Home > Research > Publications & Outputs > Joint Deep Learning: A novel framework for urba...

Links

View graph of relations

Joint Deep Learning: A novel framework for urban land cover and land use classification

Research output: Contribution to conference - Without ISBN/ISSN Conference paperpeer-review

Published

Standard

Joint Deep Learning: A novel framework for urban land cover and land use classification. / Zhang, Ce; Pan, Xin; Li, Huapeng et al.
2020. 1-5 Paper presented at GISRUK 2020.

Research output: Contribution to conference - Without ISBN/ISSN Conference paperpeer-review

Harvard

APA

Vancouver

Author

Zhang, Ce ; Pan, Xin ; Li, Huapeng et al. / Joint Deep Learning: A novel framework for urban land cover and land use classification. Paper presented at GISRUK 2020.5 p.

Bibtex

@conference{661c2ed9ab4d48669ab9aaf965aad96c,
title = "Joint Deep Learning: A novel framework for urban land cover and land use classification",
abstract = "The majority of existing research on urban land cover and land use (LULC) classification from remotely sensed imagery is to differentiate at a specific level (either land cover (LC) or land use (LU)) and at a specific scale. The spatial and hierarchical relationships between LC and LU were not considered in the previous paradigm. This paper proposed Joint Deep Learning as a novel framework for urban LULC classification. Three state-of-the-art methods were compared under the framework, including JDL, SS-JDL and a newly proposed Cross GAN. Experimental results demonstrate the superiority of Cross GAN in terms of classification accuracy and robustness.",
author = "Ce Zhang and Xin Pan and Huapeng Li and Shuqing Zhang and Peter Atkinson",
year = "2020",
month = jul,
day = "22",
language = "English",
pages = "1--5",
note = "GISRUK 2020 ; Conference date: 21-07-2020 Through 23-07-2020",
url = "http://london.gisruk.org/index.php",

}

RIS

TY - CONF

T1 - Joint Deep Learning: A novel framework for urban land cover and land use classification

AU - Zhang, Ce

AU - Pan, Xin

AU - Li, Huapeng

AU - Zhang, Shuqing

AU - Atkinson, Peter

PY - 2020/7/22

Y1 - 2020/7/22

N2 - The majority of existing research on urban land cover and land use (LULC) classification from remotely sensed imagery is to differentiate at a specific level (either land cover (LC) or land use (LU)) and at a specific scale. The spatial and hierarchical relationships between LC and LU were not considered in the previous paradigm. This paper proposed Joint Deep Learning as a novel framework for urban LULC classification. Three state-of-the-art methods were compared under the framework, including JDL, SS-JDL and a newly proposed Cross GAN. Experimental results demonstrate the superiority of Cross GAN in terms of classification accuracy and robustness.

AB - The majority of existing research on urban land cover and land use (LULC) classification from remotely sensed imagery is to differentiate at a specific level (either land cover (LC) or land use (LU)) and at a specific scale. The spatial and hierarchical relationships between LC and LU were not considered in the previous paradigm. This paper proposed Joint Deep Learning as a novel framework for urban LULC classification. Three state-of-the-art methods were compared under the framework, including JDL, SS-JDL and a newly proposed Cross GAN. Experimental results demonstrate the superiority of Cross GAN in terms of classification accuracy and robustness.

M3 - Conference paper

SP - 1

EP - 5

T2 - GISRUK 2020

Y2 - 21 July 2020 through 23 July 2020

ER -