Texture boundary detection for real-time tracking

Ali Shahrokni; Tom Drummond; Pascal Fua

doi:10.1007/978-3-540-24671-8_45

Texture boundary detection for real-time tracking

Ali Shahrokni
, Tom Drummond
, Pascal Fua

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

26 Citations (Scopus)

Abstract

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 language	English
Title of host publication	Computer Vision – ECCV 2004
Subtitle of host publication	8th European Conference on Computer Vision Prague, Czech Republic, May 11-14, 2004 Proceedings, Part II
Editors	Tomas Pajdla, Jiri Matas
Place of Publication	Berlin Germany
Publisher	Springer
Pages	566-577
Number of pages	12
ISBN (Print)	3540219838
DOIs	https://doi.org/10.1007/978-3-540-24671-8_45
Publication status	Published - 1 Dec 2004
Externally published	Yes
Event	European Conference on Computer Vision 2004 - Prague, Czechia Duration: 11 May 2004 → 14 May 2004 Conference number: 8th https://link.springer.com/book/10.1007/b97865 (Proceedings)

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	3022
ISSN (Print)	0302-9743

Conference

Conference	European Conference on Computer Vision 2004
Abbreviated title	ECCV 2004
Country/Territory	Czechia
City	Prague
Period	11/05/04 → 14/05/04
Internet address	https://link.springer.com/book/10.1007/b97865 (Proceedings)

Access to Document

10.1007/978-3-540-24671-8_45

Cite this

Shahrokni, A., Drummond, T., & Fua, P. (2004). Texture boundary detection for real-time tracking. In T. Pajdla, & J. Matas (Eds.), Computer Vision – ECCV 2004: 8th European Conference on Computer Vision Prague, Czech Republic, May 11-14, 2004 Proceedings, Part II (pp. 566-577). (Lecture Notes in Computer Science; Vol. 3022). Springer. https://doi.org/10.1007/978-3-540-24671-8_45

@inproceedings{f8193b1f999a47089f741ca65f8147c8,

title = "Texture boundary detection for real-time tracking",

abstract = "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",

author = "Ali Shahrokni and Tom Drummond and Pascal Fua",

year = "2004",

month = dec,

day = "1",

doi = "10.1007/978-3-540-24671-8\_45",

language = "English",

isbn = "3540219838",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "566--577",

editor = "Tomas Pajdla and Jiri Matas",

booktitle = "Computer Vision – ECCV 2004",

address = "Switzerland",

note = "European Conference on Computer Vision 2004, ECCV 2004 ; Conference date: 11-05-2004 Through 14-05-2004",

url = "https://link.springer.com/book/10.1007/b97865",

}

Shahrokni, A, Drummond, T & Fua, P 2004, Texture boundary detection for real-time tracking. in T Pajdla & J Matas (eds), Computer Vision – ECCV 2004: 8th European Conference on Computer Vision Prague, Czech Republic, May 11-14, 2004 Proceedings, Part II. Lecture Notes in Computer Science, vol. 3022, Springer, Berlin Germany, pp. 566-577, European Conference on Computer Vision 2004, Prague, Czechia, 11/05/04. https://doi.org/10.1007/978-3-540-24671-8_45

Texture boundary detection for real-time tracking. / Shahrokni, Ali; Drummond, Tom; Fua, Pascal.
Computer Vision – ECCV 2004: 8th European Conference on Computer Vision Prague, Czech Republic, May 11-14, 2004 Proceedings, Part II. ed. / Tomas Pajdla; Jiri Matas. Berlin Germany: Springer, 2004. p. 566-577 (Lecture Notes in Computer Science; Vol. 3022).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Texture boundary detection for real-time tracking

AU - Shahrokni, Ali

AU - Drummond, Tom

AU - Fua, Pascal

N1 - Conference code: 8th

PY - 2004/12/1

Y1 - 2004/12/1

N2 - 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

AB - 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

UR - https://www.scopus.com/pages/publications/35048885693

U2 - 10.1007/978-3-540-24671-8_45

DO - 10.1007/978-3-540-24671-8_45

M3 - Conference Paper

AN - SCOPUS:35048885693

SN - 3540219838

T3 - Lecture Notes in Computer Science

SP - 566

EP - 577

BT - Computer Vision – ECCV 2004

A2 - Pajdla, Tomas

A2 - Matas, Jiri

PB - Springer

CY - Berlin Germany

T2 - European Conference on Computer Vision 2004

Y2 - 11 May 2004 through 14 May 2004

ER -

Texture boundary detection for real-time tracking

Abstract

Publication series

Conference

Access to Document

Other files and links

Cite this