Automated extraction of coastline from satellite imagery by integrating Canny edge detection and locally adaptive thresholding methods

Abstract

This paper presents a comprehensive approach to effectively and accurately extract coastlines from satellite imagery. It consists of a sequence of image processing algorithms, in which the key component is image segmentation based on a locally adaptive thresholding technique. Several technical innovations have been made to improve the accuracy and efficiency for determining the land/water boundaries. The use of the Levenberg-Marquardt method and the Canny edge detector speeds up the convergence of iterative Gaussian curve fitting process and improves the accuracy of the bimodal Gaussian parameters. The result is increased reliability of local thresholds for image segmentation. A series of further image processing steps are applied to the segmented images. Particularly, grouping and labelling contiguous image regions into individual image objects enables us to utilize heuristic human knowledge about the size and continuity of the land and ocean masses to discriminate the true coastline from other object boundaries. The final product of our processing chain is a vector-based line coverage of the coastline, which can be readily incorporated into a GIS database. Our method has been applied to both radar and optical satellite images, and the positional precision of the resulting coastline is measured at the pixel level.

Acknowledgments

This work was supported under a National Aeronautics and Space Administration (NASA) grant NAG5-10112 and the National Science Foundation (NSF) grant No. 0126149. SAR data were processed and provided by the Radarsat: Antarctic Mapping Project of the Byrd Polar Research Center. The Landsat image was purchased using a research enhancement grant from the College of Geosciences, Texas A&M University. The authors wish to thank Hong-Gyoo Sohn for helpful discussions on the local dynamic thresholding algorithm.