Identification and 3D description of 'shallow' environmental structure in a sequence of images
- 10 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 179-185
- https://doi.org/10.1109/cvpr.1991.139684
Abstract
A framework is presented for segmenting shallow structures from their background over a sequence of images. Shallowness is first quantified as affine describability. This is embedded in a tracking system within which hypothesized model structures undergo a cycle of prediction and model-matching. Structures emerge either as shallow or non-shallow based on their affine trackability. This paper rejects continuity heuristics for purely image motion in favor of temporal continuity defined as the consistency of generic 3-D models, namely shallow structures.Keywords
This publication has 7 references indexed in Scilit:
- Translating Optical Flow Into Token Matches And Depth From LoomingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Measuring Image Flow By Tracking Edge-linesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Tracking line segmentsPublished by Springer Nature ,1990
- ISR: a database for symbolic processing in computer visionComputer, 1989
- Inherent ambiguities in recovering 3-D motion and structure from a noisy flow fieldPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Token-based extraction of straight linesIEEE Transactions on Systems, Man, and Cybernetics, 1989
- Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving ObjectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1985