APCRS-2021-0001
AUTHOR(S):
Wojciech Dominik, Marcin Bożyczko, Karolina Tułacz-Maziarz
TITLE:
DEEP LEARNING FOR AUTOMATIC LIDAR POINT CLOUD PROCESSING
ABSTRACT:
The paper presents the method of automatic point cloud classification that has been developed by OPEGIEKA. The method is based on deep learning techniques and consists of an inhouse developed algorithm of point cloud transformation to a regular array accompanied by internally designed convolutional neural network architecture. The developed workflow as well as experiences from its application during the execution of the CAPAP project are described. Results obtained on
real project data as well as statistics obtained on the ISPRS 3D semantic labelling benchmark with the use of OPEGIEKA’s method are presented. The achieved results place OPEGIEKA in the top 3 of the classification accuracy rating in the ISPRS benchmark. The implementation of OPEGIEKA’s solution into LiDAR point clouds classification workflow allowed to reduce the amount of necessary manual work.
KEY WORDS: : deep learning, LiDAR, point cloud, classification, automation
DOI: http://doi.org/10.2478/apcrs-2021-0001