Deep learning based Land Cover Change Detection Using U-Net

Wonho Jo; Key-Ho Park

doi:10.22776/kgs.2022.57.3.297

All Issue

2022 Vol.57, Issue 3 Preview Page Next Page

Research Article

Deep learning based Land Cover Change Detection Using U-Net U-Net을 이용한 딥러닝 기반의 토지피복 변화탐지

30 June 2022. pp. 297-306

PDF XML

Abstract

Remote sensing enables the iterative collection of data, which enables spatio-temporal analysis using satellite images. Detecting land cover changes using multi-time satellite imagery plays an important role in efficient land monitoring and planning. In the existing land cover change detection method, effective change detection was difficult on account of using a parameter-based model. This study proposes a new method of land cover change detection by presenting a model based on U-Net deep learning architecture. To verify the effectiveness of model presented in this study, change detection was tested in two cases according to the type of change in land cover. The model improved the efficiency by synchronizing the detection and segmentation operations, and showed effective detection results. The approach of this study can be a useful model for monitoring and managing the land.

Keywords

deep learning

fully Convolutional network

remote sensing

land cover

change detection

원격탐사를 통한 자료의 반복적 수집은 위성영상 자료를 통한 시공간적 분석을 가능하게 한다. 다중시기의 위성영상을 사용해 토지피복의 변화를 탐지하는 것은 효율적인 국토의 모니터링과 계획에 중요한 역할을 한다. 기존의 토지피복 변화탐지 방법은 매개변수 기반의 모형을 사용해 효과적인 변화탐지가 어려웠다. 본 연구는 U-Net을 이용한 딥러닝(deep learning) 기반의 변화탐지 모형을 설계하여 토지피복 변화탐지의 새로운 방법을 제시한다. 이 연구에서 설계한 변화탐지 모형의 효용성을 검증하고자, 토지피복의 변화 종류에 따른 두 가지 사례에 대한 변화탐지를 실험하였다. 연구에서 설계한 변화탐지 모형은 탐지 작업과 분할작업을 동시화해 효율성을 제고하였으며, 효과적인 탐지 결과를 보여주었다. 본 연구의 접근은 변화탐지 모형으로써 국토를 모니터링하고 관리하는데 유용한 모형이 될 수 있다.

키워드

딥러닝

완전합성곱 신경망

원격탐사

토지피복

변화탐지

References

산림청, 2020, 2019년도 산불통계 연보.

조명래･송두범･강현수, 2010, 세종시와 충남의 상생발전 모색을 위한 심포지엄.

조원호･임용호･박기호, 2019, "합성곱 신경망을 이용한 딥러닝 기반의 토지피복 분류: 한국 토지피복을 대상으로," 대한지리학회지 54, 1-16.

Foley, J. A., DeFries, R., Asner, G. P., Barford, C., Bonan, G., Carpenter, S. R., Chapin, F. S., Coe, M. T., Daily, G. C., and Gibbs, H. K., 2005, Global consequences of land use, Science, 309, 570-574. 10.1126/science.111177216040698

Gärtner, P., Förster, M., Kurban, A., and Kleinschmit, B. 2014, Object based change detection of Central Asian Tugai vegetation with very high spatial resolution satellite imagery, International Journal of Applied Earth Observation and Geoinformation, 31, 110-121. 10.1016/j.jag.2014.03.004

Green, K., 2011, Change matters, Photogrammetric Engineering and Remote Sensing, 77, 305-309.

Im, J., Rhee, J., and Jensen, J. R., 2009, Enhancing binary change detection performance using a moving threshold window (MTW) approach, Photogrammetric Engineering & Remote Sensing, 75, 951-961. 10.14358/PERS.75.8.951

Jensen, J. R., 1981, Urban change detection mapping using Landsat digital data, The American Cartographer, 8, 127-147. 10.1559/152304081784447318

Jensen, J. R., 2016, Introductory Digital Image Processing: A Remote Sensing Perspective, 4th Edition. University of South Carolina, Columbus.

Lambin, E. F., Geist, H. J., and Lepers, E., 2003, Dynamics of land-use and land-cover change in tropical regions, Annual Review of Environment and Resources, 28, 205-241. 10.1146/annurev.energy.28.050302.105459

Li, X., Chen, H., Qi, X., Dou, Q., Fu, C.-W., and Heng, P.-A., 2018, H-DenseUNet: hybrid densely connected UNet for liver and tumor segmentation from CT volumes, IEEE Transactions on Medical Imaging, 37, 2663-2674. 10.1109/TMI.2018.284591829994201

Long, J., Shelhamer, E., and Darrell, T., 2015, Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3431-3440. 10.1109/CVPR.2015.7298965

Lunetta, R. S., and Elvidge, C. D., 1998, Remote Sensing Change Detection: Environmental Monitoring Methods and Applications, Ann Arbor Press, Chelsea, MI.

National Research Council, 2002, Down to earth: Geographic Information for Sustainable Development in Africa, National Academy Press, Washington DC.

Noh, H., Hong, S., and Han, B., 2015, Learning deconvolution network for semantic segmentation, Proceedings of the IEEE International Conference on Computer Vision, 1520-1528. 10.1109/ICCV.2015.178

Purkis, S. J. and Klemas, V. V., 2011, Remote Sensing and Global Environmental Change, Wiley Blackwell, Oxford. 10.1002/9781118687659

Ronneberger, O., Fischer, P., and Brox, T., 2015, U-net: Convolutional networks for biomedical image segmentation, International Conference on Medical Image Computing and Computer-assisted Intervention, 234-241. 10.1007/978-3-319-24574-4_28

Tang, J., Li, S., and Liu, P., 2021, A review of lane detection methods based on deep learning, Pattern Recognition, 111, 107623. 10.1016/j.patcog.2020.107623

Warner, T., Almutairi, A., and Lee, J. Y., 2009, Remote Sensing of Land Cover Change, SAGE, London, UK.

Zhang, S.-H., Li, R., Dong, X., Rosin, P., Cai, Z., Han, X., Yang, D., Huang, H., and Hu, S.-M., 2019, Pose2seg: Detection free human instance segmentation, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 889-898. 10.1109/CVPR.2019.00098

Zhao, H., Shi, J., Qi, X., Wang, X., and Jia, J., 2017, Pyramid scene parsing network, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2881-2890. 10.1109/CVPR.2017.660

Zhou, Z., Rahman Siddiquee, M. M., Tajbakhsh, N., and Liang, J., 2018, Unet++: A nested u-net architecture for medical image segmentation, Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, 3-11. 10.1007/978-3-030-00889-5_132613207PMC7329239

Information

Publisher :The Korean Geographical Society
Publisher(Ko) :대한지리학회
Journal Title :Journal of the Korean Geographical Society
Journal Title(Ko) :대한지리학회지
Volume : 57
No :3
Pages :297-306
Received Date : 2022-06-10
Revised Date : 2022-06-29
Accepted Date : 2022-06-29
DOI :https://doi.org/10.22776/kgs.2022.57.3.297

Journal of the Korean Geographical SocietyISSN:1225-6633(Print)대한지리학회

All Issue