Semantic Segmentation of Lidar Point Cloud in Rural Area

Azady Bayu; Ari  Wibisono; Hanif Arief Wisesa; Naili Suri Intizhami; Wisnu Jatmiko; Ahmad Gamal

doi:10.1109/COMNETSAT.2019.8844074

Semantic Segmentation of Lidar Point Cloud in Rural Area

Azady Bayu, Ari Wibisono, Hanif Arief Wisesa, Naili Suri Intizhami, Wisnu Jatmiko, Ahmad Gamal

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Citations (Scopus)

Abstract

A 3D surface modeling format that is commonly used today is point cloud. 3D surface model segmentation could provide data for analysis in various fields. In the context of Geographic Information Systems, point cloud data obtained from the Light Detection and Ranging (LiDAR) sensor are used by machines to automatically identify objects such as houses, buildings, land, and rivers. There has been many Deep Learning approach through Convolutional Neural Network (CNN) that has been proven to be very capable for 2-dimensional imagery classification and segmentation. PointNet is a Deep Learning architecture that is designed so that the point cloud format that is still tabular form, can be directly convoluted by the CNN model. In this study, an improvement of PointNet is proposed for Point Cloud data of Kupang City. The Point Cloud data were acquired using an Unmanned Aerial Vehicle with a LiDAR sensor installed. The data were pre-processed and divided into training and testing data. The data were processed with the PointNet architecture and the model was tested using several metrics. The experiment shows that the PointNet architecture is capable on segmenting Geographical Point Cloud Data. In addition, incorporating voxel's color features could increase the performance of the segmentation.

Original language	English
Title of host publication	2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	73-78
Number of pages	6
ISBN (Electronic)	9781728137957
DOIs	https://doi.org/10.1109/COMNETSAT.2019.8844074
Publication status	Published - 1 Aug 2019
Event	8th IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Makassar, Indonesia Duration: 1 Aug 2019 → 3 Aug 2019

Publication series

Name	2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings

Conference

Conference	8th IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019
Country/Territory	Indonesia
City	Makassar
Period	1/08/19 → 3/08/19

Keywords

Convolutional Neural Network
Deep Learning
LiDAR
Point Cloud
PointNet

Access to Document

10.1109/COMNETSAT.2019.8844074

Cite this

Bayu, A., Wibisono, A., Wisesa, H. A., Intizhami, N. S., Jatmiko, W., & Gamal, A. (2019). Semantic Segmentation of Lidar Point Cloud in Rural Area. In 2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings (pp. 73-78). Article 8844074 (2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/COMNETSAT.2019.8844074

Bayu, Azady ; Wibisono, Ari ; Wisesa, Hanif Arief et al. / Semantic Segmentation of Lidar Point Cloud in Rural Area. 2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 73-78 (2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings).

@inproceedings{e787284428904b3fafa4dcb4fa4ebf19,

title = "Semantic Segmentation of Lidar Point Cloud in Rural Area",

abstract = "A 3D surface modeling format that is commonly used today is point cloud. 3D surface model segmentation could provide data for analysis in various fields. In the context of Geographic Information Systems, point cloud data obtained from the Light Detection and Ranging (LiDAR) sensor are used by machines to automatically identify objects such as houses, buildings, land, and rivers. There has been many Deep Learning approach through Convolutional Neural Network (CNN) that has been proven to be very capable for 2-dimensional imagery classification and segmentation. PointNet is a Deep Learning architecture that is designed so that the point cloud format that is still tabular form, can be directly convoluted by the CNN model. In this study, an improvement of PointNet is proposed for Point Cloud data of Kupang City. The Point Cloud data were acquired using an Unmanned Aerial Vehicle with a LiDAR sensor installed. The data were pre-processed and divided into training and testing data. The data were processed with the PointNet architecture and the model was tested using several metrics. The experiment shows that the PointNet architecture is capable on segmenting Geographical Point Cloud Data. In addition, incorporating voxel's color features could increase the performance of the segmentation.",

keywords = "Convolutional Neural Network, Deep Learning, LiDAR, Point Cloud, PointNet",

author = "Azady Bayu and Ari Wibisono and Wisesa, {Hanif Arief} and Intizhami, {Naili Suri} and Wisnu Jatmiko and Ahmad Gamal",

year = "2019",

month = aug,

day = "1",

doi = "10.1109/COMNETSAT.2019.8844074",

language = "English",

series = "2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "73--78",

booktitle = "2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings",

address = "United States",

note = "8th IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 ; Conference date: 01-08-2019 Through 03-08-2019",

