Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  Class-Specific Hough Forests for Object Detection

Gall, J., & Lempitsky, V. (2009). Class-Specific Hough Forests for Object Detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09) (pp. 1-8). Los Alamitos: IEEE Computer Society.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-000F-1995-4 Versions-Permalink: https://hdl.handle.net/11858/00-001M-0000-000F-1996-2
Genre: Konferenzbeitrag

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Gall, Jürgen1, Autor           
Lempitsky, Victor, Autor
Affiliations:
1Computer Graphics, MPI for Informatics, Max Planck Society, ou_40047              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: We present a method for the detection of instances of an object class, such as cars or pedestrians, in natural images. Similarly to some previous works, this is accomplished via generalized Hough transform, where the detections of individual object parts cast probabilistic votes for possible locations of the centroid of the whole object; the detection hypotheses then correspond to the maxima of the Hough image that accumulates the votes from all parts. However, whereas the previous methods detect object parts using generative codebooks of part appearances, we take a more discriminative approach to object part detection. Towards this end, we train a class-specific Hough forest, which is a random forest that directly maps the image patch appearance to the probabilistic vote about the possible location of the object centroid. We demonstrate that Hough forests improve the results of the Hough-transform object detection significantly and achieve state-of-the-art performance for several classes and datasets.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 2009-04-062009
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: Los Alamitos : IEEE Computer Society
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: eDoc: 520481
Anderer: Local-ID: C125675300671F7B-E043433D5A1EEF5DC125758300607EF2-Gall2009c
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Untitled Event
Veranstaltungsort: Miami, USA
Start-/Enddatum: 2009-06-20 - 2009-06-25

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: IEEE Conference on Computer Vision and Pattern Recognition (CVPR'09)
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Los Alamitos : IEEE Computer Society
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 1 - 8 Identifikator: -