DocumentCode :
6982
Title :
Geomorphological Change Detection Using Object-Based Feature Extraction From Multi-Temporal LiDAR Data
Author :
Anders, N.S. ; Seijmonsbergen, A.C. ; Bouten, W.
Author_Institution :
Inst. for Biodiversity & Ecosyst. Dynamics, Univ. of Amsterdam, Amsterdam, Netherlands
Volume :
10
Issue :
6
fYear :
2013
fDate :
Nov. 2013
Firstpage :
1587
Lastpage :
1591
Abstract :
Multi-temporal LiDAR digital terrain models (DTMs) are used for the development and testing of a method for geomorphological change analysis in western Austria. Point data from two airborne LiDAR campaigns of 2003 and 2011 were filtered and interpolated into two 2m DTMs. Seven geomorphological features were mapped by using stratified object-based image analysis (OBIA) using terrain properties derived from the DTMs. Segmentation parameters and classification rules were set and applied to both data sets which allowed analysis of geomorphological change between 2003 and 2011. Volumetric change was calculated and summarized by their landform category. The multi-temporal landform classifications show where landforms changed into other landforms as the result of geomorphological process activity. However, differences in point densities and lack of data points below dense forest hindered accurate geomorphological change detection in these areas. When challenges related to interpolation techniques are tackled, stratified OBIA of multi-temporal LiDAR data sets is a promising tool for geomorphological change detection, and affiliated applications such as monitoring risk and natural hazards, rate of change analyses, and vulnerability assessments.
Keywords :
feature extraction; geomorphology; geophysical image processing; geophysical techniques; image classification; image segmentation; optical radar; remote sensing by laser beam; AD 2003 to 2011; airborne LiDAR campaigns; change analysis rate; classification rules; geomorphological change analysis; geomorphological change detection; geomorphological features; geomorphological process activity; multitemporal LiDAR data; multitemporal LiDAR digital terrain models; multitemporal landform classifications; natural hazards; object-based feature extraction; point densities; segmentation parameters; stratified object-based image analysis; vulnerability assessments; western Austria; Austria; LiDAR; change detection; classification; geomorphology; multi-temporal; segmentation;
fLanguage :
English
Journal_Title :
Geoscience and Remote Sensing Letters, IEEE
Publisher :
ieee
ISSN :
1545-598X
Type :
jour
DOI :
10.1109/LGRS.2013.2262317
Filename :
6545299
Link To Document :
بازگشت