Leibe, Bastian ; Mikolajczyk, Krystian ; Schiele, Bernt (2006)
Segmentation based multi-cue integration for object detection.
17th British Machine Vision Conference (BMVC06). Edinburgh (04.09.2007-07.09.2007)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
This paper proposes a novel method for integrating multiple local cues, i.e. local region detectors as well as descriptors, in the context of object detection. Rather than to fuse the outputs of several distinct classifiers in a fixed setup, our approach implements a highly flexible combination scheme, where the contributions of all individual cues are flexibly recombined depending on their explanatory power for each new test image. The key idea behind our approach is to integrate the cues over an estimated top-down segmentation, which allows to quantify how much each of them contributed to the object hypothesis. By combining those contributions on a per-pixel level, our approach ensures that each cue only contributes to object regions for which it is confident and that potential correlations between cues are effectively factored out. Experimental results on several benchmark data sets show that the proposed multi-cue combination scheme significantly increases detection performancecomparedto any of its constituent cues alone. Moreover, it provides an interesting evaluation tool to analyze the complementarity of local feature detectors and descriptors.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2006 |
| Autor(en): | Leibe, Bastian ; Mikolajczyk, Krystian ; Schiele, Bernt |
| Art des Eintrags: | Bibliographie |
| Titel: | Segmentation based multi-cue integration for object detection |
| Sprache: | Englisch |
| Publikationsjahr: | 2006 |
| Ort: | Edinburgh |
| Verlag: | BMVA |
| Buchtitel: | British Machine Vision Conference 2006, BMVC06. Proceedings |
| Veranstaltungstitel: | 17th British Machine Vision Conference (BMVC06) |
| Veranstaltungsort: | Edinburgh |
| Veranstaltungsdatum: | 04.09.2007-07.09.2007 |
| Kurzbeschreibung (Abstract): | This paper proposes a novel method for integrating multiple local cues, i.e. local region detectors as well as descriptors, in the context of object detection. Rather than to fuse the outputs of several distinct classifiers in a fixed setup, our approach implements a highly flexible combination scheme, where the contributions of all individual cues are flexibly recombined depending on their explanatory power for each new test image. The key idea behind our approach is to integrate the cues over an estimated top-down segmentation, which allows to quantify how much each of them contributed to the object hypothesis. By combining those contributions on a per-pixel level, our approach ensures that each cue only contributes to object regions for which it is confident and that potential correlations between cues are effectively factored out. Experimental results on several benchmark data sets show that the proposed multi-cue combination scheme significantly increases detection performancecomparedto any of its constituent cues alone. Moreover, it provides an interesting evaluation tool to analyze the complementarity of local feature detectors and descriptors. |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Multimodale Interaktive Systeme |
| Hinterlegungsdatum: | 20 Nov 2008 08:25 |
| Letzte Änderung: | 28 Nov 2024 10:57 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum