Korean J. Remote Sens. 2024; 40(4): 387-396
Published online: August 31, 2024
https://doi.org/10.7780/kjrs.2024.40.4.6
© Korean Society of Remote Sensing
허재원1, 이창희2, 서두천3, 오재홍4, 이창노5, 한유경6*
1서울과학기술대학교 건설시스템공학과 석사과정생
2서울과학기술대학교 건설시스템공학과 박사과정생
3한국항공우주연구원 지상국 기술연구부 책임연구원
4한국해양대학교 건설공학과 교수
5서울과학기술대학교 건설시스템공학과 교수
6서울과학기술대학교 건설시스템공학과 부교수
Correspondence to : Youkyung Han
E-mail: han602@seoultech.ac.kr
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (https://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Most very high-resolution (VHR) satellite images provide rational polynomial coefficients (RPC) data to facilitate the transformation between ground coordinates and image coordinates. However, initial RPC often contains geometric errors, necessitating correction through matching with ground control points (GCPs). A GCP chip is a small image patch extracted from an orthorectified image together with height information of the center point, which can be directly used for geometric correction. Many studies have focused on area-based matching methods to accurately align GCP chips with VHR satellite images. In cases with seasonal differences or changed areas, edge-based algorithms are often used for matching due to the difficulty of relying solely on pixel values. However, traditional edge extraction algorithms, such as canny edge detectors, require appropriate threshold settings tailored to the spectral characteristics of satellite images. Therefore, this study utilizes deep learning-based edge information that is insensitive to the regional characteristics of satellite images for matching. Specifically, we use a pretrained pixel difference network (PiDiNet) to generate the edge maps for both satellite images and GCP chips. These edge maps are then used as input for normalized cross-correlation (NCC) and relative edge cross-correlation (RECC) to identify the peak points with the highest correlation between the two edge maps. To remove mismatched pairs and thus obtain the bias-compensated RPC, we iteratively apply the data snooping. Finally, we compare the results qualitatively and quantitatively with those obtained from traditional NCC and RECC methods. The PiDiNet network approach achieved high matching accuracy with root mean square error (RMSE) values ranging from 0.3 to 0.9 pixels. However, the PiDiNet-generated edges were thicker compared to those from the canny method, leading to slightly lower registration accuracy in some images. Nevertheless, PiDiNet consistently produced characteristic edge information, allowing for successful matching even in challenging regions. This study demonstrates that improving the robustness of edge-based registration methods can facilitate effective registration across diverse regions.
Keywords Edge information, RPC compensation, Image registration, Deep learning
Korean J. Remote Sens. 2024; 40(4): 387-396
Published online August 31, 2024 https://doi.org/10.7780/kjrs.2024.40.4.6
Copyright © Korean Society of Remote Sensing.
허재원1, 이창희2, 서두천3, 오재홍4, 이창노5, 한유경6*
1서울과학기술대학교 건설시스템공학과 석사과정생
2서울과학기술대학교 건설시스템공학과 박사과정생
3한국항공우주연구원 지상국 기술연구부 책임연구원
4한국해양대학교 건설공학과 교수
5서울과학기술대학교 건설시스템공학과 교수
6서울과학기술대학교 건설시스템공학과 부교수
Jaewon Hur1, Changhui Lee2, Doochun Seo3, Jaehong Oh4, Changno Lee5, Youkyung Han6*
1Master Student, Department of Civil Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea
2PhD Student, Department of Civil Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea
3Principal Researcher, Satellite Ground Station R&D Division, National Satellite Operation and Application Center, Korea Aerospace Research Institute, Daejeon, Republic of Korea
4Professor, Department of Civil Engineering, Korea Maritime and Ocean University, Busan, Republic of Korea
5Professor, Department of Civil Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea
6Associate Professor, Department of Civil Engineering, Seoul National University of Science and Technology, Seoul, Republic of Korea
Correspondence to:Youkyung Han
E-mail: han602@seoultech.ac.kr
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (https://creativecommons.org/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Most very high-resolution (VHR) satellite images provide rational polynomial coefficients (RPC) data to facilitate the transformation between ground coordinates and image coordinates. However, initial RPC often contains geometric errors, necessitating correction through matching with ground control points (GCPs). A GCP chip is a small image patch extracted from an orthorectified image together with height information of the center point, which can be directly used for geometric correction. Many studies have focused on area-based matching methods to accurately align GCP chips with VHR satellite images. In cases with seasonal differences or changed areas, edge-based algorithms are often used for matching due to the difficulty of relying solely on pixel values. However, traditional edge extraction algorithms, such as canny edge detectors, require appropriate threshold settings tailored to the spectral characteristics of satellite images. Therefore, this study utilizes deep learning-based edge information that is insensitive to the regional characteristics of satellite images for matching. Specifically, we use a pretrained pixel difference network (PiDiNet) to generate the edge maps for both satellite images and GCP chips. These edge maps are then used as input for normalized cross-correlation (NCC) and relative edge cross-correlation (RECC) to identify the peak points with the highest correlation between the two edge maps. To remove mismatched pairs and thus obtain the bias-compensated RPC, we iteratively apply the data snooping. Finally, we compare the results qualitatively and quantitatively with those obtained from traditional NCC and RECC methods. The PiDiNet network approach achieved high matching accuracy with root mean square error (RMSE) values ranging from 0.3 to 0.9 pixels. However, the PiDiNet-generated edges were thicker compared to those from the canny method, leading to slightly lower registration accuracy in some images. Nevertheless, PiDiNet consistently produced characteristic edge information, allowing for successful matching even in challenging regions. This study demonstrates that improving the robustness of edge-based registration methods can facilitate effective registration across diverse regions.
Keywords: Edge information, RPC compensation, Image registration, Deep learning
Woo-Dam Sim, Jung-Soo Lee
Korean J. Remote Sens. 2024; 40(5): 675-689