Abstract
Remote sensing image registration technology has important significance in the field of image processing. The registration technology of SAR images has been a hot research in this field, and it is also a challenge. Aiming at this difficulty, this paper proposes a fusion feature algorithm, which combines gradient, grayscale, texture, geometry and other features in heterogeneous remote sensing images for comprehensive matching. Compared with the traditional single feature, the improved detector has good performance and registration accuracy in SAR image and visible light image registration.
Full Text
Published Version
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 call