AUTHOR=Zong Huilin , Yuan Xiping , Gan Shu , Zhang Xiaolun , Yang Minglong , Lv Jie 

TITLE=UAV image matching of mountainous terrain using the LoFTR deep learning model

JOURNAL=Frontiers in Earth Science

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/earth-science/articles/10.3389/feart.2023.1203078

DOI=10.3389/feart.2023.1203078

ISSN=2296-6463

ABSTRACT=In natural terrain scene UAV image matching, traditional feature point-based methods often have problems such as an unstable number of extracted feature points, difficulty in detecting feature points in weak texture areas, uneven distribution, and low robustness. Deep learning-based image matching methods can produce larger and more reasonably distributed matching pairs, so this paper tries to perform UAV image matching based on deep learning LoFTR algorithm for natural terrain scenes. The critical technical process is: first, the LoFTR algorithm is used to generate dense feature matching, and then the epipolar line constraints are used to purify the interior points, specifically, this paper uses the MAGSAC++ method to estimate the fundamental matrix, eliminate the wrong matching pairs, and finally get reliable matching results. In this paper, six sets of visible images taken by different UAVs equipped with different sensors in the field are selected as experimental data to test the method and are compared and analyzed with the traditional classical SIFT, ASIFT, AKAZE and the KeyNet-AdaLAM deep learning method. The experimental results show that the method in this paper obtains a dense number of robust matching pairs with uniform spatial distribution in the UAV image matching of natural scenes mainly in mountainous areas, and the comprehensive performance is higher and more advantageous than the comparison methods.