Projekte pro Jahr
Abstract
Person re-identification, i.e., recognizing a single person across spatially disjoint cameras, is an important task in visual surveillance. Existing approaches either try to find a suitable description of the appearance or learn a discriminative model. Since these different representational strategies capture a large extent of complementary information we propose to combine both approaches. First, given a specific query, we rank all samples according to a feature-based similarity, where appearance is modeled by a set of region covariance descriptors. Next, a discriminative model is learned using boosting for feature selection, which provides a more specific classifier. The proposed approach is demonstrated on two datasets, where we show that the combination of a generic descriptive statistical model and a discriminatively learned feature-based model attains considerably better results than the individual models alone. In addition, we give a comparison to the state-of-the-art on a publicly available benchmark dataset.
Originalsprache | englisch |
---|---|
Titel | Proceedings of the Scandinavian Conference on Image Analysis (SCIA) |
Herausgeber (Verlag) | . |
Seiten | 91-102 |
Publikationsstatus | Veröffentlicht - 2011 |
Veranstaltung | Scandinavian Conference on Image Analysis - Ystad Saltsjöbad, Schweden Dauer: 23 Mai 2011 → 27 Mai 2011 |
Konferenz
Konferenz | Scandinavian Conference on Image Analysis |
---|---|
Land/Gebiet | Schweden |
Ort | Ystad Saltsjöbad |
Zeitraum | 23/05/11 → 27/05/11 |
Fields of Expertise
- Information, Communication & Computing
Fingerprint
Untersuchen Sie die Forschungsthemen von „Person Re-Identification by Descriptive and Discriminative Classification“. Zusammen bilden sie einen einzigartigen Fingerprint.Projekte
- 1 Abgeschlossen
Aktivitäten
- 1 Posterpräsentation
-
Poster Presentation: Person Re-Identification by Descriptive and Discriminative Classification
Martin Hirzer (Redner/in)
23 Mai 2011 → 27 Mai 2011Aktivität: Vortrag oder Präsentation › Posterpräsentation › Science to science