Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
 
 
DownloadE-Mail
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  Branch&Rank: Non-linear Object Detection

Lehmann, A., Gehler, P., & Van Gool, L. (2011). Branch&Rank: Non-linear Object Detection. In J. Hoey, S. McKenna, & E. Trucco (Eds.), Proceedings of the British Machine Vision Conference 2011 (pp. 8.1-8.11). Malvern, UK: BMVA Press. doi:10.5244/C.25.8.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0010-12CE-C Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-0024-12B2-C
Genre: Konferenzbeitrag
Latex : {Branch\&Rank}: Non-linear Object Detection

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Lehmann, Alain1, Autor
Gehler, Peter2, Autor           
Van Gool, Luc1, Autor
Affiliations:
1External Organizations, ou_persistent22              
2Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Branch&rank is an object detection scheme that overcomes the inherent limitation of branch&bound: this method works with arbitrary (classifier) functions whereas tight bounds exist only for simple functions. Objects are usually detected with less than 100 classifier evaluation, which paves the way for using strong (and thus costly) classifiers: We utilize non-linear SVMs with RBF- 2 kernels without a cascade-like approximation. Our approach features three key components: a ranking function that operates on sets of hypotheses and a grouping of these into different tasks. Detection efficiency results from adaptively sub-dividing the object search space into decreasingly smaller sets. This is inherited from branch&bound, while the ranking function supersedes a tight bound which is often unavailable (except for too simple function classes). The grouping makes the system effective: it separates image classification from object recognition, yet combines them in a single, structured SVM formulation. A novel aspect of branch&rank is that a better ranking function is expected to decrease the number of classifier calls during detection. We demonstrate the algorithmic properties using the VOC'07 dataset.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 20112011
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: eDoc: 618788
BibTex Citekey: 526
DOI: 10.5244/C.25.8
URI: http://dx.doi.org/10.5244/C.25.8
Anderer: Local-ID: C12576EE0048963A-C578EB50E10A203DC12579640041092D-Gehler2010
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: 2011 British Machine Vision Conference
Veranstaltungsort: Dundee, Scotland
Start-/Enddatum: 2011-08-29 - 2011-09-02

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Proceedings of the British Machine Vision Conference 2011
  Kurztitel : BMVC 2011
Genre der Quelle: Konferenzband
 Urheber:
Hoey, Jesse1, Herausgeber
McKenna, Stephen1, Herausgeber
Trucco, Emanuele1, Herausgeber
Affiliations:
1 External Organizations, ou_persistent22            
Ort, Verlag, Ausgabe: Malvern, UK : BMVA Press
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 8.1 - 8.11 Identifikator: ISBN: 1-901725-43-X