TY - GEN
T1 - Automatic image classification of landslides improved with terrain roughness indices in various kernel sizes
AU - Yang, Mon Shieh
AU - Lin, Ming Chang
AU - Liu, Jin King
AU - Wu, Ming Chee
PY - 2010
Y1 - 2010
N2 - Using spectral-only information for landslides classification is usually confusing with houses, roads, and other bare lands because these ground features have similar spectral patterns on images. The terrain roughness can be measured by significant wavelengths; some studies have linked the relationships between terrain roughness and the landslide by using numerical analyses of topography data. In this study, airborne LiDAR data of 1m grid are used to explore the possibility of improvement of landslide classification, the LiDAR-derived data include DEM slope and terrain roughness indices including diversity, dominance and relative richness with different grid size data are used to improvement classification accuracy. The improvement of accuracy when including DEM slope is 22% in producer's accuracy and 27% in user's accuracy. The accuracy of diversity, dominance and relative richness indices all are improved when kernel sizes enlarge in Maximum Likelihood and Mahalanobis Distance algorithms.
AB - Using spectral-only information for landslides classification is usually confusing with houses, roads, and other bare lands because these ground features have similar spectral patterns on images. The terrain roughness can be measured by significant wavelengths; some studies have linked the relationships between terrain roughness and the landslide by using numerical analyses of topography data. In this study, airborne LiDAR data of 1m grid are used to explore the possibility of improvement of landslide classification, the LiDAR-derived data include DEM slope and terrain roughness indices including diversity, dominance and relative richness with different grid size data are used to improvement classification accuracy. The improvement of accuracy when including DEM slope is 22% in producer's accuracy and 27% in user's accuracy. The accuracy of diversity, dominance and relative richness indices all are improved when kernel sizes enlarge in Maximum Likelihood and Mahalanobis Distance algorithms.
UR - http://www.scopus.com/inward/record.url?scp=78650861392&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78650861392&partnerID=8YFLogxK
U2 - 10.1109/IGARSS.2010.5652504
DO - 10.1109/IGARSS.2010.5652504
M3 - Conference contribution
AN - SCOPUS:78650861392
SN - 9781424495658
SN - 9781424495665
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 527
EP - 529
BT - 2010 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2010 30th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2010
Y2 - 25 July 2010 through 30 July 2010
ER -