Fast Multiscale Superpixel Segmentation for SAR Imagery | IEEE Journals & Magazine | IEEE Xplore

Fast Multiscale Superpixel Segmentation for SAR Imagery


Abstract:

Superpixel segmentation is essential to the rapid information extraction from synthetic aperture radar (SAR) imagery. In this letter, we propose a fast multiscale superpi...Show More

Abstract:

Superpixel segmentation is essential to the rapid information extraction from synthetic aperture radar (SAR) imagery. In this letter, we propose a fast multiscale superpixel segmentation method based on the minimum spanning tree (MST), which can generate all scales of superpixels accurately in real time. Therefore, our method has the ability to segment SAR imagery with different scales efficiently and is meaningful for applications that require different levels of SAR image details. Experimental results on two real SAR images demonstrate that our proposed superpixel segmentation method can capture the image information of different levels, resulting in better hierarchical segmentation performance in comparison with other state-of-the-art methods.
Published in: IEEE Geoscience and Remote Sensing Letters ( Volume: 19)
Article Sequence Number: 4001805
Date of Publication: 29 September 2020

ISSN Information:

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.