Detection of Land Use Change Using Transfer Learning and Aerial Photography

doi:10.16879/jkca.2022.22.3.015

All Issue

2022 Vol.22, Issue 3 Preview Page Next Page

Research Article

Detection of Land Use Change Using Transfer Learning and Aerial Photography 전이학습과 항공사진을 이용한 토지이용변화 탐지: 홍일영¹, 이경주²
Ilyoung Hong¹, Gyoungju Lee²; ¹남서울대학교 공간정보공학과 부교수
²한국교통대학교 도시･교통공학과 교수

¹Associate Professor, Department of GIS Engineering, Namseoul University
²Professor, Department of Urban and Transportation Engineering, Korea National University of Transportation

31 December 2022. pp. 15-24

PDF

Abstract

The purpose of this study is to prepare a method to detect changes in land use status by comparing aerial photos and land use status maps using a transfer learning model of deep learning. For this purpose, a spatial analysis function that compares the image prediction model of deep learning and raster and vector data was used. A method of detecting changes in land use was proposed using the prediction results for commercial, agricultural, forest, and rivers on the land use status map through the establishment of a transfer learning model. This analysis method can be used as a method to confirm the change of data by comparing the latest information in the raster format with the existing data in the vector format.

Keywords

transfer learning

areal photography

land use

spatial analysis

본 연구의 목적은 딥러닝의 전이학습 모델을 이용하여 항공사진과 토지이용현황도 간의 비교를 통해 토지이용현황의 변화를 탐지하는 방안을 마련하는 데 있다. 이러한 목적을 위해 딥러닝의 이미지 예측모델과 라스터와 벡터 자료를 비교하는 공간분석 기능을 이용하였다. 학습모델 구축을 통해 토지이용현황도의 상업지, 농지, 임지 및 수계에 대한 예측결과를 이용하여 토지이용의 변화를 탐지하는 방안을 제시하였다. 이러한 분석 방안은 라스터 형태의 최신 정보와 벡터 형태의 기존 자료와의 비교를 통해서 자료의 변화를 확인하는 방안으로 활용이 가능하다.

