Synthetic aperture radar image coloring method based on convolutional network

• Main Authors: YU WEIXUE, LI GUANQUN
• Format: Patent
• Language: Chinese; English
• Published: 30.12.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL; PHYSICS

The invention relates to the technical field of image processing, and discloses a convolutional network-based synthetic aperture radar image coloring method, which comprises the following steps of: acquiring an original synthetic aperture radar image, obtaining a refined image according to an image coloring calculation pool, and inputting the refined image into a synthetic aperture radar image coloring network to obtain a colored image. According to the method, deep multi-scale semantic feature information of a synthetic aperture radar image can be fully extracted through a dual-order three-branch convolution module assembly synthetic aperture radar image coloring generator network, so that corresponding color information is given to the synthetic aperture radar image according to surface feature information observed by the synthetic aperture radar image; and through confrontation training of joint of the discriminator network and the coloring network, the visual authenticity of the coloring result of the syn