Abstract
The symmetrical difference kernel SAR image edge detection algorithm based on the Canny operator can usually achieve effective edge detection of a single view image. When detecting a multi-view SAR image edge, it has the disadvantage of a low detection accuracy. An edge detection algorithm for a symmetric difference nuclear SAR image based on the GAN network model is proposed. Multi-view data of a symmetric difference nuclear SAR image are generated by the GAN network model. According to the results of multi-view data generation, an edge detection model for an arbitrary direction symmetric difference nuclear SAR image is constructed. A non-edge is eliminated by edge post-processing. The Hough transform is used to calculate the edge direction to realize the accurate detection of the edge of the SAR image. The experimental results show that the average classification accuracy of the proposed algorithm is 93.8%, 96.85% of the detection edges coincide with the correct edges, and 97.08% of the detection edges fall into the buffer of three pixel widths, whichshows that the proposed algorithm has a high accuracy of edge detection for kernel SAR images.
Highlights
The generative adversarial network (GAN) is a generative model proposed by Goodfellow in 2014.GAN is structurally inspired by the two-person zero-sum game in game theory
The goal of training is to make the distribution of G(z) as close as possible to the distribution training set, such as Gurumurthy and other improved GAN network models employed to enhance of real data
A symmetric difference kernel SAR image edge detection algorithm based on the GAN network model is proposed
Summary
The generative adversarial network (GAN) is a generative model proposed by Goodfellow in 2014. Due to the serious interference of speckle noise and other objects in the imaging process of symmetrical difference nuclear SAR images, the detection results under a single window cannot meet the actual needs of a high integrity and low false detection rate at the same time [7,8,9]. In order to overcome the sensitivity and limited directionality of noise in symmetrical differential nuclear synthetic aperture radar images, an edge detection algorithm based on the GAN network model is proposed in this paper. The experimental results show that the algorithm is not sensitive to strong speckle noise, and can get a better edge location with low detection error This method has a certain contribution to the accurate understanding of SAR images.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
