A Novel Method for Waterline Extraction from Remote Sensing Image Based on Quad-Tree and Multiple Active Contour Model

摘要

After the characteristics of geodesic active contour model (GAC), Chan-Vese model (CV) andlocal binary fitting model (LBF) are analyzed, and the active contour model based on regionsand edges is combined with image segmentation method based on quad-tree, a waterlineextraction method based on quad-tree and multiple active contour model is proposed in thispaper. Firstly , the method provides an initial contour according to quad-tree segmentation;secondly, a new signed pressure force (SPF) function based on global image statisticsinformation of CV model and local image statistics information of LBF model has been defined,and then, the edge stopping function(ESF) is replaced by the proposed SPF function, whichsolves the problem such as evolution stopped in advance and excessive evolution; finally, theSelective Binary and Gaussian Filtering Level Set method is used to avoid reinitializing andregularization to improve the evolution efficiency. The experimental results show that thismethod can effectively extract the weak edges and serious concave edges, and owns someproperties such as sub-pixel accuracy, high efficiency and reliability for waterline extraction.