Abstract | ||
---|---|---|
Identifying damaged buildings after natural disasters such as earthquake is important for the planning of recovery actions. We present a segment-based approach to classifying damaged building roofs in aerial laser scanning data. A challenge in the supervised classification of point segments is the generation of training samples, which is difficult because of the complexity of interpreting point clouds. We evaluate the performance of three different classifiers trained with a small set of training samples and show that feature selection improves the training and the accuracy of the resulting classification. When trained with 50 training samples, a linear discriminant classifier using a subset of six features reaches a classification accuracy of 85%. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/LGRS.2013.2257676 | IEEE Geosci. Remote Sensing Lett. |
Keywords | Field | DocType |
random forest,segment based classification,lidar,training samples,damaged building roofs,emergency management,segmentation,training,linear discriminant classifier,point clouds,earthquakes,natural disasters,disaster management,supervised classification,remote sensing by laser beam,optical radar,image classification,point segments,classification accuracy,feature selection,radar imaging,support vector machines (svm),aerial laser scanning data | Feature selection,Remote sensing,Artificial intelligence,Optical radar,Contextual image classification,Classifier (linguistics),Computer vision,Radar imaging,Laser scanning,Pattern recognition,Linear discriminant analysis,Point cloud,Mathematics | Journal |
Volume | Issue | ISSN |
10 | 5 | 1545-598X |
Citations | PageRank | References |
7 | 0.54 | 7 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kourosh Khoshelham | 1 | 65 | 12.67 |
Sander Oude Elberink | 2 | 558 | 31.48 |
Sudan Xu | 3 | 9 | 1.32 |