Browse > Article
http://dx.doi.org/10.17820/eri.2022.9.4.218

Review of Land Cover Classification Potential in River Spaces Using Satellite Imagery and Deep Learning-Based Image Training Method  

Woochul, Kang (Department of Land, Water and Environment Research, Korea Institute of Civil Engineering and Building Technology)
Eun-kyung, Jang (Department of Land, Water and Environment Research, Korea Institute of Civil Engineering and Building Technology)
Publication Information
Ecology and Resilient Infrastructure / v.9, no.4, 2022 , pp. 218-227 More about this Journal
Abstract
This study attempted classification through deep learning-based image training for land cover classification in river spaces which is one of the important data for efficient river management. For this purpose, land cover classification analysis with the RGB image of the target section based on the category classification index of major land cover map was conducted by using the learning outcomes from the result of labeling. In addition, land cover classification of the river spaces was performed by unsupervised and supervised classification from Sentinel-2 satellite images provided in an open format, and this was compared with the results of deep learning-based image classification. As a result of the analysis, it showed more accurate prediction results compared to unsupervised classification results, and it presented significantly improved classification results in the case of high-resolution images. The result of this study showed the possibility of classifying water areas and wetlands in the river spaces, and if additional research is performed in the future, the deep learning based image train method for the land cover classification could be used for river management.
Keywords
Bayesian deep learning; Image classification; Land cover; River space; Satellite image;
Citations & Related Records
Times Cited By KSCI : 4  (Citation Analysis)
연도 인용수 순위
1 Jo, W., Lim, Y., and Park, K. 2019. Deep learning based Land Cover Classification Using Convolutional Neural Network: a case study of Korea. Journal of the Korean Geographical Society 54(1): 1-16. (in Korean)
2 Kang, W., Choe, H., Jang, E., Ko, D., Kang, J., and Yeo, H. 2021a. Determination of Stream Reach for River Environment Assessment System Using Satellite Image. Ecology and Resilient Infrastructure 8(4): 179-193. (in Korean)   DOI
3 Kang, W., Jang, E.K., Yang, C.Y., and Julien, P.Y. 2021b. Geospatial analysis and model development for specific degradation in South Korea using model tree data mining. Catena, 200, 105142.
4 Kang, W., Lee, K., and Jang, E.K. 2022a. Evaluation and Validation of Estimated Sediment Yield and Transport Model Developed with Model Tree Technique. Applied Sciences 12(3), 1119.
5 Kang, W., Lee, K., and Kim, J. 2022b. Prediction of Suspended Sediment Concentration Based on the Turbidity-Concentration Relationship Determined via Underwater Image Analysis. Applied Sciences 12(12), 6125.
6 Kang, W., Yang, C.Y., Lee, J., and Julien, P.Y. 2019. Sediment yield for ungauged watersheds in South Korea. KSCE Journal of Civil Engineering 23(12): 5109-5120.   DOI
7 Kim, H. and Yeom, J. 2012. A Study on Object-Based Image Analysis Methods for Land Cover Classification in Agricultural Areas. The Korean Association of Geographic Information Studies 15(4): 26-41. (in Korean)   DOI
8 Lee, G. and Choi, Y. 2014. Land Cover Classification of Nakdong River Basin using Object-Based Image Analysis Methods. Journal of The Korean Cadastre Information Association 16(3): 3-18. (in Korean)
9 Lee, H., Ru, J., and Yu, Y. 2010. Extracting High Quality Thematic Information by Using High-Resoultion Satellite Imagery. Journal of Korean Society for Geospatial Information Science 18(1): 73-81. (in Korean)
10 Woo, H. 2017. Assessment of Definitions and Models of River Restoration based on the Functions, Services, and Values of River Ecosystem. Ecology and Resilient Infrastructure 4(3): 123-129. (in Korean)   DOI