The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLII-2/W13
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 989–993, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-989-2019
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 989–993, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-989-2019

  05 Jun 2019

05 Jun 2019

3D-CNN BASED TREE SPECIES CLASSIFICATION USING MOBILE LIDAR DATA

H. Guan1, Y. Yu2, W. Yan3, D. Li4, and J. Li5 H. Guan et al.
  • 1School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science & Technology, Nanjing, 210044, China
  • 2Faculty of Computer and Software Engineering, Huaiyin Institute of Technology, Huaian, 223003, China
  • 3School of Geographical Science, Nanjing University of Information Science & Technology, Nanjing, 210044, China
  • 4State Key laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan, China
  • 5Department of Geography and Environmental Management, University of Waterloo, Waterloo, ON N2L 3G1, Canada

Keywords: Mobile LiDAR Data, Tree Segmentation, Voxelization, NCut, Supervoxels, 3D-CNN

Abstract. Our work addresses the problem of classifying tree species from mobile LiDAR data. The work is a two step-wise strategy, including tree segmentation and tree species classification. In the tree segmentation step, a voxel-based upward growing filtering is proposed to remove terrain points from the mobile laser scanning data. Then, individual trees are segmented via a Euclidean distance clustering approach and Voxel-based Normalized Cut (VNCut) segmentation approach. In the tree species classification, a voxel-based 3D convolutional neural network (3D-CNN) model is developed based on intensity information. A road section data acquired by a RIEGL VMX-450 system are selected for evaluating the proposed tree classification method. Qualitative analysis shows that our algorithm achieves a good performance.