Deep Learning Approach to Update Road Network using VGI Data

Prajowal Manandhar; Prashanth Marpu; Zeyar Aung

doi:10.1109/CSPIS.2018.8642728

Deep Learning Approach to Update Road Network using VGI Data

Prajowal Manandhar
, Prashanth Marpu
, Zeyar Aung

Electrical Engineering

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

4 Scopus citations

Abstract

In our earlier work, we worked on extraction of the total width of road by agents traversing in the direction guided by Volunteered Geographic Information (VGI). The only downfall of VGI approach is its inability to update the new road developments. In this paper, we introduce deep learning approach to update the road network. We make use of the output of our previous work which forms as an input to train the Convolutional Neural Network (CNN). Then, further post processing is performed to remove non-road segments (such as buildings, vegetation, etc) on the output of CNN and finally, obtain the updated road map.

Original language	British English
Title of host publication	2018 International Conference on Signal Processing and Information Security, ICSPIS 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728102573
DOIs	https://doi.org/10.1109/CSPIS.2018.8642728
State	Published - 14 Feb 2019
Event	2018 International Conference on Signal Processing and Information Security, ICSPIS 2018 - Dubai, United Arab Emirates Duration: 7 Nov 2018 → 8 Nov 2018

Publication series

Name	2018 International Conference on Signal Processing and Information Security, ICSPIS 2018

Conference

Conference	2018 International Conference on Signal Processing and Information Security, ICSPIS 2018
Country/Territory	United Arab Emirates
City	Dubai
Period	7/11/18 → 8/11/18

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure
SDG 11 Sustainable Cities and Communities

Access to Document

10.1109/CSPIS.2018.8642728

OpenUrl availability

Full text

Cite this

Manandhar, P., Marpu, P., & Aung, Z. (2019). Deep Learning Approach to Update Road Network using VGI Data. In 2018 International Conference on Signal Processing and Information Security, ICSPIS 2018 Article 8642728 (2018 International Conference on Signal Processing and Information Security, ICSPIS 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSPIS.2018.8642728

@inproceedings{81498e938688482995f390dd60465826,

title = "Deep Learning Approach to Update Road Network using VGI Data",

abstract = "In our earlier work, we worked on extraction of the total width of road by agents traversing in the direction guided by Volunteered Geographic Information (VGI). The only downfall of VGI approach is its inability to update the new road developments. In this paper, we introduce deep learning approach to update the road network. We make use of the output of our previous work which forms as an input to train the Convolutional Neural Network (CNN). Then, further post processing is performed to remove non-road segments (such as buildings, vegetation, etc) on the output of CNN and finally, obtain the updated road map.",

author = "Prajowal Manandhar and Prashanth Marpu and Zeyar Aung",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 International Conference on Signal Processing and Information Security, ICSPIS 2018 ; Conference date: 07-11-2018 Through 08-11-2018",

year = "2019",

month = feb,

day = "14",

doi = "10.1109/CSPIS.2018.8642728",

language = "British English",

series = "2018 International Conference on Signal Processing and Information Security, ICSPIS 2018",

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

booktitle = "2018 International Conference on Signal Processing and Information Security, ICSPIS 2018",

address = "United States",

}

Manandhar, P, Marpu, P & Aung, Z 2019, Deep Learning Approach to Update Road Network using VGI Data. in 2018 International Conference on Signal Processing and Information Security, ICSPIS 2018., 8642728, 2018 International Conference on Signal Processing and Information Security, ICSPIS 2018, Institute of Electrical and Electronics Engineers Inc., 2018 International Conference on Signal Processing and Information Security, ICSPIS 2018, Dubai, United Arab Emirates, 7/11/18. https://doi.org/10.1109/CSPIS.2018.8642728

Deep Learning Approach to Update Road Network using VGI Data. / Manandhar, Prajowal; Marpu, Prashanth; Aung, Zeyar.
2018 International Conference on Signal Processing and Information Security, ICSPIS 2018. Institute of Electrical and Electronics Engineers Inc., 2019. 8642728 (2018 International Conference on Signal Processing and Information Security, ICSPIS 2018).

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

TY - GEN

T1 - Deep Learning Approach to Update Road Network using VGI Data

AU - Manandhar, Prajowal

AU - Marpu, Prashanth

AU - Aung, Zeyar

PY - 2019/2/14

Y1 - 2019/2/14

N2 - In our earlier work, we worked on extraction of the total width of road by agents traversing in the direction guided by Volunteered Geographic Information (VGI). The only downfall of VGI approach is its inability to update the new road developments. In this paper, we introduce deep learning approach to update the road network. We make use of the output of our previous work which forms as an input to train the Convolutional Neural Network (CNN). Then, further post processing is performed to remove non-road segments (such as buildings, vegetation, etc) on the output of CNN and finally, obtain the updated road map.

AB - In our earlier work, we worked on extraction of the total width of road by agents traversing in the direction guided by Volunteered Geographic Information (VGI). The only downfall of VGI approach is its inability to update the new road developments. In this paper, we introduce deep learning approach to update the road network. We make use of the output of our previous work which forms as an input to train the Convolutional Neural Network (CNN). Then, further post processing is performed to remove non-road segments (such as buildings, vegetation, etc) on the output of CNN and finally, obtain the updated road map.

UR - https://www.scopus.com/pages/publications/85063519713

U2 - 10.1109/CSPIS.2018.8642728

DO - 10.1109/CSPIS.2018.8642728

M3 - Conference contribution

AN - SCOPUS:85063519713

T3 - 2018 International Conference on Signal Processing and Information Security, ICSPIS 2018

BT - 2018 International Conference on Signal Processing and Information Security, ICSPIS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 International Conference on Signal Processing and Information Security, ICSPIS 2018

Y2 - 7 November 2018 through 8 November 2018

ER -

Manandhar P, Marpu P, Aung Z. Deep Learning Approach to Update Road Network using VGI Data. In 2018 International Conference on Signal Processing and Information Security, ICSPIS 2018. Institute of Electrical and Electronics Engineers Inc. 2019. 8642728. (2018 International Conference on Signal Processing and Information Security, ICSPIS 2018). doi: 10.1109/CSPIS.2018.8642728

Deep Learning Approach to Update Road Network using VGI Data

Abstract

Publication series

Conference

UN SDGs

Access to Document

OpenUrl availability

Other files and links

Fingerprint

Cite this