%0 Conference Proceedings
%4 sid.inpe.br/mtc-m18/2012/05.14.18.14
%2 sid.inpe.br/mtc-m18/2012/05.14.18.14.40
%@isbn 978-85-17-00059-1
%T Geomorphological change detection using object-based feature extraction from multi-temporal LiDAR data
%D 2012
%A Seijmonsbergen, Arie C.,
%A Anders, Niels S.,
%A Bouten, Willem,
%@electronicmailaddress a.c.seijmonsbergen@uva.nl
%@electronicmailaddress n.s.anders@uva.nl
%@electronicmailaddress w.bouten@uva.nl
%E Feitosa, Raul Queiroz,
%E Costa, Gilson Alexandre Ostwald Pedro da,
%E Almeida, Cláudia Maria de,
%E Fonseca, Leila Maria Garcia,
%E Kux, Hermann Johann Heinrich,
%B International Conference on Geographic Object-Based Image Analysis, 4 (GEOBIA).
%C Rio de Janeiro
%8 May 7-9, 2012
%I Instituto Nacional de Pesquisas Espaciais (INPE)
%J São José dos Campos
%P 484-489
%S Proceedings
%1 Instituto Nacional de Pesquisas Espaciais (INPE)
%K Geomorphology, LIDAR, Multi-temporal, Change Detection, Classification, Segmentation.
%X Multi-temporal LiDAR DTMs are used for the development and testing of a method for geomorphological change analysis in western Austria. Our test area is located on a mountain slope in the Gargellen Valley in western Austria. Six geomorphological features were mapped by using stratified Object-Based Image Analysis (OBIA) and segmentation optimization using 1m LiDAR DTMs of 2002 and 2005. Based on the 2002 data, the scale parameter for each geomorphological feature was optimized by comparing manually digitized training samples with automatically recognized image objects. Classification rule sets were developed to extract the feature types of interest. The segmentation and classification settings were then applied to both LiDAR DTMs which allowed the detection of geomorphological change between 2002 and 2005. FROM-TO changes of geomorphological categories were calculated and linked to volumetric changes which were derived from the subtracted DTMs. Enlargement of mass movement areas at the cost of glacial eroded bedrock was detected, although most changes occurred within mass movement categories and channel incisions, as the result of material removal and/or deposition. The proposed method seems applicable for geomorphological change detection in mountain areas. In order to improve change detection results, processing errors and noise that negatively influence the segmentation accuracy need to be reduced. Despite these concerns, we conclude that stratified OBIA applied to multi-temporal LiDAR datasets is a promising tool for of geomorphological change detection.
%9 Change Detection
%@language en
%3 130.pdf