Abstract
Although various methods can effectively segment synthetic aperture radar (SAR) images, we found that the method combining superpixel and image edge information can get better results. To solve the problem that common SAR image segmentation methods often segment pixels incorrectly in edge region, a superpixel boundary-based edge description algorithm (SpBED) is proposed. First, an edge detection method with three edge detectors is used. Therefore, accurate strong edges of SAR images can be extracted, and false edges that are easy to appear in a single detection method can be effectively eliminated. Then the weak edges of the image are extracted by superpixel generation algorithm. The extracted weak edges can supplement the edge information that is difficult to extract by edge detection. Superpixel boundaries are also used to carry the strong edges, so that the strong and weak edges can be completely represented by superpixel boundaries. Finally, boundary constraint superpixel smoothing is used to reduce the effects of noise, and k-means algorithm is performed on superpixels. Since edge information is carried by superpixels, it effectively guarantees the segmentation accuracy in edge region. Compared with seven state-of-the-art algorithms, segmentation results on simulated images and real images demonstrate the effectiveness of the proposed SpBED.
Highlights
I N RECENT decades, synthetic aperture radar (SAR) has played an important role in terrain classification, crop monitoring, disaster detection, and other fields [1]
It can be seen that the accuracy and kappa coefficient of the proposed algorithm are the highest, which proves the effectiveness of the proposed algorithm
The accuracy of ILKFCM, NSFCM, and FKPFCM algorithms has decreased, they are relatively stable under different noises
Summary
I N RECENT decades, synthetic aperture radar (SAR) has played an important role in terrain classification, crop monitoring, disaster detection, and other fields [1]. SHANG et al.: SUPERPIXEL BOUNDARY-BASED EDGE DESCRIPTION ALGORITHM FOR SAR IMAGE SEGMENTATION a lot of computing time. Some other methods used immune cloning to find the optimal clustering center to achieve a better SAR image segmentation effect [26]. Various methods can effectively segment SAR images, we found that the method of combining superpixel and image edge information can get better results. In order to realize the above scheme of improving efficiency and segmentation accuracy, this article proposes a superpixel boundary-based edge description algorithm (SpBED) for SAR image segmentation. Because different edge detection methods have different response characteristics, the problem of edge extraction error which is easy to occur in a single method can be avoided It helps to preserve the edges of the image and makes the boundaries of the segmentation results clearer.
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
