Enhancing Wildfire Damage Detection Performance with Swin Transformer Using PlanetScope and Sentinel-2 Satellite Imagery: Analysis of Multi-Source Data Fusion
Wildfire damage detection has a pivotal role in forest management and recovery strategy planning. This study demonstrates that the use of a deep learning Swin (shifted windows) Transformer model, by integrating high-resolution PlanetScope and Sentinel-2 satellite imagery, can effectively enhance wildfire damage detection performance. A 5-fold cross-validation was conducted on five major wildfire areas in South Korea, with independent detection performance evaluated for each region to assess the model’s reliability and generalization. The comparison between traditional geometric augmentat...
Korean J. Remote Sens. 2024; 40(6): 991-1004
A Study on the Planning Methodology of Geographic Education Contents Using Satellite Information Data: Case Studies of Geography Education Content in Incheon and Jeju Island
This study explores ways to expand the area of use of satellite information data and increase its value. Specifically, on the premise of using satellite information data in the field of geography education, a methodology for planning geography education content is presented. For the research methodology, domestic and foreign literature surveys and cases in the content area were investigated and analyzed. According to domestic and international case studies, education was provided to analyze changes in the urban environment by applying Global Positioning System (GPS) and Geographic Information ...
Korean J. Remote Sens. 2024; 40(6): 1253-1264
Automatic Training Data Generation Method for Self-Supervised End-to-End Matching Network to Extract Matching Points from Very High-Resolution Satellite Imagery
In this study, we propose an automatic training dataset generation method to build a self-supervised matching network, using an End-to-end approach, to extract matching points between very high-resolution (VHR) satellite images. A homography matrix that transforms the scale, rotation, and translation of a single VHR remote-sensing image is applied to generate reference and sensed image patches. After adjusting the contrast and brightness of the sensed image patch, Gaussian and speckle noise are added, and shading and motion blur effects are applied to give it different characteristics from the...
Korean J. Remote Sens. 2024; 40(6): 1449-1460
A Method for Time-Series Change Detection in Urban Areas Based on SHP and Coherence Information from SAR Imagery: Focusing on the Application of KOMPSAT-5 Imagery in Port Areas
In this paper, we proposed a method based on statistically homogeneous pixel (SHP) and coherence information for time series change detection of urban areas using synthetic aperture radar (SAR) images. The proposed framework was applied to KOMPSAT-5 SAR time series data to conduct time series change detection experiments on container yards in port areas. If the algorithm is verified with more SAR images in the future, the algorithm for detecting time series changes in areas of interest using domestic KOMPSAT SAR satellite images will become more generalized and reliable.
Korean J. Remote Sens. 2024; 40(6): 1475-1481
December 31, 2024

Vol. 40, No. 6, pp. 881-1521

Aims and Scope
Korean Journal of Remote Sensing serves the remote sensing community with the publication of results based on theory, technology and applications of remote sensing fields. Thoroughly interdisciplinary, this journal focuses on the research and development of remote sensing science and technologies and promotes the exchange of expert knowledge among remote sensing researchers as well.
More +

Current Issue Vol. 40, No. 6, December 2024

Online First Articles

Submit Your Manuscript

If you want to submit your manuscript to us,
please submit it through the online system now.

Go to Submit

Most View (2021 - 2023)

View More +

Most Downloaded (2021 - 2023)

View More +

Announcement

View More +

About the Journal

Aims and Scope

Korean Journal of Remote Sensing serves the remote sensing community with the publication of results based on theory, technology and applications of remote sensing fields. Thoroughly interdisciplinary, this journal focuses on the research and development of remote sensing science and technologies and promotes the exchange of expert knowledge among remote sensing researchers as well.

Areas of interest include, but are not necessarily restricted to:
– Remote Sensor Technology
– Novel Sensor Design and Platforms Development ...

More +

Editorial Office

VISITORS

Since August 10, 2024
TODAY 134
TOTAL 28,031

Korean Journal of Remote Sensing