Browse > Article
http://dx.doi.org/10.7780/kjrs.2022.38.6.4.3

Exploratory Study of the Applicability of Kompsat 3/3A Satellite Pan-sharpened Imagery Using Semantic Segmentation Model  

Chae, Hanseong (Department of Geography, Kyung Hee University)
Rhim, Heesoo (Department of Geography, Kyung Hee University)
Lee, Jaegwan (Industry-Academic Cooperation Foundation, Kyung Hee University)
Choi, Jinmu (Department of Geography, Kyung Hee University)
Publication Information
Korean Journal of Remote Sensing / v.38, no.6_4, 2022 , pp. 1889-1900 More about this Journal
Abstract
Roads are an essential factor in the physical functioning of modern society. The spatial information of the road has much longer update cycle than the traffic situation information, and it is necessary to generate the information faster and more accurately than now. In this study, as a way to achieve that goal, the Pan-sharpening technique was applied to satellite images of Kompsat 3 and 3A to improve spatial resolution. Then, the data were used for road extraction using the semantic segmentation technique, which has been actively researched recently. The acquired Kompsat 3/3A pan-sharpened images were trained by putting it into a U-Net based segmentation model along with Massachusetts road data, and the applicability of the images were evaluated. As a result of training and verification, it was found that the model prediction performance was maintained as long as certain conditions were maintained for the input image. Therefore, it is expected that the possibility of utilizing satellite images such as Kompsat satellite will be even higher if rich training data are constructed by applying a method that minimizes the impact of surrounding environmental conditions affecting models such as shadows and surface conditions.
Keywords
Semantic segmentation; U-Net; Pan-sharpening; Kompsat imagery; Road extraction;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 Byun, Y.G., Y.K. Han, and T.B. Chae, 2011. Road Extraction from High Resolution Satellite Image Using Object-based Road Model, Korean Journal of Remote Sensing, 27(4): 421-433 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2011.27.4.421   DOI
2 Kim, H.S. and K.H. Choi, 2022. A Framework of 3D Road Extraction and Update Using Drone Images, Journal of the Korea Academia-Industrial, 23(5): 572-579 (in Korean with English abstract). https://doi.org/10.5762/KAIS.2022.23.5.572   DOI
3 Lee, J.K., K.J. Lee, and S.H. Ju, 2008. Development of Digital Map On-demand Updating System, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 26(5): 537-546 (in Korean with English abstract).
4 Ministry of Government Legislation, 2021. Road Act, https://elaw.klri.re.kr/kor_service/lawView.do?hseq=49884&lang=ENG, Accessed on Nov. 10, 2022.
5 Wang, G., C. Ma, and X. Liang, 2022. Application of Road Extraction from High-Resolution Remote Sensing Images in Tourism Navigation and GIS, Wireless Communications and Mobile Computing, 2022: 1-8. https://doi.org/10.1155/2022/2422030   DOI
6 Zhang, Z.X., Q.J. Liu, and Y.H. Wang, 2018. Road Extraction by Deep Residual U-Net, IEEE Geoscience and Remote Sensing Letters, 15(5): 749-753. https://doi.org/10.1109/LGRS.2018.2802944   DOI
7 Oh, H.Y., S.B. Jeon, G. Kim, and M.H. Jeong, 2022. Road Extraction from Images Using Semantic Segmentation Algorithm, Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 40(3): 237-247 (in Korean with English abstract). https://doi.org/10.7848/ksgpc.2022.40.3.239   DOI
8 Park, S.J., J.H. Han, and S.M. Young, 2020. Efficient Deep Neural Network Architecture based on Semantic Segmentation for Paved Road Detection, Journal of the Korea Institute of Information and Communication Engineering, 24(11): 1437-1444 (in Korean with English abstract). https://doi.org/10.6109/jkiice.2020.24.11.1437   DOI
9 Ronneberger, O., P. Fischer, and T. Brox, 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation, Proc. of Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, Munich, Germany, Oct. 5-9. vol. 9351, pp. 234-241. https://doi.org/10.1007/978-3-319-24574-4_28   DOI
10 Tan, J.H., M. Gao, K. Yang, and T. Duan, 2021. Remote Sensing Road Extraction by Road Segmentation Network, Applied Science, 11(11): 5050. https://doi.org/10.3390/app11115050   DOI
11 Lee, D.H., J.H. Kim, and H.M. Choi, 2007. Histogram-based road border line extractor for road extraction from satellite imagery, Journal of the Institute of Electronics Engineers of Korea SP, 44(5): 27-34 (in Korean with English abstract).
12 Lee, H.J., K.J. Park, and C. Park, 2009. Analysis of Application and Economical Efficiency on Next Generation Digital Maps on Demand Updating System, Journal of the Korean Society for Geospatial Information Science, 17(2): 133-143 (in Korean with English abstract).
13 Abdollahi, A., B. Pradhan, G. Sharma, K.N.A. Maulud, and A. Alamri, 2021. Improving Road Semantic Segmentation Using Generative Adversarial Network, IEEE Access, 9: 64381-64392. https://doi.org/10.1109/ACCESS.2021.3075951   DOI
14 ESA (European Space Agency), 2022a. KOMPSAT-3, https://www.eoportal.org/satellite-missions/kompsat3#eos-electro-optical-subsystem, Accessed on Nov. 10, 2022.
15 ESA (European Space Agency), 2022b. KOMPSAT-3A, https://www.eoportal.org/satellite-missions/kompsat3a#eop-quick-facts-section, Accessed on Nov. 10, 2022.
16 Lee, K.M., S.Y. Go, K.M. Kim, and G.S. Cho, 2014. Extracting Method The New Roads by Using High-resolution Aerial Orthophotos, Journal of the Korean Society for Geospatial Information System, 22(3): 3-10 (in Korean with English abstract). https://doi.org/10.7319/kogsis.2014.22.3.003   DOI
17 Maxwell, A.E., T.A. Warner, and L.A. Guillen, 2021. Accuracy Assessment in Convolutional Neural Network-Based Deep Learning Remote Sensing Studies-Part 2: Recommendations and Best Practices, Remote Sensing, 13(13): 2591. https://doi.org/10.3390/rs13132591   DOI
18 Mnih, V., 2013. Machine Learning for Aerial Image Labeling, University of Toronto, Toronto, ON, Canada.
19 Balraj, A., 2020. UNet (ResNet50 frontend) Road Segmentation PyTorch, https://www.kaggle.com/code/balraj98/unet-resnet50-frontend-roadsegmentation-pytorch, Accessed on Nov. 10, 2022.