Texture boundary detection for real-time tracking

Ali Shahrokni, Tom Drummond, Pascal Fua

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

24 Citations (Scopus)


e propose an approach to texture boundary detection that only requires a line-search in the direction normal to the edge. It is therefore very fast and can be incorporated into a real-time 3-D pose estimation algorithm that retains the speed of those that rely solely on gradient properties along object contours but does not fail in the presence of highly textured object and clutter. This is achieved by correctly integrating probabilities over the space of statistical texture models. We will show that this rigorous and formal statistical treatment results in good performance under demanding circumstances

Original languageEnglish
Title of host publicationComputer Vision – ECCV 2004
Subtitle of host publication8th European Conference on Computer Vision Prague, Czech Republic, May 11-14, 2004 Proceedings, Part II
EditorsTomas Pajdla, Jiri Matas
Place of PublicationBerlin Germany
Number of pages12
ISBN (Print)3540219838
Publication statusPublished - 1 Dec 2004
Externally publishedYes
EventEuropean Conference on Computer Vision 2004 - Prague, Czech Republic
Duration: 11 May 200414 May 2004
Conference number: 8th
https://link.springer.com/book/10.1007/b97865 (Proceedings)

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743


ConferenceEuropean Conference on Computer Vision 2004
Abbreviated titleECCV 2004
CountryCzech Republic
Internet address

Cite this