Probabilistic active recognition of multiple objects using hough-based geometric matching features

Book section

3D Object recognition is an important task for mobile platforms to dynamically interact in human environments. This computer vision task also plays a fundamental role in the areas of automated surveillance, Simultaneous Localization and Mapping (SLAM) applications for robots and video retrieval. The recognition of objects in realistic circumstances, where multiple objects may appear together with significant occlusions and clutter from distracter objects, is a complicated and challenging problem. Particularly in such situations multiple viewpoints are necessary for recognition [17] as single viewpoints may be of poor quality and not contain sufficient information to reliably recognise or verify all objects’ identities unambiguously.

Authors: Govender, N; Torr, P; Keaikitse, M; Nicolls, F; Warrell, J

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer
• Host title: New Development in Robot Vision
• Pages: 89-109
• Chapter number: 6
• Series: Cognitive Systems Monographs
• Series number: 23
• Publication date: 2014-09-26
• DOI: 10.1007/978-3-662-43859-6_6
• EISSN: 1867-4933
• ISSN: 1867-4925
• EISBN: 9783662438596
• ISBN: 9783662438589
• Language: English
• Keywords: mutual information; training image; active recognition; scale invariant feature transform; distracter object