키워드

전이학습

항공사진

토지이용현황도

공간분석

References

박은관･최병남･김대종, 1998, ｢토지이용계획을 위한 GIS 활용방안 연구｣, 국토연구원.
박지영･강영옥･김지연, 2022, “거리 영상과 시멘틱 세그먼테이션을 활용한 보행환경 평가 지표 개발,” 한국지도학회지, 22(1), 53-68, 10.16879/jkca.2022.22.1.053
서기환, 2018, “GeoAI 기반의 토지이용변화 모니터링 혁신과 활용방안,” 국토정책 Brief, 1-6.
우제윤･구지희･이정훈･홍창희, 2001, “국토이용 현황 분석을 위한 토지이용현황도 활용 방안 연구-전북지역 대상,” 한국공간정보시스템학회 논문지, 3(2), 63-70.
유수홍･이지상･노현주･박효근･손홍규, 2017, “CNN 기법을 이용한 공간정보 자동분류연구,” 한국지형공간정보학회 학술대회, 167-168.
윤여수･김광백･박현준, 2020, “합성곱 신경망을 이용한 구글 어스에서의 녹지 비율 측정,” 한국정보통신학회논문지, 24(3), 349-354.
조나혜･강영옥･윤지영･박소연. 2019, “지능형 관광 서비스를 위한 관광 사진 분류체계 개발,” 한국지도학회지, 19(3), 87-101, 10.16879/jkca.2019.19.3.087
조원호･임용호･박기호, 2019, “합성곱 신경망을 이용한 딥러닝 기반의 토지피복 분류: 한국 토지피복을 대상으로,” 대한지리학회지, 54(1), 1-16.
조은래･김경환･유환희, 2009, “고해상도 위성영상을 이용한 토지이용변화 분석,” 대한공간정보학회지, 17(1), 3-11.
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., and Kudlur, M., 2016, Tensorflow: A system for largescale largescale machine learning, Proceedings, 12th Symposium on Operating Systems Design and Implementation, 2–4 November, Savannah, USA, pp.265-283.
Basu, S., Ganguly, S., Mukhopadhyay, S., DiBiano, R., Karki, M., and Nemani, R., 2015, DeepSat: a learning framework for satellite imagery, Proceedings, 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems. ACM, 37. 10.1145/2820783.2820816
Carrio, A., Sampedro, C., Rodriguez-Ramos, A., and Campoy, P., 2017, A review of deep learning methods and applications for unmanned aerial vehicles, Journal of Sensors, 2017. 10.1155/2017/3296874
Castelluccio, M., Poggi, G., Sansone, C., and Verdoliva, L., 2015, Land use classification in remote sensing images by convolutional neural networks, arXiv preprint arXiv:1508.00092. https://arxiv.org/pdf/1508.00092.pdf
Helber, P., Bischke, B., Dengel, A., and Borthm D., 2017, Eurosat: A novel dataset and deep learning benchmark for land use and land cover classificaꠓtion, arXiv:1709.00029 (v1). 10.1109/IGARSS.2018.8519248
Hu, F., Xia, G.S., Hu, J., and Zhang, L., 2015, Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery, Remote Sensing, 7(11), 14680- 14707. 10.3390/rs71114680
Krizhevsky, A., Sutskever, I., and Hinton, G., 2017, Imagenet classification with deep convolutional neural networks, Communications of the ACM, 60(6), 84-90. 10.1145/3065386
Lary, D., Alavi, A, Gandomi, A., and Walker, A., 2016, Machine learning in geosciences and remote sensing, Geoscience Frontiers, 7(1), 3-10. 10.1145/3065386
Mahdianpari, M., Salehi, B., Rezaee, M., Mohammadiꠓmanesh, F., and Zhang, Y., 2018, Very deep conꠓvolutional neural networks for complex land cover mapping using multispectral remote sensing imagery, Remote Sensing, 10(7), 1119. 10.3390/rs10071119
Marcos, D., Volpi, M., Kellenberger, B., and Tuia, D., 2018, Land cover mapping at very high resolution with rotation equivariant CNNs: Towards small yet accurate models, ISPRS Journal of Photogrammetry and Remote Sensing, 145, 96-107. 10.1016/j.isprsjprs.2018.01.021
Ribani, R. and Marengoni, M., 2019, A survey of transfer learning for convolutional neural networks, Proceedings, 2019 32^nd SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T), IEEE, 47-57. 10.1109/SIBGRAPI-T.2019.0001030707918
Scott, G.J., England, M.R., Starms, W.A., Marcum, R. A., and Davis, C.H., 2017, Training deep convolutional neural networks for land–cover classification of high-resolution imagery, IEEE Geoscience and Remote Sensing Letters, 14(4), 549-553. 10.1109/LGRS.2017.2657778
Wang, J., Luo, C., Huang, H., Zhao, H., and Wang, S., 2017, Transferring pre-trained deep CNNs for remote scene classification with general features learned from linear PCA network, Remote Sensing, 9(3), 225. 10.3390/rs9030225
Xie, M., Jean, N., Burke, M., Lobell, D., and Ermon, S., 2016, Transfer learning from deep features for remote sensing and poverty mapping, Proceedings, Thirtieth AAAI Conference on Artificial Intelligence, 3929-3935. 10.1609/aaai.v30i1.9906
Xing, H., Meng, Y., Wang, Z., Fan, K., and Hou, D., 2018, Exploring geo-tagged photos for land cover validation with deep learning, ISPRS Journal of Photogrammetry and Remote Sensing, 141, 237- 251. 10.1016/j.isprsjprs.2018.04.025
Yang, Y. and Newsam, S., 2010, Bag-of-visual-words and spatial extensions for land-use classification, Proꠓceedings of the 18th SIGSPATIAL international conference on advances in geographic information systems. ACM, 270-279. 10.1145/1869790.1869829
Zhong, Y., Fei, F., Liu, Y., Zhao, B., and Jiao, H., 2017, SatCNN: Satellite image dataset classification using agile convolutional neural networks, Remote Sensing Letters, 8(2), 136-145. 10.1080/2150704X.2016.1235299

Information

Publisher :The Korean Cartographic Association
Publisher(Ko) :한국지도학회
Journal Title :Journal of the Korean Cartographic Association
Journal Title(Ko) :한국지도학회지
Volume : 22
No :3
Pages :15-24
DOI :https://doi.org/10.16879/jkca.2022.22.3.015

[1] 박은관･최병남･김대종, 1998, ｢토지이용계획을 위한 GIS 활용방안 연구｣, 국토연구원.

[2] 박지영･강영옥･김지연, 2022, “거리 영상과 시멘틱 세그먼테이션을 활용한 보행환경 평가 지표 개발,” 한국지도학회지, 22(1), 53-68, 10.16879/jkca.2022.22.1.053

[3] 서기환, 2018, “GeoAI 기반의 토지이용변화 모니터링 혁신과 활용방안,” 국토정책 Brief, 1-6.

[4] 우제윤･구지희･이정훈･홍창희, 2001, “국토이용 현황 분석을 위한 토지이용현황도 활용 방안 연구-전북지역 대상,” 한국공간정보시스템학회 논문지, 3(2), 63-70.

[5] 유수홍･이지상･노현주･박효근･손홍규, 2017, “CNN 기법을 이용한 공간정보 자동분류연구,” 한국지형공간정보학회 학술대회, 167-168.

[6] 윤여수･김광백･박현준, 2020, “합성곱 신경망을 이용한 구글 어스에서의 녹지 비율 측정,” 한국정보통신학회논문지, 24(3), 349-354.

[7] 조나혜･강영옥･윤지영･박소연. 2019, “지능형 관광 서비스를 위한 관광 사진 분류체계 개발,” 한국지도학회지, 19(3), 87-101, 10.16879/jkca.2019.19.3.087

[8] 조원호･임용호･박기호, 2019, “합성곱 신경망을 이용한 딥러닝 기반의 토지피복 분류: 한국 토지피복을 대상으로,” 대한지리학회지, 54(1), 1-16.

