文献类型：会议论文

英文题名：A coastline detection method based on level set

作者：Wang, Qian[1]; Lu, Ke[1]; Duan, Fuqing[2]; He, Ning[3]; Yang, Lei[4]

第一作者：Wang, Qian

机构：[1] College of Engineering and Information Technology, Graduate University, Chinese Academy of Sciences, Beijing, 100049, China; [2] College of Information Science and Technology, Beijing Normal University, Beijing, 100875, China; [3] School of Information, Beijing Union University, Beijing 100101, China; [4] National Satellite Meteorological Center, Beijing 100081, China

第一机构：College of Engineering and Information Technology, Graduate University, Chinese Academy of Sciences, Beijing, 100049, China

会议论文集：Human-Computer Interaction: Towards Intelligent and Implicit Interaction - 15th International Conference, HCI International 2013, Proceedings

会议日期：July 21, 2013 - July 26, 2013

会议地点：Las Vegas, NV, United states

语种：英文

外文关键词：Edge detection - Human computer interaction - Image segmentation - Infrared imaging - Landforms

摘要：This paper proposes a level set based coastline detection method by using the template initialization and local energy minimization. It can complete the sea-land boundary detection in infrared channel image. This method is an improvement on the traditional level set algorithm by using the information of GSHHS to optimize the initialization procedure, which can reduce the number of iterations and numerical errors. Moreover, this method optimizes regional energy functional, and can achieve the rapid coastline detection. Experiments on the IR image of FY-2 satellite show that the method has fast speed and high accuracy. ? 2013 Springer-Verlag.