River channel segmentation in polarimetric SAR images: Watershed transform combined with average contrast maximisation
作者：
Highlights：
• A new approach to river channel segmentation from polarimetric SAR images.
• It combines the watershed segmentation with average contrast maximisation.
• The over-segmentation is reduced using gradient reconstruction.
• The average segmentation time for an image of 1383 × 821 pixels amounts to 1.73 s.
• The average overlap value index amounts to 90% in the experiments completed.
摘要
•A new approach to river channel segmentation from polarimetric SAR images.•It combines the watershed segmentation with average contrast maximisation.•The over-segmentation is reduced using gradient reconstruction.•The average segmentation time for an image of 1383 × 821 pixels amounts to 1.73 s.•The average overlap value index amounts to 90% in the experiments completed.
论文关键词：Synthetic Aperture Radar (SAR),Polarimetric synthetic aperture radar,River channel segmentation,Watershed segmentation,Over–segmentation reduction,Morphological image processing
论文评审过程：Received 1 August 2016, Revised 6 April 2017, Accepted 7 April 2017, Available online 8 April 2017, Version of Record 19 April 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.04.018
