Sabatta, DScaramuzza, DSiegwart, R2010-07-152010-07-152010-05Sabatta, D, Scaramuzza, D and Siegwart, R. 2010. Improved appearance-based matching in similar and dynamic environments using a vocabulary tree. 2010 IEEE International Conference on Robotics and Automation. 3-8 May 2010, Anchorange, Alaska, USA, pp 1008-1013978-1-4244-5040-4http://hdl.handle.net/10204/40942010 IEEE International Conference on Robotics and Automation. 3-8 May 2010, Anchorange, Alaska, USA.In this paper the authors present a topological map building algorithm based on a Vocabulary Tree that is robust to features present in dynamic or similar environments. The algorithm recognises incorrect loop closures, not supported by the odometry, and uses this information to update the feature weights in the tree to suppress further associations from these features. Two methods of adjusting these feature entropies are proposed, one decreasing entropy related to incorrect features in a uniform manner and the other proportional to the contribution of the said feature. Preliminary results showing the performance of the proposed method are presented where it is found that by adjusting the feature entropies, the number of incorrect associations can be reduced while improving the quality of the correct matchesenVocabulary treeAppearance-based mappingTopological map buildingRoboticsConference PresentationSabatta, D., Scaramuzza, D., & Siegwart, R. (2010). Improved appearance-based matching in similar and dynamic environments using a vocabulary tree. Institute of Electrical and Electronics Engineers (IEEE). http://hdl.handle.net/10204/4094Sabatta, D, D Scaramuzza, and R Siegwart. "Improved appearance-based matching in similar and dynamic environments using a vocabulary tree." (2010): http://hdl.handle.net/10204/4094Sabatta D, Scaramuzza D, Siegwart R, Improved appearance-based matching in similar and dynamic environments using a vocabulary tree; Institute of Electrical and Electronics Engineers (IEEE); 2010. http://hdl.handle.net/10204/4094 .TY - Conference Presentation AU - Sabatta, D AU - Scaramuzza, D AU - Siegwart, R AB - In this paper the authors present a topological map building algorithm based on a Vocabulary Tree that is robust to features present in dynamic or similar environments. The algorithm recognises incorrect loop closures, not supported by the odometry, and uses this information to update the feature weights in the tree to suppress further associations from these features. Two methods of adjusting these feature entropies are proposed, one decreasing entropy related to incorrect features in a uniform manner and the other proportional to the contribution of the said feature. Preliminary results showing the performance of the proposed method are presented where it is found that by adjusting the feature entropies, the number of incorrect associations can be reduced while improving the quality of the correct matches DA - 2010-05 DB - ResearchSpace DP - CSIR KW - Vocabulary tree KW - Appearance-based mapping KW - Topological map building KW - Robotics LK - https://researchspace.csir.co.za PY - 2010 SM - 978-1-4244-5040-4 T1 - Improved appearance-based matching in similar and dynamic environments using a vocabulary tree TI - Improved appearance-based matching in similar and dynamic environments using a vocabulary tree UR - http://hdl.handle.net/10204/4094 ER -