Abstract
The superpixel segmentation algorithm, as a preprocessing technique, should show good performance in fast segmentation speed, accurate boundary adherence and homogeneous regularity. A fast superpixel segmentation algorithm by iterative edge refinement (IER) works well on optical images. However, it may generate poor superpixels for Polarimetric synthetic aperture radar (PolSAR) images due to the influence of strong speckle noise and many small-sized or slim regions. To solve these problems, we utilized a fast revised Wishart distance instead of Euclidean distance in the local relabeling of unstable pixels, and initialized unstable pixels as all the pixels substituted for the initial grid edge pixels in the initialization step. Then, postprocessing with the dissimilarity measure is employed to remove the generated small isolated regions as well as to preserve strong point targets. Finally, the superiority of the proposed algorithm is validated with extensive experiments on four simulated and two real-world PolSAR images from Experimental Synthetic Aperture Radar (ESAR) and Airborne Synthetic Aperture Radar (AirSAR) data sets, which demonstrate that the proposed method shows better performance with respect to several commonly used evaluation measures, even with about nine times higher computational efficiency, as well as fine boundary adherence and strong point targets preservation, compared with three state-of-the-art methods.
Highlights
Polarimetric synthetic aperture radar (PolSAR) is popular and attractive due to its advantage of providing richer information with four channels HH, HV, VH and VV, where HH, HV, VH and VV denote the polarization models for horizontal transmit and horizontal receive (HH), horizontal transmit and vertical receive (HV), vertical transmit and horizontal receive (VH), and vertical transmit and vertical receive (VV), respectively
That is because our method of initialization is proposed for those images with small-sized or slim regions which are common in real-world PolSAR images
This is mainly because when the size of the image is small, the initial unstable pixels to be relabeled in our method are of a small number, but with the large size of images to process, more pixels need to be relabeled by Pol-iterative edge refinement (IER) in the first few iterations
Summary
Polarimetric synthetic aperture radar (PolSAR) is popular and attractive due to its advantage of providing richer information with four channels HH, HV, VH and VV, where HH, HV, VH and VV denote the polarization models for horizontal transmit and horizontal receive (HH), horizontal transmit and vertical receive (HV), vertical transmit and horizontal receive (VH), and vertical transmit and vertical receive (VV), respectively. Many researches have been developed on PolSAR images. PolSAR image classification [1,2,3,4,5] is a basic issue. There are basically two approaches for classification: (1) pixel-based classification; (2) region-based classification. Due to the presence of inherent speckle noise in PolSAR images, traditional pixel-based classification algorithms have some drawbacks [6], i.e., sensitivity to noise and more computation. Compared to the traditional pixel-based methods, region-based algorithms process images at region level instead of pixel level, making the information of regions more available with better anti-noise performance. Additional region generation methods are generally required beforehand, e.g., superpixel algorithms
Sign-in/Register to view highlights & summary 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 callDisclaimer: 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.
