Abstract
In ocean surveillance, ship targets are the focus of attention. The ship target segmentation of SAR images is still challenging due to not only speckle noise but also the variations of backscattering intensities. A new segmentation method for ship targets is proposed in this paper, based on the nonlocal processing principle. The level set is implemented by using nonlocal comparison of patches. In the procedure of pairwise interaction, only the local homogeneity of image features is utilized, and this is important in optimizing regions with homogeneous features. In order to make the method applicable for SAR images, a distribution metric is incorporated into the energy function to suppress the multiplicative noise. Experimental results based on TerraSAR data illustrate the effective performance of the proposed method on the ship target segmentation: It can overcome the speckle noise and intensity variations.
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 callMore From: IOP Conference Series: Earth and Environmental Science
Disclaimer: 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.
