DBPapers
DOI: 10.5593/SGEM2014/B23/S10.016

DATA FUSION AND SUPERVISED CLASSIFICATIONS WITH LIDAR DATA AND MULTISPECTRAL IMAGERY

O. Sinagra, S. Lim
Wednesday 1 October 2014 by Libadmin2014

References: 14th International Multidisciplinary Scientific GeoConference SGEM 2014, www.sgem.org, SGEM2014 Conference Proceedings, ISBN 978-619-7105-12-4 / ISSN 1314-2704, June 19-25, 2014, Book 2, Vol. 3, 129-136 pp

ABSTRACT
The proposed research aims to amalgamate a lidar point cloud and a multispectral image in order to classify the surveyed area into chosen categories by using a supervised classification algorithm. An airborne lidar point cloud and a QuickBird satellite image of Red, Green, Blue, and Near-Infrared bands over a city of Strasbourg, France, were processed to achieve the data fusion and estimate the accuracy of the proposed method. Firstly, the multispectral image was used to create three raster images representing Normalised Difference Vegetation Index (NDVI), Soil-Adjusted Vegetation Index (SAVI), and Global Environment Monitoring Index (GEMI), respectively. Secondly, the lidar point cloud was used to calculate the height of the features above ground and the 3-dimensional information was converted to a raster image. In total, seven different rasters were created by combining the aforementioned four rasters and tested to determine the best combination. A supervised classification method known as the Support Vector Machine (SVM) algorithm was applied to the rasters to classify them into three categories: ground, vegetation, and artificial objects. Confusion matrices of the classification results indicate that the overall accuracy of the classification improves when the lidar data is integrated rather than the multispectral imagery is used alone.

Keywords: Lidar, multispectral image, supervised classification, support vector machine, data fusion.