Relaxed Pairwise Learned Metric for Person Re-identification

Martin Hirzer, Peter Roth, Martin Köstinger, Horst Bischof

Publikation: Beitrag in Buch/Bericht/KonferenzbandBeitrag in einem Konferenzband

Abstract

Matching persons across non-overlapping cameras is a rather challenging task. Thus, successful methods often build on complex feature representations or sophisticated learners. A recent trend to tackle this problem is to use metric learning to find a suitable space for matching samples from different cameras. However, most of these approaches ignore the transition from one camera to the other. In this paper, we propose to learn a metric from pairs of samples from different cameras. In this way, even less sophisticated features describing color and texture information are sufficient for finally getting state-of-the-art classification results. Moreover, once the metric has been learned, only linear projections are necessary at search time, where a simple nearest neighbor classification is performed. The approach is demonstrated on three publicly available datasets of different complexity, where it can be seen that state-of-the-art results can be obtained at much lower computational costs.
Originalspracheenglisch
TitelProceedings of the European Conference on Computer Vision (ECCV)
Herausgeber (Verlag).
Seiten780-793
DOIs
PublikationsstatusVeröffentlicht - 2012
Veranstaltung12th European Conference on Computer Vision: ECCV 2012 - Florenz, Italien
Dauer: 7 Okt 201213 Okt 2012

Konferenz

Konferenz12th European Conference on Computer Vision
KurztitelECCV 2012
LandItalien
OrtFlorenz
Zeitraum7/10/1213/10/12

Fields of Expertise

  • Information, Communication & Computing

Fingerprint

Untersuchen Sie die Forschungsthemen von „Relaxed Pairwise Learned Metric for Person Re-identification“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren