Aiming at the feature that the cloud detection algorithm using cloud area features can take parallel computing at many places, combined with the advantage of pipeline parallel processing of FPGA processing data, this paper proposes a method for achieving high-speed real-time cloud detection based on FPGA development on the remote sensing camera side. And it designs logical architecture for the parallel computing and extraction of multiple cloud area features in the cloud detection algorithm. In addition, a method for solving the difference and comparison probability of image entropy is developed, which can achieve the rapid and accurate detection of cloud layers in remote sensing images. The hardware test results show that the proposed method can realize cloud detection processing on remote sensing images with an input resolution of 512*512 on the Xilinx z7020clg400 series FPGA platform, at the 12th pixel clock cycle after image transmission (the pixel clock is: 65MHz) to obtain the discrimination result and the accuracy of cloud area discrimination for the Landsat8 remote sensing atlas can reach 85.38%. Besides, the processing efficiency is greatly improved, which can meet the real-time cloud discrimination requirements of the spaceborne platform.
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.