Fast SAR Image Segmentation via Merging Cost With Relative Common Boundary Length Penalty

• Published in: IEEE transactions on geoscience and remote sensing Vol. 52; no. 10; pp. 6434 - 6448
• Main Authors: Shui, Peng-Lang, Zhang, Ze-Jun
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.10.2014; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Assessments; Boundaries; Detectors; False alarms; Image edge detection; Image segmentation; Merging; Merging cost with relative common boundary length penalty (RCBLP); nearest neighbor graph (NNG); Partitions; ratio edge strength map (RESM); region merging; Segmentation; Speckle; Synthetic aperture radar; synthetic aperture radar (SAR) image segmentation; Transforms; watershed transform; region merging; ratio edge strength map (RESM); synthetic aperture radar (SAR) image segmentation; Merging cost with relative common boundary length penalty (RCBLP); watershed transform; nearest neighbor graph (NNG)
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2013.2296561

In this paper, a region-merging-based method is proposed for fast segmentation of amplitude-format synthetic aperture radar (SAR) images. It combines the existing fast initial partition by applying the watershed transform to the thresholded ratio edge strength map with fast region merging by using a new merging cost with relative common boundary length penalty (RCBLP) and the nearest neighbor graph (NNG) for fast search minimal edge on a region adjacency graph (RAG). A new statistical similarity measure, which is a scale-invariant and approximately constant false alarm rate with respect to region sizes, is proposed and combined with an RCBLP term to form a new merging cost. The region-merging process starting from the initial partition is fast implemented by means of the RAG and NNG. Several quantitative indexes in optical image segmentation assessment are borrowed for quantitative assessment of segmentation quality. Experiments to synthetic and real SAR images are reported. The results show that the proposed method is fast and attains higher quality segmentation results than the two recent state-of-the-art methods.