[9] 조은래･김경환･유환희, 2009, “고해상도 위성영상을 이용한 토지이용변화 분석,” 대한공간정보학회지, 17(1), 3-11.

[10] Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., and Kudlur, M., 2016, Tensorflow: A system for largescale largescale machine learning, Proceedings, 12th Symposium on Operating Systems Design and Implementation, 2–4 November, Savannah, USA, pp.265-283.

[11] Basu, S., Ganguly, S., Mukhopadhyay, S., DiBiano, R., Karki, M., and Nemani, R., 2015, DeepSat: a learning framework for satellite imagery, Proceedings, 23rd SIGSPATIAL International Conference on Advances in Geographic Information Systems. ACM, 37. 10.1145/2820783.2820816

[12] Carrio, A., Sampedro, C., Rodriguez-Ramos, A., and Campoy, P., 2017, A review of deep learning methods and applications for unmanned aerial vehicles, Journal of Sensors, 2017. 10.1155/2017/3296874

[13] Castelluccio, M., Poggi, G., Sansone, C., and Verdoliva, L., 2015, Land use classification in remote sensing images by convolutional neural networks, arXiv preprint arXiv:1508.00092. https://arxiv.org/pdf/1508.00092.pdf

[14] Helber, P., Bischke, B., Dengel, A., and Borthm D., 2017, Eurosat: A novel dataset and deep learning benchmark for land use and land cover classificaꠓtion, arXiv:1709.00029 (v1). 10.1109/IGARSS.2018.8519248

[15] Hu, F., Xia, G.S., Hu, J., and Zhang, L., 2015, Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery, Remote Sensing, 7(11), 14680- 14707. 10.3390/rs71114680

[16] Krizhevsky, A., Sutskever, I., and Hinton, G., 2017, Imagenet classification with deep convolutional neural networks, Communications of the ACM, 60(6), 84-90. 10.1145/3065386

[17] Lary, D., Alavi, A, Gandomi, A., and Walker, A., 2016, Machine learning in geosciences and remote sensing, Geoscience Frontiers, 7(1), 3-10. 10.1145/3065386

[18] Mahdianpari, M., Salehi, B., Rezaee, M., Mohammadiꠓmanesh, F., and Zhang, Y., 2018, Very deep conꠓvolutional neural networks for complex land cover mapping using multispectral remote sensing imagery, Remote Sensing, 10(7), 1119. 10.3390/rs10071119

[19] Marcos, D., Volpi, M., Kellenberger, B., and Tuia, D., 2018, Land cover mapping at very high resolution with rotation equivariant CNNs: Towards small yet accurate models, ISPRS Journal of Photogrammetry and Remote Sensing, 145, 96-107. 10.1016/j.isprsjprs.2018.01.021

[20] Ribani, R. and Marengoni, M., 2019, A survey of transfer learning for convolutional neural networks, Proceedings, 2019 32^nd SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T), IEEE, 47-57. 10.1109/SIBGRAPI-T.2019.0001030707918

[21] Scott, G.J., England, M.R., Starms, W.A., Marcum, R. A., and Davis, C.H., 2017, Training deep convolutional neural networks for land–cover classification of high-resolution imagery, IEEE Geoscience and Remote Sensing Letters, 14(4), 549-553. 10.1109/LGRS.2017.2657778

[22] Wang, J., Luo, C., Huang, H., Zhao, H., and Wang, S., 2017, Transferring pre-trained deep CNNs for remote scene classification with general features learned from linear PCA network, Remote Sensing, 9(3), 225. 10.3390/rs9030225

[23] Xie, M., Jean, N., Burke, M., Lobell, D., and Ermon, S., 2016, Transfer learning from deep features for remote sensing and poverty mapping, Proceedings, Thirtieth AAAI Conference on Artificial Intelligence, 3929-3935. 10.1609/aaai.v30i1.9906

[24] Xing, H., Meng, Y., Wang, Z., Fan, K., and Hou, D., 2018, Exploring geo-tagged photos for land cover validation with deep learning, ISPRS Journal of Photogrammetry and Remote Sensing, 141, 237- 251. 10.1016/j.isprsjprs.2018.04.025

[25] Yang, Y. and Newsam, S., 2010, Bag-of-visual-words and spatial extensions for land-use classification, Proꠓceedings of the 18th SIGSPATIAL international conference on advances in geographic information systems. ACM, 270-279. 10.1145/1869790.1869829

[26] Zhong, Y., Fei, F., Liu, Y., Zhao, B., and Jiao, H., 2017, SatCNN: Satellite image dataset classification using agile convolutional neural networks, Remote Sensing Letters, 8(2), 136-145. 10.1080/2150704X.2016.1235299

Journal of the Korean Cartographic Association ISSN:1598-6160(Print) 한국지도학회지

All Issue