Towards multispectral, multi‐sensor indoor positioning and target identification. Issue 15 (1st July 2017)

• Record Type: Journal Article
• Authors: Kaasalainen, S.; Ruotsalainen, L.; Kirkko‐Jaakkola, M.; Nevalainen, O.; Hakala, T.
• Is Part Of: Electronics letters. Volume 53:Issue 15(2017)
• Page Start: 1008
• Page End: 1011
• Publication Date: 2017-07-01
• Subjects: image fusion -- image segmentation -- learning (artificial intelligence) -- statistical analysis -- real‐time systems; enhanced decision fusion -- semantically segmented images -- local majority saliency map -- ensemble machine learning schemes -- voting algorithm -- statistical perspective -- decision redundancy -- real‐time systems -- uncertainty challenges -- saliency map generation -- local majority filter -- pixel labelling -- random decision forest model -- intermediate labelled images -- voting pool; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2017.1473
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : A concept and first results of combining multispectral light detection and ranging (LiDAR) with positioning sensors to produce spatially resolved target identification in indoor environment is presented. The aim is to enhance the sensor‐based indoor localisation with a multispectral target identification and mapping. There is a growing need for automatic and mobile mapping and surveillance in buildings and locations where satellite positioning is not available. LiDAR is a common sensor in feature‐based simultaneous localisation and mapping. As multispectral LiDARs are emerging and becoming increasingly popular in research applications, the multi/hyperspectral point clouds are likely to improve object recognition and enable a new level of autonomous surveillance in the near future. The first results show that position solution can be obtained using sensors attached to the LiDAR.