Abstract
This paper introduces a robust method for panoramic unmanned aerial vehicle (UAV) image mosaic. In the traditional automatic panoramic image stitching method (Autostitch), it assumes that the camera rotates about its optical centre and the group of transformations the source images may undergo is a special group of homographies. It is rare to get such ideal data in reality. In particular, remote sensing images obtained by UAV do not satisfy such an ideal situation, where the images may not be on a plane yet and even may suffer from nonrigid changes, leading to poor mosaic results. To overcome the above mentioned challenges, in this paper a nonrigid matching algorithm is introduced to the mosaic system to generate accurate feature matching on remote sensing images. We also propose a new strategy for bundle adjustment to make the mosaic system suitable for the UAV image panoramic mosaic effect. Experimental results show that our method outperforms the traditional method and some of the latest methods in terms of visual effect.
Highlights
Unmanned aerial vehicle (UAV) remote sensing is a low-altitude technology, which has become an important means of information acquisition
To address the aforementioned challenges, we introduce a nonrigid matching algorithm on the basis of motion field interpolation, namely, vector field consensus (VFC) [16], to the mosaic system for generating accurate feature matching on remote sensing images
In bundle adjustment [17], we propose a new strategy that improves the original relationship of homography conversion and use the homography response to perform bundle adjustment, which is robust to our image mosaic
Summary
Unmanned aerial vehicle (UAV) remote sensing is a low-altitude technology, which has become an important means of information acquisition. A UAV image has a small view of scene due to the low flying altitude and limited focal length of the camera; capturing a relatively complete target area becomes difficult. Multiple images of the same target should be combined by technical means to obtain a complete scene of the desired target. Traditional image stitching [4] includes feature matching, image matching, bundle adjustment, automatic panorama straightening, gain compensation, and multiband blending [5,6]. This system may appear perfect, but several errors emerge when images contain a large amount of nonideal data. The effect remains unsatisfactory, and the problem may be even further severe when scenes are captured by UAVs involving nonrigid changes
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
