[논문]Land Use and Land Cover Mapping from Kompsat-5 X-band Co-polarized Data Using Conditional Generative Adversarial Network

Jang, Jae-Cheol; Park, Kyung-Ae

doi:10.7780/kjrs.2022.38.1.9

[국내논문] Land Use and Land Cover Mapping from Kompsat-5 X-band Co-polarized Data Using Conditional Generative Adversarial Network 원문보기

대한원격탐사학회지 = Korean journal of remote sensing, v.38 no.1, 2022년, pp.111 - 126

Jang, Jae-Cheol (Department of Science Education, Seoul National University) , Park, Kyung-Ae (Department of Earth Science Education, Seoul National University)

Abstract ▼ AI-Helper

Land use and land cover (LULC) mapping is an important factor in geospatial analysis. Although highly precise ground-based LULC monitoring is possible, it is time consuming and costly. Conversely, because the synthetic aperture radar (SAR) sensor is an all-weather sensor with high resolution, it could replace field-based LULC monitoring systems with low cost and less time requirement. Thus, LULC is one of the major areas in SAR applications. We developed a LULC model using only KOMPSAT-5 single co-polarized data and digital elevation model (DEM) data. Twelve HH-polarized images and 18 VV-polarized images were collected, and two HH-polarized images and four VV-polarized images were selected for the model testing. To train the LULC model, we applied the conditional generative adversarial network (cGAN) method. We used U-Net combined with the residual unit (ResUNet) model to generate the cGAN method. When analyzing the training history at 1732 epochs, the ResUNet model showed a maximum overall accuracy (OA) of 93.89 and a Kappa coefficient of 0.91. The model exhibited high performance in the test datasets with an OA greater than 90. The model accurately distinguished water body areas and showed lower accuracy in wetlands than in the other LULC types. The effect of the DEM on the accuracy of LULC was analyzed. When assessing the accuracy with respect to the incidence angle, owing to the radar shadow caused by the side-looking system of the SAR sensor, the OA tended to decrease as the incidence angle increased. This study is the first to use only KOMPSAT-5 single co-polarized data and deep learning methods to demonstrate the possibility of high-performance LULC monitoring. This study contributes to Earth surface monitoring and the development of deep learning approaches using the KOMPSAT-5 data.

주제어

표/그림 (15)

그림 Fig. 1. MODIS land cover from the Annual International Geosphere-Biosphere Programme over (a) Northeast Asia and (b) the South Korea in 2019.
그림 Fig. 2. A series of KOMPSAT-5 single co-polarized images used for training and testing the land use and land cover (LULC) classification model.
그림 Fig. 3. Land use and land cover (LULC) map produced by Ministry of Environment (ME), South Korea.
그림 Fig. 4. Flow diagram of (a) residual unit and (b) ResUNet.
표 Table 1. Layout of a typical error matrix (confusion matrix)
그림 Fig. 5. Changes in overall accuracy and kappa coefficient with respect to the training epochs of the ResUNet model training epochs, where a red line and blue line indicate the overall accuracy and kappa coefficient from validation datasets, respectively.
그림 Fig. 6. (a, d) KOMPSAT-5 HH-pol backscattering coefficient image observed on (a-c) August 21, 2014 at 09:22 UTC and (d-f) January 2, 2015 at 20:48 UTC, (b, e) result of land use and land cover (LULC) classification derived from KOMPSAT-5 single co-polarized data using ResUNet, and (c, f) the actual LULC.
표 Table 2. Error matrix on the classified map of the KOMPSAT-5 HH-pol image observed on August 21, 2014 at 09:22 UTC
표 Table 3. Error matrix on the classified map of the KOMPSAT-5 HH-pol image observed on January 2, 2015 at 20:48 UTC
그림 Fig. 7. (a, d) KOMPSAT-5 VV-pol backscattering coefficient image observed on (a-c) May 12, 2017 at 21:03 UTC and (d-f) March 6, 2018 at 09:20 UTC, (b, e) result of land use and land cover (LULC) classification derived from KOMPSAT-5 single co-polarized data using ResUNet, and (c, f) the actual LULC.
표 Table 4. Error matrix on the classified map of the KOMPSAT-5 VV-pol image observed on May 12, 2017 at 21:03 UTC
표 Table 5. Error matrix on the classified map of the KOMPSAT-5 VV-pol image observed on March 6, 2018 at 09:20 UTC
그림 Fig. 8. (a, c, e, g) The result of land use and land cover (LULC) classification and (b, d, f, h) the comparison result of actual LULC classification derived from KOMPSAT-5 single co-polarized data including DEM and excluding DEM observed on (a, b) August 21, 2014 at 09:22 UTC, (c, d) January 2, 2015 at 20:48 UTC, (e, f) May 12, 2017 at 21:03 UTC, and (g, h) March 6, 2018 at 09:20 UTC.
그림 Fig. 9. Comparison of overall accuracy with incidence angle of the KOMPSAT-5.
그림 Fig. 10. Illustration of geometrical effect (i.e. foreshortening, layover, and radar shadow) on a given row of the synthetic aperture radar (SAR) image, where h and θ indicate the height and incidence angle, respectively; V, B, and W represent the vegetation, built-up, and water bodies, respectively.

