- GeoAI Dataset for Training Deep Learning-Based Optical Satellite Image Matching Model
-
Jin-Woo Yu, Che-Won Park, Hyung-Sup Jung
-
GEO DATA. 2023;5(4):244-250. Published online December 28, 2023
-
DOI: https://doi.org/10.22761/GD.2023.0048
-
-
 Abstract
 PDF
- Satellite imagery is being used to monitor the Earth, as it allows for the continuous provision of multi-temporal observations with consistent quality. To analyze time series remote sensing data with high accuracy, the process of image registration must be conducted beforehand. Image registration techniques are mainly divided into region-based registration and feature-based registration, and both techniques extract the same points based on the similarity of spectral characteristics and object shapes between master and slave images. In addition, recently, deep learning-based siamese neural network and convolutional neural network models have been utilized to match images. This has high performance compared to previous non-deep learning algorithms, but a very large amount of data is required to train a deep learning-based image registration model. In this study, we aim to generate a dataset for training a deep learning-based optical image registration model. To build the data, we acquired Satellite Side-Looking (S2Looking) data, an open dataset, and performed preprocessing and data augmentation on the data to create input data. After that, we added offsets to the X and Y directions between the master and slave images to create label data. The preprocessed input data and labeled data were used to build a dataset suitable for image registration. The data is expected to be useful for training deep learning-based satellite image registration models.
- Mapping of Groundwater Pollution Vulnerability in Entire South Korea Using DRATIC Model
-
Won-Kyung Baek, Sung-Hwan Park, Jin-Woo Yu, Young-Woong Yoon, Hyung-Sup Jeong
-
GEO DATA. 2021;3(2):32-38. Published online July 21, 2021
-
DOI: https://doi.org/10.22761/DJ2021.3.2.005
-
-
Abstract
PDF
- Groundwater pollution vulnerability was mapped for entire South Korea using groundwater, topography, geology, and soil data. For this, the DRASTIC model developed by the US Environmental Protection Agency was used and the geographic information system (GIS) was used as the basic tool. This groundwater pollution vulnerability map can be usefully used as basic data for groundwater development and conservation management. The constructed data is provided as entire South Korean and regional data, respectively. In addition, in order to expand the accessibility of the data, it is converted and provided in three data formats: ASCII, ArcGIS Grid, and GeoTIFF. All these satellite image analysis data can be downloaded free of charge from the Environment Big Data Platform website (www.bigdata-environment.kr).
- Construction of Analyzed Satellite Image and Service
-
Won-Kyung Baek, Sung-Hwan Park, Jin-Woo Yu, Young-Woong Yoon, Hyung-Sup Jung
-
GEO DATA. 2020;2(2):45-55. Published online December 30, 2020
-
DOI: https://doi.org/10.22761/DJ2020.2.2.007
-
-
634
View
-
15
Download
-
1
Citations
-
Abstract
PDF
- In this study, 17 types of satellite analysis maps were generated using Landsat-8 and Sentinel-2 satellite images acquired at 2019 and 2020. Totally, 68 of satellite analysis data were produced. The scope of deployment is South Korea as a whole, with a resolution of 30 meters, and the coordinate system is UTM-K coordinates. The established data will be provided in both South Korean and regional data respectively. In addition, it is provided by three data format: ASCII, ArcGIS Grid, and GeoTIFF for enhancing accessibility of the data. All these satellite analysis data can be downloaded free of charge from the Environmental Big Data website (www.bigdata-environment.kr), an environmental business big data platform.
-
Citations
Citations to this article as recorded by  - Expand and Renewal of Analyzed Satellite Image and Service
Young-Woong Yoon, Che-Won Park, Sung-Hyun Gong, Won-Kyung Baek, Hyung-Sup Jung
GEO DATA.2021; 3(4): 32. CrossRef
|
GAIDAS
