Sabatta, DG2009-05-182009-05-182008-11Sabatta, DG. 2008. Vision-based topological map building and localisation using persistent features. Robotics and Mechatronics Symposium, Bloemfontein, South Africa, 11 November 2008, pp 1-69780620424639http://hdl.handle.net/10204/3388Robotics and Mechatronics Symposium, Bloemfontein, South Africa, 11 November 2008This paper proposes a topological mapping technique that utilises persistent SIFT features to reduce the amount of data storage required. It delivers, as an output, a topological map that lends itself well to conventional path planning techniques. The approach assimilates features into a statistical model which promises improved data association. Experiments were performed using omnidirectional camera images from the Cogniron dataset. A map was constructed from one of the supplied routes and the performance of the localisation algorithm evaluated using another route within the same environment. Thereafter the map was updated using the comparison route and the results discussed. The statistical feature association approach is shown to be more robust than conventional methodsenTopological map techniqueLocalisation algorithmRoboticsScale invariant feature transform (SIFT)SIFT featuresDatasetsMapsVision-based topological map buildingMechatronics symposiumConference PresentationSabatta, D. (2008). Vision-based topological map building and localisation using persistent features. http://hdl.handle.net/10204/3388Sabatta, DG. "Vision-based topological map building and localisation using persistent features." (2008): http://hdl.handle.net/10204/3388Sabatta D, Vision-based topological map building and localisation using persistent features; 2008. http://hdl.handle.net/10204/3388 .TY - Conference Presentation AU - Sabatta, DG AB - This paper proposes a topological mapping technique that utilises persistent SIFT features to reduce the amount of data storage required. It delivers, as an output, a topological map that lends itself well to conventional path planning techniques. The approach assimilates features into a statistical model which promises improved data association. Experiments were performed using omnidirectional camera images from the Cogniron dataset. A map was constructed from one of the supplied routes and the performance of the localisation algorithm evaluated using another route within the same environment. Thereafter the map was updated using the comparison route and the results discussed. The statistical feature association approach is shown to be more robust than conventional methods DA - 2008-11 DB - ResearchSpace DP - CSIR KW - Topological map technique KW - Localisation algorithm KW - Robotics KW - Scale invariant feature transform (SIFT) KW - SIFT features KW - Datasets KW - Maps KW - Vision-based topological map building KW - Mechatronics symposium LK - https://researchspace.csir.co.za PY - 2008 SM - 9780620424639 T1 - Vision-based topological map building and localisation using persistent features TI - Vision-based topological map building and localisation using persistent features UR - http://hdl.handle.net/10204/3388 ER -