificial Intelligence, 1981
- Analysis of occluding contourProceedings of the Royal Society of London. B. Biological Sciences, 1977
- Understanding image intensitiesArtificial Intelligence, 1977
- DISCUSSION OF THE CONTROL OF EYE VERGENCE MOVEMENTSPublished by Elsevier ,1971