Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
Zur Ablage hinzufügen
 Lokale TagsFreigabegeschichteDetailsÜbersicht
  Learning People Detectors for Tracking in Crowded Scenes

Tang, S., Andriluka, M., Milan, A., Schindler, K., Roth, S., & Schiele, B. (2013). Learning People Detectors for Tracking in Crowded Scenes. In ICCV 2013 (pp. 1049-1056). Los Alamitos, CA: IEEE Computer Society. doi:10.1109/ICCV.2013.134.

Item is

 

einblenden: alle ausblenden: alle

Basisdaten

einblenden: ausblenden:
Datensatz-Permalink: https://hdl.handle.net/11858/00-001M-0000-0017-B185-E Versions-Permalink: https://hdl.handle.net/21.11116/0000-000E-21E8-7
Genre: Konferenzbeitrag

Dateien

einblenden: Dateien
ausblenden: Dateien
:
tang_iccv_13.pdf (beliebiger Volltext), 3MB
 
Datei-Permalink:
-
Name:
tang_iccv_13.pdf
Beschreibung:
-
OA-Status:
Sichtbarkeit:
Privat
MIME-Typ / Prüfsumme:
application/pdf
Technische Metadaten:
Copyright Datum:
-
Copyright Info:
-
Lizenz:
-

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Tang, Siyu1, Autor           
Andriluka, Mykhaylo1, Autor           
Milan, Anton2, Autor
Schindler, Konrad2, Autor
Roth, Stefan2, Autor
Schiele, Bernt1, Autor                 
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2External Organizations, ou_persistent22              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: People tracking in crowded real-world scenes is challenging due to frequent and long-term occlusions. Recent tracking methods obtain the image evidence from object (people) detectors, but typically use off-the-shelf detectors and treat them as black box components. In this paper we argue that for best performance one should explicitly train people detectors on failure cases of the overall tracker instead. To that end, we first propose a novel joint people detector that combines a state-of-the-art single person detector with a detector for pairs of people, which explicitly exploits common patterns of person-person occlusions across multiple viewpoints that are a common failure case for tracking in crowded scenes. To explicitly address remaining failure cases of the tracker we explore two methods. First, we analyze typical failure cases of trackers and train a detector explicitly on those failure cases. And second, we train the detector with the people tracker in the loop, focusing on the most common tracker failures. We show that our joint multi-person detector significantly improves both detection accuracy as well as tracker performance, improving the state-of-the-art on standard benchmarks.

Details

einblenden:
ausblenden:
Sprache(n): eng - English
 Datum: 20132013-12
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: BibTex Citekey: 766
DOI: 10.1109/ICCV.2013.134
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: IEEE International Conference on Computer Vision
Veranstaltungsort: Sydney, Australia
Start-/Enddatum: 2013-12-01 - 2013-12-08

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: ICCV 2013
  Kurztitel : ICCV 2013
  Untertitel : 2013 IEEE International Conference on Computer Vision ; 1 - 8 December 2013 Sydney, NSW, Australia ; Proceedings
Genre der Quelle: Konferenzband
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: Los Alamitos, CA : IEEE Computer Society
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 1049 - 1056 Identifikator: -