A modified GAC model for extracting waterline from
remotely sensed imagery
Kun Ruan
a,b
, Yong Zha
a
, Zeming Zhou
b
and Pinglv Yang
b
a
Jiangsu Centre for Collaborative Innovation in Geographical Information Resource Development and
Application, Key Laboratory of Virtual Geographic Environment of Ministry of Education, College of
Geographic Science, Nanjing Normal University, Nanjing, China;
b
College of Meteorology and
Oceanography, P.L.A. University of Science and Technology, Nanjing, China
ABSTRACT
At present many methods are available for extracting waterline
automatically from remotely sensed imagery. They are commonly
limited by their inability to accurately detect waterline when the
land–sea interface is not so distinctive on the imagery. This study
aims to develop a new model of extraction in which both the
spectral features of water and the spatial feature of waterline itself
are incorporated into the level set framework. This model consists
of three terms. The first term, which is derived from the spectral
features, drives the curve evolution. The second term, curvature
flow, guarantees the smoothness of the curve in the process of
evolution. The third term, the boundary attraction force, attracts
the evolving curve to the genuine position. Experimental results
with Landsat Thematic Mapper (TM) data sets validate the effec-
tiveness of the proposed model. It can improve the accuracy of
extracted waterline and effectively prevent the omission of weak
boundaries from the detected results that are common in both
geodesic active contour (GAC) and distance-regularized level set
evolution (DRLSE) results.
ARTICLE HISTORY
Received 30 March 2015
Accepted 17 June 2016
1. Introduction
Waterline refers to the intersecting boundary between land and sea at a given moment.
It is very important to map waterline accurately. For instance, multi-temporal waterlines
can be used to demarcate the inter-tidal zone, study its topography, map shoreline,
detect reef and underwater islands, and even monitor shoals, such as analysis of
changes in shoal sedimentation (Chen 2012; Shen 2011). Waterline extraction forms an
important and fundamental step in mapping coastline and (reef) islands, monitoring
natural disasters, and studying the dynamic change and trend of shoreline evolution. As
an efficient means of data acquisition, remote sensing has the advantages of expansive
coverage, fast speed, all-inclusiveness, frequent coverage, dynamics, and cost-e ffective-
ness in its application to the coastal zone. It can be a potentially convenient and
CONTACT Y. Zha Yong Zha yzha@njnu.edu.cn Jiangsu Center for Collaborative Innovation in Geographical
Information Resource Development and Application, Key Laboratory of Virtual Geographic Environment of Ministry of
Education, College of Geographic Science, Nanjing Normal University, Nanjing 210097, China
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2016
VOL. 37, NO. 17, 3961–3973
http://dx.doi.org/10.1080/01431161.2016.1207263
© 2016 Informa UK Limited, trading as Taylor & Francis Group
Downloaded by [Nanjing Normal University], [Yong Zha] at 20:07 12 July 2016