Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
 DetailsÜbersicht
  An efficient divide-and-conquer cascade for nonlinear object detection

Lampert, C. (2010). An efficient divide-and-conquer cascade for nonlinear object detection. In Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010) (pp. 1022-1029). Piscataway, NJ, USA: IEEE.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-BF96-9 Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-BF97-7
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Lampert, CH1, 2, Autor           
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Dept. Empirical Inference, Max Planck Institute for Intelligent System, Max Planck Society, ou_1497647              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: We introduce a method to accelerate the evaluation of object detection cascades with the help of a divide-and-conquer procedure in the space of candidate regions. Compared to the exhaustive procedure that thus far is the state-of-the-art for cascade evaluation, the proposed method requires fewer evaluations of the classifier functions, thereby speeding up the search. Furthermore, we show how the recently developed efficient subwindow search (ESS) procedure [11] can be integrated into the last stage of our method. This allows us to use our method to act not only as a faster procedure for cascade evaluation, but also as a tool to perform efficient branch-and-bound object detection with nonlinear quality functions, in particular kernelized support vector machines. Experiments on the PASCAL VOC 2006 dataset show an acceleration of more than 50 by our method compared to standard cascade evaluation.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2010-06
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: ISBN: 978-1-424-47029-7
URI: http://cvl.umiacs.umd.edu/conferences/cvpr2010/
DOI: 10.1109/CVPR.2010.5540107
BibTex Citekey: 6770
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010)
Veranstaltungsort: San Francisco, CA, USA
Start-/Enddatum: -

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Twenty-Third IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2010)
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Piscataway, NJ, USA : IEEE
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 1022 - 1029 Identifikator: -