| Title |
Comparison of Feature Point Extraction Algorithms Using Unmanned Aerial Vehicle RGB Reference Orthophoto |
| Authors |
이기림(Lee, Kirim) ; 성지훈(Seong, Jihoon) ; 정세정(Jung, Sejung) ; 신현길(Shin, Hyeongil) ; 김도훈(Kim, Dohoon) ; 이원희(Lee Wonhee) |
| DOI |
https://doi.org/10.12652/Ksce.2024.44.2.0263 |
| Keywords |
무인항공기; 지상기준점; 특징점; 정사영상 Unmanned aerial vehicle; Ground control point; Feature point; Orthophoto |
| Abstract |
As unmanned aerial vehicles(UAVs) and sensors have been developed in a variety of ways, it has become possible to update information on the ground faster than existing aerial photography or remote sensing. However, acquisition and input of ground control points(GCPs) UAV photogrammetry takes a lot of time, and geometric distortion occurs if measurement and input of GCPs are incorrect. In this study, RGB-based orthophotos were generated to reduce GCPs measurment and input time, and comparison and evaluation were performed by applying feature point algorithms to target orthophotos from various sensors. Four feature point extraction algorithms were applied to the two study sites, and as a result, speeded up robust features(SURF) was the best in terms of the ratio of matching pairs to feature points. When compared overall, the accelerated-KAZE(AKAZE) method extracted the most feature points and matching pairs, and the binary robust invariant scalable keypoints(BRISK) method extracted the fewest feature points and matching pairs. Through these results, it was confirmed that the AKAZE method is superior when performing geometric correction of the objective orthophoto for each sensor. |