Land Use Land Cover Classification from Satellite Imagery using mUnet: A Modified Unet Architecture

Lakshya Garg, Parul Shukla, Sandeep Kumar Singh, Vaishangi Bajpai, Utkarsh Yadav

2019

Abstract

Land-use-land-cover classification(LULC) is used to automate the process of providing labels, describing the physical land type to represent how a land area is being used. Many sectors such as telecom, utility, hydrology etc need land use and land cover information from remote sensing images. This information provides an insight into the type of geographical distribution of a region with providing low level features such as amount of vegetation, building area, and geometry etc as well as higher level concepts such as land use classes. This information is particularly useful for resource-starved rapidly developing cities for urban planning and resource management. LULC also provides historical changes in land-use patterns over a period of time. In this paper, we analyze patterns of land use in urban and rural neighborhoods using high resolution satellite imagery, utilizing a state of the art deep convolutional neural network. The proposed LULC network, termed as mUnet is based on an encoder-decoder convolutional architecture for pixel-level semantic segmentation. We test our approach on 3 band, FCC satellite imagery covering 225 km2 area of Karachi. Experimental results show the superiority of our proposed network architecture vis-à-vis other state of the art networks.

Paper Citation

in Harvard Style

Garg L., Shukla P., Singh S., Bajpai V. and Yadav U. (2019). Land Use Land Cover Classification from Satellite Imagery using mUnet: A Modified Unet Architecture. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 359-365. DOI: 10.5220/0007370603590365

in Bibtex Style

@conference{visapp19,
author={Lakshya Garg and Parul Shukla and Sandeep Kumar Singh and Vaishangi Bajpai and Utkarsh Yadav},
title={Land Use Land Cover Classification from Satellite Imagery using mUnet: A Modified Unet Architecture},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP},
year={2019},
pages={359-365},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007370603590365},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP
TI - Land Use Land Cover Classification from Satellite Imagery using mUnet: A Modified Unet Architecture
SN - 978-989-758-354-4
AU - Garg L.
AU - Shukla P.
AU - Singh S.
AU - Bajpai V.
AU - Yadav U.
PY - 2019
SP - 359
EP - 365
DO - 10.5220/0007370603590365
PB - SciTePress