Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B3, 283-287, 2016
http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B3/283/2016/
doi:10.5194/isprs-archives-XLI-B3-283-2016
 
09 Jun 2016
TENSOR MODELING BASED FOR AIRBORNE LiDAR DATA CLASSIFICATION
N. Li1,2, C. Liu1, N. Pfeifer2, J. F. Yin3, Z.Y. Liao3, and Y. Zhou1 1College of Survey and Geoinformation, Tongji University, 200092, Shanghai, China
2Deptartment of Geodesy and Geoinformation, Technische Universität Wien, 1040 Vienna, Austria
3Department of Mathmetrics, Tongji University, 200092, Shanghai, China
Keywords: Feature Selection, Tensor Processing, KNN classification Abstract. Feature selection and description is a key factor in classification of Earth observation data. In this paper a classification method based on tensor decomposition is proposed. First, multiple features are extracted from raw LiDAR point cloud, and raster LiDAR images are derived by accumulating features or the “raw” data attributes. Then, the feature rasters of LiDAR data are stored as a tensor, and tensor decomposition is used to select component features. This tensor representation could keep the initial spatial structure and insure the consideration of the neighborhood. Based on a small number of component features a k nearest neighborhood classification is applied.
Conference paper (PDF, 1159 KB)


Citation: Li, N., Liu, C., Pfeifer, N., Yin, J. F., Liao, Z. Y., and Zhou, Y.: TENSOR MODELING BASED FOR AIRBORNE LiDAR DATA CLASSIFICATION, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLI-B3, 283-287, doi:10.5194/isprs-archives-XLI-B3-283-2016, 2016.

BibTeX EndNote Reference Manager XML