A Bayesian approach for place recognition
Ramos, Fabio. T, Upcroft, Ben, Kumar, Suresh, & Durrant-Whyte, Hugh. F (2005) A Bayesian approach for place recognition. In Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence IJCAI-05 Workshop on Reasoning with Uncertainty in Robotics (RUR-05), International Joint Conference on Artificial Intelligence, Edinburgh Scotland UK.
This paper presents a robust place recognition algorithm for mobile robots. The framework proposed combines nonlinear dimensionality reduction, nonlinear regression under noise, and variational Bayesian learning to create consistent probabilistic representations of places from images. These generative models are learnt from a few images and used for multi-class place recognition where classification is computed from a set of feature-vectors. Recognition can be performed in near real-time and accounts for complexity such as changes in illumination, occlusions and blurring. The algorithm was tested with a mobile robot in indoor and outdoor environments with sequences of 1579 and 3820 images respectively. This framework has several potential applications such as map building, autonomous navigation, search-rescue tasks and context recognition.
Impact and interest:
Citation counts are sourced monthly from and citation databases.
Citations counts from theindexing service can be viewed at the linked Google Scholar™ search.
|Item Type:||Conference Paper|
|Additional Information:||RUR05 Workshop notes http://www.cs.mcgill.ca/~jpineau/files/rur05notes.pdf|
|Keywords:||Algorithm, mobile robots, Bayesian, place recognition|
|Subjects:||Australian and New Zealand Standard Research Classification > ENGINEERING (090000) > ELECTRICAL AND ELECTRONIC ENGINEERING (090600)|
|Divisions:||Past > QUT Faculties & Divisions > Faculty of Built Environment and Engineering
Past > Schools > School of Engineering Systems
|Copyright Owner:||[Please consult author]|
|Deposited On:||10 May 2011 01:18|
|Last Modified:||01 Mar 2012 00:59|
Repository Staff Only: item control page