TY - GEN
T1 - Outdoor LiDAR Point Cloud Building Segmentation
T2 - 13th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2021
AU - Gamal, Ahmad
AU - Husodo, Ario Yudo
AU - Jati, Grafika
AU - Alhamidi, Machmud R.
AU - Ma'Sum, M. Anwar
AU - Ardhianto, Ronni
AU - Jatmiko, Wisnu
N1 - Funding Information:
ACKNOWLEDGMENT This work is supported by the National Research and Innovation Agency (BRIN) with the research title "Pengembangan Sistem Big Data Perkotaan Berbasis Kejerdasan Buatan untuk Analisis Kepatuhan Bangunan Terhadap Rencana Tata Ruang Wilayah dan Perijinan Pembangunan dalam Rangka Peningkatan Pendapatan Daerah dan Perlinduagan Kualitas Lingkungan Perkotaan". The grant number is 26/E1/PRN/IV/2021. We also thank to PT. Pangripta Geomatika Indonesia (PGI) for providing the LiDAR dataset.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - The demand for 3D modeling using LiDAR as the primary source for observing, planning, and managing urban areas has increased. Using LiDAR data improves the accuracy of the modeling so that it can be used for policy determination and infrastructure planning. Various kinds of research on LiDAR data have been carried out, one of which is indoor and outdoor LiDAR segmentation. For outdoor cases, LiDAR data can be obtained from two points of view, namely ground view and aerial view. In this paper, we discuss the advancements and challenges of LiDAR 3D modeling in building segmentation that we have carried out. We collect LiDAR data with unmanned aerial vehicles. We use several algorithms such as PointNet and the Dynamic Graph Convolutional Neural Network variations to group structures from LiDAR data. The result is that the proposed method can segment buildings, surfaces, and vegetation well. The average accuracy produced for the Kupang and Depok datasets reaches 70%-80%.
AB - The demand for 3D modeling using LiDAR as the primary source for observing, planning, and managing urban areas has increased. Using LiDAR data improves the accuracy of the modeling so that it can be used for policy determination and infrastructure planning. Various kinds of research on LiDAR data have been carried out, one of which is indoor and outdoor LiDAR segmentation. For outdoor cases, LiDAR data can be obtained from two points of view, namely ground view and aerial view. In this paper, we discuss the advancements and challenges of LiDAR 3D modeling in building segmentation that we have carried out. We collect LiDAR data with unmanned aerial vehicles. We use several algorithms such as PointNet and the Dynamic Graph Convolutional Neural Network variations to group structures from LiDAR data. The result is that the proposed method can segment buildings, surfaces, and vegetation well. The average accuracy produced for the Kupang and Depok datasets reaches 70%-80%.
KW - 3D Modeling
KW - Building Segmentation
KW - Dynamic Graph Convolutional Neural Network
KW - LiDAR
KW - PointNet
UR - http://www.scopus.com/inward/record.url?scp=85123854696&partnerID=8YFLogxK
U2 - 10.1109/ICACSIS53237.2021.9631345
DO - 10.1109/ICACSIS53237.2021.9631345
M3 - Conference contribution
AN - SCOPUS:85123854696
T3 - 2021 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2021
BT - 2021 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2021
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 23 October 2021 through 26 October 2021
ER -