EXPLORING ALS AND DIM DATA FOR SEMANTIC SEGMENTATION USING CNNS

International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

Politz, F.^1¹ 

[1] Institute of Cartography and Geoinformatics, Leibniz University Hannover, Germany^1

关键词: Airborne Laser Scanning;    Dense Image Matching;    CNN;    encoder-decoder Network;    semantic segmentation;    point cloud;   

DOI  :  10.5194/isprs-archives-XLII-1-347-2018

学科分类：地球科学(综合)

来源: Copernicus Publications

【 摘 要 】

Over the past years, the algorithms for dense image matching (DIM) to obtain point clouds from aerial images improved significantly. Consequently, DIM point clouds are now a good alternative to the established Airborne Laser Scanning (ALS) point clouds for remote sensing applications. In order to derive high-level applications such as digital terrain models or city models, each point within a point cloud must be assigned a class label. Usually, ALS and DIM are labelled with different classifiers due to their varying characteristics. In this work, we explore both point cloud types in a fully convolutional encoder-decoder network, which learns to classify ALS as well as DIM point clouds. As input, we project the point clouds onto a 2D image raster plane and calculate the minimal, average and maximal height values for each raster cell. The network then differentiates between the classes ground, non-ground, building and no data. We test our network in six training setups using only one point cloud type, both point clouds as well as several transfer-learning approaches. We quantitatively and qualitatively compare all results and discuss the advantages and disadvantages of all setups. The best network achieves an overall accuracy of 96 % in an ALS and 83 % in a DIM test set.

【 授权许可】

CC BY