Abstract
Limited by bandwidth, Beidou short message system has certain limitations in the application of image transmission. To improve the problem, this paper proposes a Beidou short message transmission method based on high-quality image compression and reconstruction. We introduce the current mainstream deep learning framework based on variational autoencoders as our baseline. In order to achieve high-quality image compression and reconstruction, firstly, the attention mechanism is added to make the network automatically pay attention to beneficial information. Secondly, the image quality discriminator is designed that can provide the image definition score explicitly and is differentiable. Furthermore, based on the discriminator, a two-stage training method is proposed: first, the discriminator is trained with the data set synthesized by the Gaussian Blur, then the weights of the discriminator are fixed and the output of the discriminator is used to guide the network to generate images with high quality. The effectiveness of the method is verified by a series of experiments.
Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
