Open AccessTOWARDS AUTOMATIC SINGLE-SENSOR MAPPING BY MULTISPECTRAL AIRBORNE LASER SCANNING
Author(s) -
Eero Ahokas,
Juha Hyyppä,
X. Yu,
X. Liang,
Leena Matikainen,
Kirsi Karila,
Paula Litkey,
A. Kukko,
A. Jaakkola,
H. Kaartinen,
Markus Holopainen,
Mikko Vastaranta
Publication year - 2016
Publication title -
the international archives of the photogrammetry, remote sensing and spatial information sciences/international archives of the photogrammetry, remote sensing and spatial information sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.264
H-Index - 71
eISSN - 1682-1777
pISSN - 1682-1750
DOI - 10.5194/isprsarchives-xli-b3-155-2016
Subject(s) - remote sensing , multispectral image , laser scanning , point cloud , land cover , deciduous , forest inventory , taiga , environmental science , reference data , multispectral scanner , multispectral pattern recognition , geography , computer science , forestry , land use , forest management , artificial intelligence , laser , data mining , ecology , optics , physics , biology
This paper describes the possibilities of the Optech Titan multispectral airborne laser scanner in the fields of mapping and forestry. Investigation was targeted to six land cover classes. Multispectral laser scanner data can be used to distinguish land cover classes of the ground surface, including the roads and separate road surface classes. For forest inventory using point cloud metrics and intensity features combined, total accuracy of 93.5% was achieved for classification of three main boreal tree species (pine, spruce and birch).When using intensity features – without point height metrics - a classification accuracy of 91% was achieved for these three tree species. It was also shown that deciduous trees can be further classified into more species. We propose that intensity-related features and waveform-type features are combined with point height metrics for forest attribute derivation in area-based prediction, which is an operatively applied forest inventory process in Scandinavia. It is expected that multispectral airborne laser scanning can provide highly valuable data for city and forest mapping and is a highly relevant data asset for national and local mapping agencies in the near future.