Fusion of hyperspectral and LiDAR data in classification of urban areas

Ghamisi, Pedram, Benediktsson, Jon Atli and Phinn, Stuart (2014). Fusion of hyperspectral and LiDAR data in classification of urban areas. In: Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International. Joint 2014 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2014 and the 35th Canadian Symposium on Remote Sensing, CSRS 2014, Quebec City, QC Canada, (181-184). 13 - 18 July 2014. doi:10.1109/IGARSS.2014.6946386

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads

Author Ghamisi, Pedram
Benediktsson, Jon Atli
Phinn, Stuart
Title of paper Fusion of hyperspectral and LiDAR data in classification of urban areas
Conference name Joint 2014 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2014 and the 35th Canadian Symposium on Remote Sensing, CSRS 2014
Conference location Quebec City, QC Canada
Conference dates 13 - 18 July 2014
Convener Monique Bernier
Proceedings title Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International
Series International Geoscience and Remote Sensing Symposium (IGARSS)
Place of Publication Piscataway, NJ United States
Publisher Institute of Electrical and Electronics Engineers
Publication Year 2014
Year available 2014
Sub-type Fully published paper
DOI 10.1109/IGARSS.2014.6946386
Open Access Status
ISBN 9781479957750
Start page 181
End page 184
Total pages 4
Collection year 2015
Language eng
Formatted Abstract/Summary
in this paper, the fusion of hyperspectral and LiDAR data is taken into account in order to develop a new classification framework for the accurate analysis of urban areas. In this method, an attribute profile is considered in order to model the spatial information of LiDAR and hyperspectral data. In parallel, in order to reduce the redundancy of the hyperspectral data and address the so-called curse of dimensionality, a supervised feature extraction technique is used. Then, the new features obtained by the attribute profile and the supervised feature extraction technique are concatenated into a stacked vector. The final classification map is achieved by using a Random Forest classifier. Results infer that the proposed method can provide very good results in terms of classification accuracy and CPU processing time in an automatic manner
Keyword Data fusion
Hyperspectral
LiDAR
Random forest
Supervised feature extraction
Q-Index Code E1
Q-Index Status Confirmed Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in Thomson Reuters Web of Science Article
Scopus Citation Count Cited 4 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 02 Dec 2014, 04:03:54 EST by System User on behalf of School of Geography, Planning & Env Management