Edge Detection Algorithm of a Symmetric Difference Kernel SAR Image Based on the GAN Network Model
Open Access
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.Keywords
Funding Information
- Liaoning Provincial Department of Education Key Laboratory Basic Research Project (LJZS001)
- National Natural Science Foundation of China (41274048)
- Major projects in Guangdong Province (2016B090904001)
- Development of surveillance video augmentation system under smog environment (201604010051)
- Automotive Electronics Surge Protection Semiconductor TVS Product Development and Industrialization (2016B090903001)
- Development and industrialization of professional chips for HD network cameras (2016B090918126)
- Tianshan Innovation Team Project (Y744261)
This publication has 26 references indexed in Scilit:
- Unsupervised change detection in SAR images based on frequency difference and a modified fuzzy c-means clusteringInternational Journal of Remote Sensing, 2018
- A novel approach based on structural information for change detection in SAR imagesInternational Journal of Remote Sensing, 2018
- Novel class-relativity non-local means with principal component analysis for multitemporal SAR image change detectionInternational Journal of Remote Sensing, 2017
- Change detection in SAR images based on the logarithmic transformation and total variation denoising methodRemote Sensing Letters, 2016
- Lunar surface crater topology generation using adaptive edge detection algorithmIET Image Processing, 2016
- Unsupervised change detection in SAR images using curvelet and L1-norm based soft segmentationInternational Journal of Remote Sensing, 2016
- An Optimal Fuzzy System for Edge Detection in Color Images Using Bacterial Foraging AlgorithmIEEE Transactions on Fuzzy Systems, 2016
- Evaluation of different SAR change detectors based on vehicle recognition with MSTAR data setRemote Sensing Letters, 2015
- Multi-model radiometric slope correction of SAR images of complex terrain using a two-stage semi-empirical approachRemote Sensing of Environment, 2015
- The use of the frequency-dependent finite-difference time-domain method for induced current and SAR calculations for a heterogeneous model of the human bodyIEEE Transactions on Electromagnetic Compatibility, 1994