一种八邻域图像边界追踪改进算法  

An Improving Image Boundary Tracking Algorithm Based on Eight Neighborhood

作　　者：胡晋山 康建荣 张琪 刘鹏程[2] 朱铭达 HU Jinshan;KANG Jianrong;ZHANG Qi;LIU Pengcheng;ZHU Mingda(School of Geography,Geomatics and Planning,Jiangsu Normal University,Xuzhou 221116,China;College of Urban and Environment Science,Huazhong Normal University,Wuhan 430079,China;Kewen College,Jiangsu Normal University,Xuzhou 221116,China)

机构地区：[1]江苏师范大学地理测绘与城乡规划学院,江苏徐州221116 [2]华中师范大学城市与环境科学学院,湖北武汉430079 [3]江苏师范大学科文学院,江苏徐州221116

出　　处：《测绘通报》2018年第12期21-25,共5页Bulletin of Surveying and Mapping

基　　金：国家自然科学基金(41671395; 51574132);江苏省高等学校大学生创新项目(201813988006Y)

摘　　要：针对传统的边界追踪算法主要用来提取环形封闭边界的局限性,提出了基于八邻域目标边界追踪改进算法,着重解决了图像追踪过程中边界重叠部位的内外边界标定与"孤岛"处理。应用本文算法与摩尔邻域边界追踪算法分别对MPEG7-CE图形库中的4幅图像进行边界提取测试,结果表明改进算法提取结果正确。最后将本文算法应用于北极冰雪图像海冰边界提取,试验结果表明改进的算法可以有效提取大范围具有复杂拓扑关系的图像边界。Aiming at the limitation of traditional boundary tracking algorithms which are mainly used to extract annular closed boundary,an improved boundary tracking algorithm based on eight neighborhood targets is proposed,which focuses on the internal and external boundary calibration and "solated island"processing in image tracking.The proposed algorithm and the Moore neighborhood boundary tracking algorithm are used to test the four images in the MPEGT-CE image library respectively.The results show that the improved algorithm is correct.Finally,the algorithm is applied to the sea ice extraction of the Arctic snow image.Experimental results show that the improved algorithm can effectively extract large range of image boundaries with complex topological relationships.

关 键 词：二值图像 八邻域 边界追踪 终止准则 拓扑关系 

分 类 号：P237[天文地球—摄影测量与遥感]