| ECVision indexed and annotated bibliography of cognitive computer vision publications This bibliography was created by Hilary Buxton and Benoit Gaillard, University of Sussex, as part of ECVision Specific Action 8-1 The complete text version of this BibTeX file is available here: ECVision_bibliography.bib
L. Williams and A. Hanson
ABSTRACT
Researchers in computer vision have primarily studied the problem of visual re construction of environmental structure that is plainly visible. In this thesis, the conventional goals of visual reconstruction are generalized to include both visible and occluded forward facing surfaces. This larger fraction of the environment is termed the anterior surfaces. Because multiple anterior surface neighborhoods project onto a single image neighborhood wherever surfaces overlap, surface neighborhoods and image neighborhoods are not guaranteed to be in onetoone correspondence, as con ventional ``shapefrom'' methods assume. The result is that the topology of three dimensional scene structure can no longer be taken for granted, but must be inferred from evidence provided by image contours. Where boundaries are not occluded and where surface reflectance is distinct from that of the background, boundaries will be marked by image contours. However, where boundaries are occluded, or where surface reflectance matches background re flectance, there will be no detectable luminance change in the image. Deducing the complete image trace of the boundaries of the anterior surfaces under these circum stances is called the figural completion problem. |
|
| Site generated on Friday, 06 January 2006
|