Matching vehicles under large pose transformations using approximate 3D models and piecewise MRF model

We propose a robust object recognition method based on approximate 3D models that can effectively match objects under large viewpoint changes and partial occlusion. The specific problem we solve is: given two views of an object, determine if the views are for the same or different object. Our domain...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Yanlin Guo, Cen Rao, Samarasekera, S., Kim, J., Kumar, R., Sawhney, H.
Format:	Tagungsbericht
Sprache:	eng
Schlagworte:	Belief propagation Feature extraction Geometry Lighting Markov random fields Object recognition Robustness Solid modeling Surveillance Vehicles
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!