Price, MGreen, JDickens, J2012-02-082012-02-082011-11Price, M, Green, J and Dickens, J. Creating three-dimensional thermal maps. 4th Robotics and Mechatronics Conference, CSIR International Convention Centre, Pretoria, South Africa, 23-15 November 2011978-0-620-51897-0http://www.robmech.co.za/files/default/proceedings/robm_proceedings_3.pdfhttp://hdl.handle.net/10204/55544th Robotics and Mechatronics Conference, CSIR International Convention Centre, Pretoria, South Africa, 23-15 November 2011A method for generating 3D maps of mines with thermal imaging texture from a robotic platform is presented. The objective is to use these models to generate risk maps that can be used to assess mine safety. Analysis will take place offline, but the data collection platform will be autonomous. Our registration method is based on aligning 3D descriptors that are extracted from range images and uses ICP for refinement. The descriptors encode the distribution of radial distances in the vicinity of keypoints, and enable alignment of non-sequential scans that are visibly different. Thermal texture is added to the registered point cloud using a once-off calibration between the 3D and thermal cameras. Two alternate visualisation schemes are discussed, and results are shown for a real mine stope.enThermal maps3-D thermal mapsRobotic platforms3d mappingMining roboticsThermal scanningConference PresentationPrice, M., Green, J., & Dickens, J. (2011). Creating three-dimensional thermal maps. RobMech. http://hdl.handle.net/10204/5554Price, M, J Green, and J Dickens. "Creating three-dimensional thermal maps." (2011): http://hdl.handle.net/10204/5554Price M, Green J, Dickens J, Creating three-dimensional thermal maps; RobMech; 2011. http://hdl.handle.net/10204/5554 .TY - Conference Presentation AU - Price, M AU - Green, J AU - Dickens, J AB - A method for generating 3D maps of mines with thermal imaging texture from a robotic platform is presented. The objective is to use these models to generate risk maps that can be used to assess mine safety. Analysis will take place offline, but the data collection platform will be autonomous. Our registration method is based on aligning 3D descriptors that are extracted from range images and uses ICP for refinement. The descriptors encode the distribution of radial distances in the vicinity of keypoints, and enable alignment of non-sequential scans that are visibly different. Thermal texture is added to the registered point cloud using a once-off calibration between the 3D and thermal cameras. Two alternate visualisation schemes are discussed, and results are shown for a real mine stope. DA - 2011-11 DB - ResearchSpace DP - CSIR KW - Thermal maps KW - 3-D thermal maps KW - Robotic platforms KW - 3d mapping KW - Mining robotics KW - Thermal scanning LK - https://researchspace.csir.co.za PY - 2011 SM - 978-0-620-51897-0 T1 - Creating three-dimensional thermal maps TI - Creating three-dimensional thermal maps UR - http://hdl.handle.net/10204/5554 ER -