De Villiers, JJermy, R2014-05-262014-05-262013-12De Villiers, J and Jermy, R. 2013. An analysis of fusion algorithms for LWIR and visual images. In: 24th Annual symposium of the Pattern Recognition Association of South Africa, Johannesburg, South Africa, 3 December 2013http://www.prasa.org/proceedings/2013/prasa2013-02.pdfhttp://hdl.handle.net/10204/743324th Annual symposium of the Pattern Recognition Association of South Africa, Johannesburg, South Africa, 3 December 2013This paper presents a comparison of methods to fuse pre-registered colour visual and long wave infra-red images to create a new image containing both visual and thermal cues. Three methods of creating the artificially coloured fused images are presented. These three methods along with the raw visual and LWIR imagery are then evaluated using the Analytical Hierarchy Process for three different scenarios using a set of 32 observers. The scenarios entail bright, dim and dark conditions which directly affect the amount of visual information available. Both the standard method and a novel voting methodology are used to evaluate the results, the latter providing similar ranking but better discrimination between the voter’s preferences. The results show that fused images are preferred for non-dark conditions with the thermal based hue offset algorithm being preferred.enLong wave infrared imageryFusion algorithmsPre-registered colour visualThermal cuesLWIRAnalytical Hierarchy ProcessConference PresentationDe Villiers, J., & Jermy, R. (2013). An analysis of fusion algorithms for LWIR and visual images. PRASA 2013 Proceedings. http://hdl.handle.net/10204/7433De Villiers, J, and R Jermy. "An analysis of fusion algorithms for LWIR and visual images." (2013): http://hdl.handle.net/10204/7433De Villiers J, Jermy R, An analysis of fusion algorithms for LWIR and visual images; PRASA 2013 Proceedings; 2013. http://hdl.handle.net/10204/7433 .TY - Conference Presentation AU - De Villiers, J AU - Jermy, R AB - This paper presents a comparison of methods to fuse pre-registered colour visual and long wave infra-red images to create a new image containing both visual and thermal cues. Three methods of creating the artificially coloured fused images are presented. These three methods along with the raw visual and LWIR imagery are then evaluated using the Analytical Hierarchy Process for three different scenarios using a set of 32 observers. The scenarios entail bright, dim and dark conditions which directly affect the amount of visual information available. Both the standard method and a novel voting methodology are used to evaluate the results, the latter providing similar ranking but better discrimination between the voter’s preferences. The results show that fused images are preferred for non-dark conditions with the thermal based hue offset algorithm being preferred. DA - 2013-12 DB - ResearchSpace DP - CSIR KW - Long wave infrared imagery KW - Fusion algorithms KW - Pre-registered colour visual KW - Thermal cues KW - LWIR KW - Analytical Hierarchy Process LK - https://researchspace.csir.co.za PY - 2013 T1 - An analysis of fusion algorithms for LWIR and visual images TI - An analysis of fusion algorithms for LWIR and visual images UR - http://hdl.handle.net/10204/7433 ER -