Man-made target detection in the natural background is the core problem of high-resolution optical remote sensing image interpretation, and it is an important application direction in the target recognition, situation awareness, and other fields. This paper proposes a man-made target detection method based on red-edge spectral information in the natural background. In this method, the red-edge spectrum information of vegetation is used to suppress background interference and narrow the search area in large remote sensing images, to improve the probability of target detection. The automatic extraction model of man-made targets is trained by the public dataset COD10K and self-constructed remote sensing dataset, and detection experiments are carried out by using the multispectral images from the WorldView-3 satellite and the Sentinel-2 A/B satellites. The experimental results show that the proposed algorithm has high detection accuracy and fast detection speed for the green runway, green buildings, and another man-made targets in the forest or grassland. Compared with the traditional man-made target detection algorithm, this method is more suitable for the rapid search of large area remote sensing images.
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.