Watershed-based hierarchical SAR image segmentation

• Published in: International journal of remote sensing Vol. 20; no. 17; pp. 3377 - 3390
• Main Authors: Li, Wei, Benie, Goze B., He, Dong-Chen, Wang, Shengrui, Ziou, Djemel, Hugh, Q., Gwyn, J.
• Format: Journal Article
• Language: English
• Published: Abingdon Taylor & Francis Group 01.01.1999; Taylor and Francis
• Subjects: Applied geophysics; Areal geology. Maps; Earth sciences; Earth, ocean, space; Exact sciences and technology; Geologic maps, cartography; Internal geophysics; Canada; Manitoba; Ontario; Western Canada; Eastern Canada; agriculture; algorithms; drainage basins; synthetic aperture radar; land use; morphology; Space remote sensing; segmentation; cartography; North America; landform evolution
• ISSN: 0143-1161; 1366-5901
• DOI: 10.1080/014311699211390

Watershed transformation is a powerful image segmentation tool recently developed in mathematical morphology. In order to segment images initially oversegmented by watershed transformation, two approaches are considered: one is the thresholding of the gradient image proposed by us which is capable of keeping more salient image contours; the other is the well known centroid linkage region growing algorithm which merges regions with certain statistical similarities. By choosing suitable thresholds in the two approaches, hierarchical image segmentation algorithms can be constructed. A Ratio of Averages (ROA) edge detector is proposed to replace the morphological edge detectors prior to watershed transformation when applied to Synthetic Aperture Radar (SAR) images. Applications to SAR agricultural image segmentation with these hierarchical segmentation algorithms are presented. It is demonstrated that the algorithms are efficient in the segmentation of the SARimages and appropriate for land use applications when the land cover is made up of individual plots.