Convolutional Neural Network for Road Network Detections Using Sentinel 2A


Authors : Bayu Yanuargi; Ema Utami; Kusnawi

Volume/Issue : Volume 7 - 2022, Issue 12 - December

Google Scholar : https://bit.ly/3IIfn9N

Scribd : https://bit.ly/3WuVHh8

DOI : https://doi.org/10.5281/zenodo.7487943

Abstract : Road network data is critical information that used by government for development planning and by the services provider such as transportation and logistic company to deliver their services and prices calculations. Use of sentinel 2A satellite imagery data will solve the road map update cost issue since this data is free to use. The only problem on sentinel 2A is only about the medial spatial resolution that only able to detect 10 meters object. Using GPS data for the ground truth data will help to create the road masking data that can be used for the training. The result of the combination between these two data on Convolutional Neural Network are satisfied enough with accuracies score is 99% and soft dice error only 0.5%.

Keywords : Convolutional Neural Network (CNN), Sentinel, GPS, U-Net, Deep Learning.

Road network data is critical information that used by government for development planning and by the services provider such as transportation and logistic company to deliver their services and prices calculations. Use of sentinel 2A satellite imagery data will solve the road map update cost issue since this data is free to use. The only problem on sentinel 2A is only about the medial spatial resolution that only able to detect 10 meters object. Using GPS data for the ground truth data will help to create the road masking data that can be used for the training. The result of the combination between these two data on Convolutional Neural Network are satisfied enough with accuracies score is 99% and soft dice error only 0.5%.

Keywords : Convolutional Neural Network (CNN), Sentinel, GPS, U-Net, Deep Learning.

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe