Activities per year
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.
|Title of host publication||Proceedings of the European Conference on Computer Vision (ECCV)|
|Publication status||Published - 2012|
|Event||12th European Conference on Computer Vision: ECCV 2012 - Florenz, Italy|
Duration: 7 Oct 2012 → 13 Oct 2012
|Conference||12th European Conference on Computer Vision|
|Abbreviated title||ECCV 2012|
|Period||7/10/12 → 13/10/12|
Fields of Expertise
- Information, Communication & Computing
FingerprintDive into the research topics of 'Relaxed Pairwise Learned Metric for Person Re-identification'. Together they form a unique fingerprint.
- 1 Poster presentation
Martin Hirzer (Speaker)7 Oct 2012 → 13 Oct 2012
Activity: Talk or presentation › Poster presentation › Science to science