AI 본문요약
AI-Helper

제안 방법

This paper presents a ResUNet model that maps LULC classification using only KOMPSAT-5 single co-polarized data and DEM data. We classified 30 KOMPSAT-5 images into 24 images for model training and six images for model testing.
We classified 30 KOMPSAT-5 images into 24 images for model training and six images for model testing. We used the ResUNet model for LULC classification using only KOMPSAT- 5 single co-polarized data and analyzed the training history of the model. At 1732 epochs, the model showed a maximum OA of 93.

대상 데이터

For the HH polarized data, two KOMPSAT-5 images observed on August 21, 2014, and January 2, 2015, were used for model testing. For the VV-polarized data, four KOMPSAT-5 images observed on April 14, 2017, May 12, 2017, March 6, 2018, and May 5, 2018, were used for model testing. In addition, we used Shuttle Radar Topography Mission (SRTM) DEM data as auxiliary data for LULC classification.

이론/모형

In this study, we adopted the trained ResUNet model with 1732 epochs to estimate LULC from the KOMPSAT-5 single co-polarized data.

성능/효과

91. Thus, we adopted a trained model with epochs of 1732 as the reference LULC model.
The accuracy of each polarization mode was verified. There was no significant difference in accuracy based on polarization, and the model showed high performance for HH-and VV-polarized data with an OA greater than 90.
There was no significant difference in accuracy based on polarization, and the model showed high performance for HH-and VV-polarized data with an OA greater than 90. Overall, the LULC model accurately distinguished water body areas from other LULC types. In particular, the model showed that the UA and PA of wetlands were lower than those of other LULC types.
Overall, the LULC model accurately distinguished water body areas from other LULC types. In particular, the model showed that the UA and PA of wetlands were lower than those of other LULC types. The relatively low accuracy of the wetlands was caused by the tidal conditions.
In particular, the model showed that the UA and PA of wetlands were lower than those of other LULC types. The relatively low accuracy of the wetlands was caused by the tidal conditions. Because South Korea has strong tidal effects, some areas of wetlands can be submerged under high-tide conditions.
Because South Korea has strong tidal effects, some areas of wetlands can be submerged under high-tide conditions. Thus, they showed different backscatter coefficient characteristics, depending on the satellite observation time and tidal conditions, which contributed to the error. Furthermore, when using the model excluding DEM, the model showed a tendency to smoothen the LULC result, difficulty in classifying the LULC over the boundary area of each LULC and the vegetation on wetland, and lower accuracy than the model including DEM.
Thus, they showed different backscatter coefficient characteristics, depending on the satellite observation time and tidal conditions, which contributed to the error. Furthermore, when using the model excluding DEM, the model showed a tendency to smoothen the LULC result, difficulty in classifying the LULC over the boundary area of each LULC and the vegetation on wetland, and lower accuracy than the model including DEM. When assessing the accuracy with respect to the incidence angle, the OA showed a tendency to decrease as the incidence angle increased.
Furthermore, when using the model excluding DEM, the model showed a tendency to smoothen the LULC result, difficulty in classifying the LULC over the boundary area of each LULC and the vegetation on wetland, and lower accuracy than the model including DEM. When assessing the accuracy with respect to the incidence angle, the OA showed a tendency to decrease as the incidence angle increased. This is because of the radar shadow caused by the side-looking system of the SAR sensor.
Field-based LULC monitoring systems are time- consuming, costly, and difficult to operate in real time and will play only a limited role in the future. However, LULC based on satellite data can save time and cost, and it can be operated in real time.
However, LULC based on satellite data can save time and cost, and it can be operated in real time. In particular, among the satellite data, because the SAR sensor is less affected by atmospheric conditions and 24 hr available observation time, it is useful for monitoring the Earth’s surface. This study is the first LULC application that uses only KOMPSAT-5 single co-polarized data and deep learning methods.
In particular, among the satellite data, because the SAR sensor is less affected by atmospheric conditions and 24 hr available observation time, it is useful for monitoring the Earth’s surface. This study is the first LULC application that uses only KOMPSAT-5 single co-polarized data and deep learning methods. This demonstrates the possibility of an LULC monitoring system using only KOMPSAT-5 single-co-polarized data with high performance.
This study is the first LULC application that uses only KOMPSAT-5 single co-polarized data and deep learning methods. This demonstrates the possibility of an LULC monitoring system using only KOMPSAT-5 single-co-polarized data with high performance. It is believed that the accuracy and application area of the LULC model will be further improved by using more training data.
It is believed that the accuracy and application area of the LULC model will be further improved by using more training data. This study contributes to the application of KOMPSAT-5 data and the development of deep-learning approaches using KOMPSAT-5 data.
We used the ResUNet model for LULC classification using only KOMPSAT- 5 single co-polarized data and analyzed the training history of the model. At 1732 epochs, the model showed a maximum OA of 93.89 and a kappa coefficient of 0.91. Thus, we adopted a trained model with epochs of 1732 as the reference LULC model.
The accuracy of each polarization mode was verified. There was no significant difference in accuracy based on polarization, and the model showed high performance for HH-and VV-polarized data with an OA greater than 90. Overall, the LULC model accurately distinguished water body areas from other LULC types.

