Change search
ReferencesLink to record
Permanent link

Direct link
A model-free voting approach to cue integration
KTH, Superseded Departments, Numerical Analysis and Computer Science, NADA.
1998 (English)Doctoral thesis, monograph (Other scientific)
Abstract [en]

Vision systems, such as "seeing" robots, should be able tooperate robustly in generic environments. In this thesis, weinvestigate certain aspects of how these demands of robusmessof a systems approach to vision could be met.

Firstly, we suggest that robustness can be improved byfusing the variety of infor mation offered by the environment,and, therefore, we investigate the effectiveness of using thecoincidence of multiple cues. Secondly, we are concerned aboutthe use of coarse algorithms. Even though the environmentprovides much information, it is neither necessary nor possibleto extract all information available. Therefore, we will showthat coarse algorithms will suffice for certain problems. Toinvestigate the effectiveness of using the coincidence ofmultiple cues, we perform a series of experiments on detectingplanar surfaces in binocular images. These experiments arebased on two schemes of a somewhat different character.

The first one is ahyporhesls-and-testscheme that incorporates the cues ina certaln order and hence, by design, imposes a ranking ofthem. The general idea is to use arbitrary cues exploitinglocal image data to get an idea about whether the model (aplanar surface) is seen in the image and at which location itis found. If one or more cues strongly indicate a certaininstance of a model, then this observation serves as ahypothesis to be tested by other cues to support or reject thishypothesis. In comparison to the cues used for hypothesisgeneration, those used for hypothesis testing should be morereliable and can also have a higher computational complexitysince they are only employed when needed.The general idea of the second scheme is to first use asimple, and quick cue exploiting local image data toget anidea of where in the image the model (a planar surface) couldbe found. After this initial localization step, all cues thatcan be computed are gathered and allowed tovorefor the occurrence of the model in the hypothesizedregion. The initialization of this approach is a hypothesisforming step, similar to that of the hypothesis-and-testapproach This step though, is much weaker because it onlyindicates a region in the images where to look. The approachallows direct fusion of incommensurable cues, such as intensityand surface orientation. Generally, it can be regarded as aless restrictive approach than the hypothesis-and-test approach. We propose that coarse algorithms may be motivated from arobustness and flexibtl hy point of view. Our experimentsdemonstrate that there is support for this claim, at least, forsome tasks of relevante, such as those of finding planarsurfaces, or similar simple models.

Keywords:computer vision multiple cues. cueintegration, consensus voting, coincidence, coarse method,robustness. grouping and segmentation, plane detection

Place, publisher, year, edition, pages
Stockholm: Numerisk analys och datalogi , 1998. , 116 p.
Trita-NA-P, 9811
URN: urn:nbn:se:kth:diva-2677ISBN: 91-7170-289-XOAI: diva2:8358
Public defence
NR 20140805Available from: 2000-01-01 Created: 2000-01-01Bibliographically approved

Open Access in DiVA

fulltext(5574 kB)833 downloads
File information
File name FULLTEXT01.pdfFile size 5574 kBChecksum SHA-1
Type fulltextMimetype application/pdf

By organisation
Numerical Analysis and Computer Science, NADA

Search outside of DiVA

GoogleGoogle Scholar
Total: 833 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 349 hits
ReferencesLink to record
Permanent link

Direct link