Govender, NatashaWarrell, JTorr, PNicolls, F2014-10-092014-10-092013-09Govender, N., Warrell, J., Torr, P. and Nicolls, F. 2013. Probabilistic object and viewpoint models for active object recognition. In: IEEE Africon 2013, Mauritius, 9-12 September 2013http://www.robots.ox.ac.uk/~tvg/publications/2013/Govender_2013_africon_probablistic1.pdfhttp://hdl.handle.net/10204/7714IEEE Africon 2013, Mauritius, 9-12 September 2013For mobile robots to perform certain tasks in human environments, fast and accurate object verification and recognition is essential. Bayesian approaches to active object recognition have proved effective in a number of cases, allowing information across views to be integrated in a principled manner, and permitting a principled approach to data acquisition. Existing approaches however mostly rely on probabilistic models which make simplifying assumptions such as that features may be treated independently and that objects will appear without clutter at test time. We develop a number of probabilistic object and viewpoint models which are explicitly designed to cope with situations in which these assumptions fail, and show these to perform well in a Bayesian active recognition setting using test data in which objects appear in cluttered environments with significant occlusion.enMobile robots3D Object recognitionSimultaneous Localization and MappingSLAMConference PresentationGovender, N., Warrell, J., Torr, P., & Nicolls, F. (2013). Probabilistic object and viewpoint models for active object recognition. http://hdl.handle.net/10204/7714Govender, Natasha, J Warrell, P Torr, and F Nicolls. "Probabilistic object and viewpoint models for active object recognition." (2013): http://hdl.handle.net/10204/7714Govender N, Warrell J, Torr P, Nicolls F, Probabilistic object and viewpoint models for active object recognition; 2013. http://hdl.handle.net/10204/7714 .TY - Conference Presentation AU - Govender, Natasha AU - Warrell, J AU - Torr, P AU - Nicolls, F AB - For mobile robots to perform certain tasks in human environments, fast and accurate object verification and recognition is essential. Bayesian approaches to active object recognition have proved effective in a number of cases, allowing information across views to be integrated in a principled manner, and permitting a principled approach to data acquisition. Existing approaches however mostly rely on probabilistic models which make simplifying assumptions such as that features may be treated independently and that objects will appear without clutter at test time. We develop a number of probabilistic object and viewpoint models which are explicitly designed to cope with situations in which these assumptions fail, and show these to perform well in a Bayesian active recognition setting using test data in which objects appear in cluttered environments with significant occlusion. DA - 2013-09 DB - ResearchSpace DP - CSIR KW - Mobile robots KW - 3D Object recognition KW - Simultaneous Localization and Mapping KW - SLAM LK - https://researchspace.csir.co.za PY - 2013 T1 - Probabilistic object and viewpoint models for active object recognition TI - Probabilistic object and viewpoint models for active object recognition UR - http://hdl.handle.net/10204/7714 ER -