후속연구

This demonstrates the possibility of an LULC monitoring system using only KOMPSAT-5 single-co-polarized data with high performance. It is believed that the accuracy and application area of the LULC model will be further improved by using more training data. This study contributes to the application of KOMPSAT-5 data and the development of deep-learning approaches using KOMPSAT-5 data.

참고문헌 (26)

Alberga, V., 2007. A study of land cover classification Using polarimetric SAR parameters, International Journal of Remote Sensing, 28(17): 3851-3870.

상세보기
Dwivedi, R.S., K. Sreenivas, and K.V. Ramana, 2005. Cover: Land- use/land- cover change analysis in part of Ethiopia using Landsat Thematic Mapper data, International Journal of Remote Sensing, 26(7): 1285-1287.

상세보기
Friedl, M.A., D. Sulla-Menashe, B. Tan, A. Schneider, N. Ramankutty, A. Sibley, and X. Huang, 2010. MODIS Collection 5 global land cover: algorithm refinements and characterization of new datasets, Remote Sensing of Environment, 114(1): 168-182.

상세보기
Goel, K., 2014. Advanced stacking techniques and Applications in high resolution SAR interferometry, Technical University of Munich, Munich, Germany.
Hasselmann, K., R.K. Raney, W.J. Plant, W. Alpers, R.A. Shuchman, D.R. Lyzenga, C.L. Rufenach, and M.J. Tucker, 1985. Theory of synthetic aperture radar ocean imaging: A MARSEN view, Journal of Geophysical Research: Oceans, 90(C3): 4659-4686.

상세보기
He, K., X. Zhang, S. Ren, and J. Sun, 2016. Deep residual learning for image recognition, Proc. of 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, Jun. 27-30, pp. 770-778.
Horritt, M.S., D.C. Mason, D.M. Cobby, I.J. Davenport, and P.D. Bates, 2003. Waterline mapping in flooded vegetation from airborne SAR imagery, Remote Sensing of Environment, 85(3): 271-281.

상세보기
Jang, J.C., K. Park, and D. Yang, 2018. Validation of sea surface wind estimated from KOMPSAT-5 backscattering coefficient data, Korean Journal of Remote Sensing, 34(6-3): 1383-1398 (in Korean with English abstract).

