You are in:Home/Publications/” Aerial images and lidar data fusion for automatic feature extraction using the self-organizing map (SOM) classifier”, In: Bretar F, Pierrot-Deseilligny M, Vosselman G (Eds), Laser scanning 2009, IAPRS, Vol. XXXVIII, Part 3/W8 – Paris, France, September 1-2, pp. 317 – 322

Prof. Ahmed Abdel Sattar Shaker :: Publications:

Title:
” Aerial images and lidar data fusion for automatic feature extraction using the self-organizing map (SOM) classifier”, In: Bretar F, Pierrot-Deseilligny M, Vosselman G (Eds), Laser scanning 2009, IAPRS, Vol. XXXVIII, Part 3/W8 – Paris, France, September 1-2, pp. 317 – 322
Authors: Salah, M., Trinder, J., Shaker A., Hamed, M. and ELsagheer, A
Year: 2009
Keywords: Not Available
Journal: Not Available
Volume: Not Available
Issue: Not Available
Pages: Not Available
Publisher: Not Available
Local/International: International
Paper Link: Not Available
Full paper Not Available
Supplementary materials Not Available
Abstract:

This paper presents work on the development of automatic feature extraction from multispectral aerial images and lidar data based on test data from two different study areas with different characteristics. First, we filtered the lidar point clouds to generate a Digital Terrain Model (DTM) using a novel filtering technique based on a linear first-order equation which describes a tilted plane surface, and then the Digital Surface Model (DSM) and the Normalised Digital Surface Model (nDSM) were generated. After that a total of 22 uncorrelated feature attributes have been generated from the aerial images, the lidar intensity image, DSM and nDSM. The attributes include those derived from the Grey Level Co-occurrence Matrix (GLCM), Normalized Difference Vegetation Indices (NDVI) and slope. Finally, a SOM was used to detect buildings, trees, roads and grass from the aerial image, lidar data and the generated attributes. The results show that using lidar data in the SOM improves the accuracy of feature detection by 38% compared with using aerial photography alone, while using the generated attributes as well improve the detection results by a further 10%. The results also show that the following attributes contributed most significantly to detection of buildings, trees, roads and grass respectively: entropy (from GLCM) derived from nDSM; slope derived from nDSM; homogeneity (from the GLCM) derived from nDSM; and homogeneity derived from nDSM

Google ScholarAcdemia.eduResearch GateLinkedinFacebookTwitterGoogle PlusYoutubeWordpressInstagramMendeleyZoteroEvernoteORCIDScopus