}

Bayu, A, Wibisono, A, Wisesa, HA, Intizhami, NS, Jatmiko, W & Gamal, A 2019, Semantic Segmentation of Lidar Point Cloud in Rural Area. in 2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings., 8844074, 2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 73-78, 8th IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019, Makassar, Indonesia, 1/08/19. https://doi.org/10.1109/COMNETSAT.2019.8844074

Semantic Segmentation of Lidar Point Cloud in Rural Area. / Bayu, Azady; Wibisono, Ari ; Wisesa, Hanif Arief et al.
2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 73-78 8844074 (2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Semantic Segmentation of Lidar Point Cloud in Rural Area

AU - Bayu, Azady

AU - Wibisono, Ari

AU - Wisesa, Hanif Arief

AU - Intizhami, Naili Suri

AU - Jatmiko, Wisnu

AU - Gamal, Ahmad

PY - 2019/8/1

Y1 - 2019/8/1

N2 - A 3D surface modeling format that is commonly used today is point cloud. 3D surface model segmentation could provide data for analysis in various fields. In the context of Geographic Information Systems, point cloud data obtained from the Light Detection and Ranging (LiDAR) sensor are used by machines to automatically identify objects such as houses, buildings, land, and rivers. There has been many Deep Learning approach through Convolutional Neural Network (CNN) that has been proven to be very capable for 2-dimensional imagery classification and segmentation. PointNet is a Deep Learning architecture that is designed so that the point cloud format that is still tabular form, can be directly convoluted by the CNN model. In this study, an improvement of PointNet is proposed for Point Cloud data of Kupang City. The Point Cloud data were acquired using an Unmanned Aerial Vehicle with a LiDAR sensor installed. The data were pre-processed and divided into training and testing data. The data were processed with the PointNet architecture and the model was tested using several metrics. The experiment shows that the PointNet architecture is capable on segmenting Geographical Point Cloud Data. In addition, incorporating voxel's color features could increase the performance of the segmentation.

AB - A 3D surface modeling format that is commonly used today is point cloud. 3D surface model segmentation could provide data for analysis in various fields. In the context of Geographic Information Systems, point cloud data obtained from the Light Detection and Ranging (LiDAR) sensor are used by machines to automatically identify objects such as houses, buildings, land, and rivers. There has been many Deep Learning approach through Convolutional Neural Network (CNN) that has been proven to be very capable for 2-dimensional imagery classification and segmentation. PointNet is a Deep Learning architecture that is designed so that the point cloud format that is still tabular form, can be directly convoluted by the CNN model. In this study, an improvement of PointNet is proposed for Point Cloud data of Kupang City. The Point Cloud data were acquired using an Unmanned Aerial Vehicle with a LiDAR sensor installed. The data were pre-processed and divided into training and testing data. The data were processed with the PointNet architecture and the model was tested using several metrics. The experiment shows that the PointNet architecture is capable on segmenting Geographical Point Cloud Data. In addition, incorporating voxel's color features could increase the performance of the segmentation.

KW - Convolutional Neural Network

KW - Deep Learning

KW - LiDAR

KW - Point Cloud

KW - PointNet

UR - http://www.scopus.com/inward/record.url?scp=85073442780&partnerID=8YFLogxK

U2 - 10.1109/COMNETSAT.2019.8844074

DO - 10.1109/COMNETSAT.2019.8844074

M3 - Conference contribution

T3 - 2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings

SP - 73

EP - 78

BT - 2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019

Y2 - 1 August 2019 through 3 August 2019

ER -

Bayu A, Wibisono A, Wisesa HA, Intizhami NS, Jatmiko W , Gamal A. Semantic Segmentation of Lidar Point Cloud in Rural Area. In 2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 73-78. 8844074. (2019 IEEE International Conference on Communication, Networks and Satellite, Comnetsat 2019 - Proceedings). doi: 10.1109/COMNETSAT.2019.8844074

Semantic Segmentation of Lidar Point Cloud in Rural Area

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this