원문보기 상세보기
Jang, J.C., K. Park, D. Yang, and S.G. Lee, 2019. Improvement of KOMPSAT-5 Sea Surface Wind with Correction Equation Retrieval and Application of Backscattering Coefficient, Korean Journal of Remote Sensing, 35(6-4): 1373-1389 (in Korean with English abstract).
Kavzoglu, T. and P.M. Mather, 2003. The use of backpropagating artificial neural networks in land cover classification, International Journal of Remote Sensing, 24(23): 4907-4938.

상세보기
Kropatsch, W.G. and D. Strobl, 1990. The generation of SAR layover and shadow maps from digital elevation models, IEEE Transactions on Geoscience and Remote Sensing, 28(1): 98-107.

상세보기
Kumar, P., D.K. Gupta, V.N. Mishra, and R. Prasad, 2015. Comparison of support vector machine, artificial neural network, and spectral angle mapper algorithms for crop classification using LISS IV data, International Journal of Remote Sensing, 36(6): 1604-1617.

상세보기
Li, C. and M. Wand, 2016. Precomputed real-time texture synthesis with markovian generative adversarial networks, Proc. of 2016 European Conference on Computer Vision, Amsterdam, Netherlands, Oct. 11-14, pp. 702-716.
Liu, X., J. He, Y. Yao, J. Zhang, H. Liang, H. Wang, and Y. Hong, 2017. Classifying urban land use by integrating remote sensing and social media data, International Journal of Geographical Information Science, 31(8): 1675-1696.

상세보기
Lu, D. and Q. Weng, 2007. A survey of image classification methods and techniques for improving classification performance, International Journal of Remote Sensing, 28(5): 823-870.

상세보기
Niu, X., D. Yang, K. Yang, H. Pan, Y. Dou, and F. Xia, 2021. Image translation between high-resolution optical and synthetic aperture radar (SAR) data, International Journal of Remote Sensing, 42(12): 4758-4784.

상세보기
Niu, X. and Y. Ban, 2013. Multi-temporal RADARSAT-2 polarimetric SAR data for urban land-cover classification using an object-based support vector machine and a rule-based approach, International Journal of Remote Sensing, 34(1): 1-26.

상세보기
Park, W., W.K. Baek, J.S. Won, and H.S. Jung, 2020. Comparison of Input Image Dimensions for Ship Detection from KOMPSAT-5 SAR Image Using Deep Neural Network, Journal of Coastal Research, 102(SI): 208-217.
Phiri, D. and J. Morgenroth, 2017. Developments in Landsat land cover classification methods: A review, Remote Sensing, 9(9): 967.

상세보기
Prasath, V.S. and O. Haddad, 2014. Radar shadow detection in synthetic aperture radar images using digital elevation model and projections, Journal of Applied Remote Sensing, 8(1): 083628.

상세보기
Ronneberger, O., P. Fischer, and T. Brox, 2015. U-net: Convolutional networks for biomedical image segmentation, Proc. of 2015 International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany, Oct. 5- 9, pp. 234-241.
Shiraishi, T., T. Motohka, R.B. Thapa, M. Watanabe, And M. Shimada, 2014.Comparative assessment Of supervised classifiers for land use-land cover classification in a tropical region using time-series PALSAR mosaic data, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(4): 1186-1199.

상세보기
Turnes, J.N., J.D.B. Castro, D.L. Torres, P.J.S. Vega, R.Q. Feitosa, and P.N. Happ, 2020. Atrous cgan for sar to optical image translation, IEEE Geoscience and Remote Sensing Letters, 19: 1-5.
Zhang, C., I. Sargent, X. Pan, H. Li, A. Gardiner, J. Hare, and P.M. Atkinson, 2019.Joint Deep Learning for land cover and land use classification, Remote Sensing of Environment, 221: 173-187.

상세보기
Zhang, G., W.B. Fei, Z. Li, X. Zhu, and D.R. Li, 2010. Evaluation of the RPC model for spaceborne SAR imagery, Photogrammetric Engineering and Remote Sensing, 76(6): 727-733.

상세보기
Zhang, Z., Q. Liu, and Y. Wang, 2018. Road extraction by deep residual u-net, IEEE Geoscience and Remote Sensing Letters, 15(5): 749-753.

상세보기

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증