Space-based remote sensing is an important way of detecting many types of land targets. For the purpose of taking cover, land targets have a strong demand for avoiding space-based remote sensing reconnaissance. In practice, space-based reconnaissance will produce huge data, which are unbearable for human-beings. Therefore, the data processing must rely on artificial intelligence technology such as deep neural network. Many previous works show that the existing intelligent target detection algorithm based on deep neural network will be affected by perturbations. Firstly, this paper establishes a target detection method based on the Faster RCNN framework, and then three types of disturbances methods are studied to help the mobile radar to counter the typical space-based artificial intelligence detection algorithm. The simulation results show that the three types of disturbances methods can fool the typical target detection technology based on deep neural network.
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.