TAILORED FEATURES FOR SEMANTIC SEGMENTATION WITH A DGCNN USING FREE TRAINING SAMPLES OF A COLORED AIRBORNE POINT CLOUD
Automation of 3D LiDAR point cloud processing is expected to increase the production rate of many applications including automatic map generation. Fast development on high-end hardware has boosted the expansion of deep learning research for 3D classification and segmentation. However, deep learning...
Main Authors: | E. Widyaningrum, M. K. Fajari, R. C. Lindenbergh, M. Hahn |
---|---|
Format: | Article |
Language: | English |
Published: |
Copernicus Publications
2020-08-01
|
Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
Online Access: | https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLIII-B2-2020/339/2020/isprs-archives-XLIII-B2-2020-339-2020.pdf |
Similar Items
-
Airborne Laser Scanning Point Cloud Classification Using the DGCNN Deep Learning Method
by: Elyta Widyaningrum, et al.
Published: (2021-02-01) -
ACCURACY COMPARISON OF VHR SYSTEMATIC-ORTHO SATELLITE IMAGERIES AGAINST VHR ORTHORECTIFIED IMAGERIES USING GCP
by: E. Widyaningrum, et al.
Published: (2016-06-01) -
Processing Laser Point Cloud in Fully Mechanized Mining Face Based on DGCNN
by: Zhizhong Xing, et al.
Published: (2021-07-01) -
COMPREHENSIVE COMPARISON OF TWO IMAGE-BASED POINT CLOUDS
FROM AERIAL PHOTOS WITH AIRBORNE LIDAR FOR LARGE-SCALE MAPPING
by: E. Widyaningrum, et al.
Published: (2017-09-01) -
Automatic LIDAR building segmentation based on DGCNN and euclidean clustering
by: Ahmad Gamal, et al.
Published: (2020-11-01)