TU Darmstadt / ULB / TUbiblio

Part Based Object Detection with a Flexible Context Constraint : Supporting Object Detection with Easy Context

Biehl, Karl Robert (2013)
Part Based Object Detection with a Flexible Context Constraint : Supporting Object Detection with Easy Context.
Technische Universität Darmstadt
Masterarbeit, Bibliographie

Kurzbeschreibung (Abstract)

This work describes an object detection system which integrates flexible spatial context constraints to improve detection performance. It allows spatial scale deformation of the object relative to its context. The contextual model extends an existing deformable parts model and is trained on partially labeled data using a latent SVM. The approach can be applied to any object detection problem where the object class always exists in the one typical image context, but the context can appear independently. A new scoring method is used to model the asymmetric relationship between object and context. Furthermore, the system enables the use of contextual non-maximum suppression, a context sensitive way to discard redundant detections. Trained on our combined dataset of dresses and persons, the system achieves a significant improvement in detection performance when compared with basic deformable parts models.

Typ des Eintrags: Masterarbeit
Erschienen: 2013
Autor(en): Biehl, Karl Robert
Art des Eintrags: Bibliographie
Titel: Part Based Object Detection with a Flexible Context Constraint : Supporting Object Detection with Easy Context
Sprache: Englisch
Publikationsjahr: 2013
Kurzbeschreibung (Abstract):

This work describes an object detection system which integrates flexible spatial context constraints to improve detection performance. It allows spatial scale deformation of the object relative to its context. The contextual model extends an existing deformable parts model and is trained on partially labeled data using a latent SVM. The approach can be applied to any object detection problem where the object class always exists in the one typical image context, but the context can appear independently. A new scoring method is used to model the asymmetric relationship between object and context. Furthermore, the system enables the use of contextual non-maximum suppression, a context sensitive way to discard redundant detections. Trained on our combined dataset of dresses and persons, the system achieves a significant improvement in detection performance when compared with basic deformable parts models.

Freie Schlagworte: Object detection, Deformable models, Constraints
Zusätzliche Informationen:

73 p.

Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Graphisch-Interaktive Systeme
Hinterlegungsdatum: 12 Nov 2018 11:16
Letzte Änderung: 12 Nov 2018 11:16
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen