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

Woochul Kang; Eun-kyung Jang

doi:10.17820/eri.2022.9.4.218

All Issue

2022 Vol.9, Issue 4 Preview Page Next Page

Original Article

Review of Land Cover Classification Potential in River Spaces Using Satellite Imagery and Deep Learning-Based Image Training Method 딥 러닝 기반 이미지 트레이닝을 활용한 하천 공간 내 피복 분류 가능성 검토

31 December 2022. pp. 218-227

PDF XML

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

본 연구는 효율적인 하천 관리를 위해 중요한 데이터 중 하나인 하천 공간의 토지피복 분류를 위해 딥 러닝 기반의 이미지 트레이닝 방법의 활용가능성을 검토하였다. 이를 위해 대상 구간의 RGB 이미지를 활용하여 라벨링 작업 후 학습시킨 결과를 활용하여 기존 대분류 지표를 기준으로 토지피복 분류를 시도하였다. 또한 개방형으로 제공되는 Sentinel-2 위성 영상으로부터 무감독 분류 및 감독 분류에 의한 하천 공간의 토지피복 분류를 수행하였으며, 딥 러닝 기반 이미지 분류 결과와 비교하였다. 분석 결과의 경우 무감독 분류 결과와 비교하여 매우 향상된 예측 결과를 보여주었으며, 고해상도 이미지의 경우 더욱 정확한 분류 결과를 제시하였다. 단순한 이미지 라벨링을 통해 분류된 피복 분류 결과는 하천 공간 내 수역과 습지의 분류 가능성을 보여주었으며, 향후 추가적인 연구 수행이 이루어진다면 하천 관리를 위해 딥 러닝 기반 이미지 트레이닝 기법을 이용한 하천 공간내 피복 분류 결과의 활용이 가능할 것으로 판단된다.

키워드

Bayesian Deep Learning

이미지 분류

토지피복

하천 공간

위성영상

References

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)

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)

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. 10.1016/j.catena.2021.105142

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. 10.3390/app12031119

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. 10.3390/app12126125

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. 10.1007/s12205-019-0085-3

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) 10.11108/kagis.2012.15.4.026

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)

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)

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)

Information

Publisher :Korean Society of Ecology and Infrastructure Engineering
Publisher(Ko) :응용생태공학회
Journal Title :Ecology and Resilient Infrastructure
Journal Title(Ko) :응용생태공학회 논문집
Volume : 9
No :4
Pages :218-227
Received Date : 2022-10-11
Revised Date : 2022-12-06
Accepted Date : 2022-12-06
DOI :https://doi.org/10.17820/eri.2022.9.4.218

Ecology and Resilient Infrastructure ISSN:2288-8527(Online) 응용생태공학회 논문집

All Issue