Arming at the problems of large-scale remote sensing image, complex surface background and sparse aggregation of aircraft objects in remote sensing detection, we propose an efficient remote sensing aircraft object detection algorithm based on Faster R-CNN. Firstly, we embed a lightweight aircraft object recognition network in Faster R-CNN network to filter invalid remote sensing image slices. Then, we fuse the feature map of lightweight aircraft object recognition network (LAORNet) into Faster R-CNN to enhance the semantics of aircraft objects. In addition, we add an rotation parameter to the Faster R-CNN bordering regression, so that the Faster R-CNN can predict the rotation angle of the aircraft in the image. The experimental results show that our algorithm has 86.94% AP50 and 34 fps on UCAS-AOD dataset, which has achieved competitive results.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.