Abstract
Dense image matching is a crucial step in many image processing tasks. Subpixel accuracy and fractional measurement are commonly pursued, considering the image resolution and application requirement, especially in the field of remote sensing. In this study, we conducted a practical analysis and comparative study on area-based dense image matching with subpixel accuracy for remote sensing applications, with a specific focus on the subpixel capability and robustness. Twelve representative matching algorithms with two types of correlation-based similarity measures and seven types of subpixel methods were selected. The existing matching algorithms were compared and evaluated in a simulated experiment using synthetic image pairs with varying amounts of aliasing and two real applications of attitude jitter detection and disparity estimation. The experimental results indicate that there are two types of systematic errors: displacement-dependent errors, depending on the fractional values of displacement, and displacement-independent errors represented as unexpected wave artifacts in this study. In addition, the strengths and limitations of different matching algorithms on the robustness to these two types of systematic errors were investigated and discussed.
Highlights
Dense image matching is the process of determining correspondences between two or more overlapping images in a high-density or even pixel-to-pixel manner
A simple visual inspection of the disparity maps showed that there existed systematic errors in some a simple visual inspection of the disparity maps showed that there existed systematic errors in some matching disparity maps obtained by SimiFit-NCC, SimiFit-SGM, and MicMac matching results
Based on the experimental results using both simulated and real data, the systematic errors in subpixel dense image matching can be generally divided into two types: displacement-dependent induced in subpixel dense image matching can be generally divided into two types: and displacement-independent errors
Summary
Dense image matching is the process of determining correspondences between two or more overlapping images in a high-density or even pixel-to-pixel manner. The objective and contribution of this study are extended to subpixel measurement [48,49], while the selected matching algorithms have been often to compare and investigate the relative performance of typical algorithms for dense image matching used in different applications with success and cover seven types of subpixel methods mentioned on remote sensing data with a particular focus on the subpixel capability and robustness to the above. The remainder of this similarity measures, and the subpixel methods under study.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
