Two coastline detection methods in Synthetic Aperture Radar imagery based on Level Set Algorithm

  • Authors:

  • Yue Ouyang;Jinsong Chong;Yirong Wu

  • Affiliations:

  • National Key Laboratory of Microwave Imaging Technology, Institute of Electronics, Chinese Academy of Sciences, Beijing, China,Graduate University of Chinese Academy of Sciences, Beijing, China;National Key Laboratory of Microwave Imaging Technology, Institute of Electronics, Chinese Academy of Sciences, Beijing, China;National Key Laboratory of Microwave Imaging Technology, Institute of Electronics, Chinese Academy of Sciences, Beijing, China

  • Venue:
  • International Journal of Remote Sensing - Pan Ocean Remote Sensing: Oceanic Manifestation of Global Changes
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

In Synthetic Aperture Radar (SAR) ocean applications, coastline detection is basic and crucial. After accurate shoreline information is obtained, monitoring, mapping and other applications can be continued. Level Set Algorithm (LSA) is one of the efficient tools of edge detection, which has been applied successfully to coastline detection in radar imagery. However, using LSA is a time-consuming process when applied to high resolution images. This paper provides two novel approaches based on LSA that can enhance the detection speed. In the first method, the moving manner is simplified when the contour is far from the real boundary of images. In the second method, reducing resolution enables the coarse boundary to be obtained by LSA in the low resolution image. Then, the contour detection is continued by LSA in high resolution images based on the coarse boundary. Experimental results using Radarsat images show the effectiveness of these two new methods and verify the improved velocity in contour detection compared with the original LSA.