TitleUnposed Object Recognition using an Active Approach
Publication TypeConference Proceedings
Year of Conference2013
AuthorsLawson, W, Trafton, JG
Conference NameInternational Conference on Computer VIsion Theory and Applications
Conference LocationBarcelona, Spain

Object recognition is a practical problem with a wide variety of potential applications. Recognition
becomes substantially more dicult when objects have not been presented in some logical, \posed"
manner selected by a human observer. We propose to solve this problem using active object
recognition, where the same object is viewed from multiple viewpoints when it is necessary to
gain condence in the classication decision. We demonstrate the eect of unposed objects on a
state-of-the-art approach to object recognition, then show how an active approach can increase
accuracy. The active approach works by attaching condence to recognition, prompting further
inspection when condence is low. We demonstrate a performance increase on a wide variety of
objects from the RGB-D database, showing a signicant increase in recognition accuracy.

Full Text
NRL Publication Release Number: