TY - GEN
T1 - Large-scale 3D Point Cloud Semantic Segmentation with 3D U-Net ASPP Sparse CNN
AU - Hirzi, Naufal Muhammad
AU - Ma'sum, Muhammad Anwar
AU - Pratama, Mahardhika
AU - Jatmiko, Wisnu
N1 - Funding Information:
ACKNOWLEDGMENT We gratefully acknowledge the support from Tokopedia UI AI Center, Faculty of Computer Science, University of Indonesia and PUTI Q1 from Universitas Indonesia for research project entitled “Asesmen Kerusakan Bangunan Akibat Bencana Gempa Bumi Menggunakan Residual
Funding Information:
We gratefully acknowledge the support from Tokopedia UI AI Center, Faculty of Computer Science, University of Indonesia and PUTI Q1 from Universitas Indonesia for research project entitled "Asesmen Kerusakan Bangunan Akibat Bencana Gempa Bumi Menggunakan Residual Siamese Neural Network Pada Data Lidar", with number NKB-395/UN2.RST/HKP.05.00/2022.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - 3D geometric modelling of urban areas has the potential for further development, not only for 3D urban visualization. 3D point cloud, as 3D data commonly used in 3D urban geometry modelling, is needed to extract objects from point clouds to analyze urban landscapes. An automated method to analyze objects from the 3D point cloud can be achieved by using the semantic segmentation method. Unlike other segmentation tasks in 3D point cloud data, 3D urban point cloud segmentation has the challenge of segmenting different object sizes on various types of landscape contours with imbalanced distribution of the object. Therefore, this study modified 3D U-Net Sparse CNN by adding Atrous Spatial Pyramid Pooling (ASPP) as one of the modules in this model, called 3D U-Net ASPP Sparse CNN. The use of ASPP aims to get the contextual multi-scale information of the input feature map from the encoder part of U-Net. Furthermore, 3D U-Net ASPP Sparse CNN is implemented by using weighted dice loss as the loss function. The experiment result shows 3D U-Net ASPP Sparse CNN with weighted dice loss has achieved the best evaluation score in our experiment, with OA = 96.53 and mIoU = 63.59.
AB - 3D geometric modelling of urban areas has the potential for further development, not only for 3D urban visualization. 3D point cloud, as 3D data commonly used in 3D urban geometry modelling, is needed to extract objects from point clouds to analyze urban landscapes. An automated method to analyze objects from the 3D point cloud can be achieved by using the semantic segmentation method. Unlike other segmentation tasks in 3D point cloud data, 3D urban point cloud segmentation has the challenge of segmenting different object sizes on various types of landscape contours with imbalanced distribution of the object. Therefore, this study modified 3D U-Net Sparse CNN by adding Atrous Spatial Pyramid Pooling (ASPP) as one of the modules in this model, called 3D U-Net ASPP Sparse CNN. The use of ASPP aims to get the contextual multi-scale information of the input feature map from the encoder part of U-Net. Furthermore, 3D U-Net ASPP Sparse CNN is implemented by using weighted dice loss as the loss function. The experiment result shows 3D U-Net ASPP Sparse CNN with weighted dice loss has achieved the best evaluation score in our experiment, with OA = 96.53 and mIoU = 63.59.
KW - 3D Semantic Segmentation
KW - 3D U-Net ASPP
KW - Point Cloud
KW - Sparse Convolutional neural networks
UR - http://www.scopus.com/inward/record.url?scp=85141836135&partnerID=8YFLogxK
U2 - 10.1109/IWBIS56557.2022.9924988
DO - 10.1109/IWBIS56557.2022.9924988
M3 - Conference contribution
AN - SCOPUS:85141836135
T3 - IWBIS 2022 - 7th International Workshop on Big Data and Information Security, Proceedings
SP - 59
EP - 64
BT - IWBIS 2022 - 7th International Workshop on Big Data and Information Security, Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th International Workshop on Big Data and Information Security, IWBIS 2022
Y2 - 1 October 2022 through 3 October 2022
ER -