Journal
COMPUTERS & ELECTRICAL ENGINEERING
Volume 90, Issue -, Pages -Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.compeleceng.2021.107007
Keywords
UAV images; Image mosaic; RSIFT; Ghosting elimination; Scale invariance
Categories
Funding
- National Natural Science Foundation of China [61671470]
Ask authors/readers for more resources
This research focuses on UAV image mosaic to generate high-quality panoramic images rapidly without distortions or ghosting. By constructing a RSIFT operator and utilizing the AANAP algorithm, the proposed method achieves improved feature extraction speed by at least 78% compared to SIFT, effectively eliminating motion ghosting. The experimental results demonstrate fast and high-quality mosaic images.
Research on unmanned aerial vehicles (UAV) image mosaic aims to generate a high-quality panoramic image without distortions or ghosting at a high operation speed. To this end, this study first constructed a Rapid Scale-Invariant Feature Transform (RSIFT) operator to reduce computer time. Subsequently, we employ the As-Natural-As-Possible (AANAP) algorithm for image registration. An image segmentation algorithm is applied to eliminate the motion ghosting. Lastly, A special aerial images dataset for image mosaic is constructed, based on which the comparable experiments with state-of-art image mosaic methods are conducted. Experimental results demonstrate that the feature extraction speed with the proposed algorithm is improved by at least 78% compared to SIFT, and the motion ghosting is effectively eliminated, thus achieving a fast and high-quality mosaic.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available