基于粒子滤波算法的物体轮廓提取  

Object contour extraction by particle filtering

作　　者：叶发茂[1] 苏林[1] 李树楷[1] 

机构地区：[1]中国科学院遥感应用研究所,北京100101

出　　处：《辽宁工程技术大学学报（自然科学版）》2005年第z2期66-69,共4页Journal of Liaoning Technical University (Natural Science)

基　　金：国家自然科学基金(40201035)

摘　　要：为了解决物体轮廓提取工作中,由于图像的复杂性和多义性无法依靠计算机来自动完成,而手工提取又存在速度慢、精度低、工作量大等缺点的问题,提出了一种基于粒子滤波算法的物体轮廓的提取算法,该方法可以整合各种先验信息到模型中去提高提取精度。实验证明该方法通过很少的人工交互就可以很好的提取复杂物体的轮廓。该方法为提取物体轮廓线提供了较好的解决对策。Contour extraction plays an important role in the field of image processing,and it is difficult to automatically extract object contour due to the complexity of image.However,manual approach is laborious, tedious and complex task.To speed the extraction of contour,a new algorithm for extraction of object contour based on particle filtering is proposed and how to design the components of the algorithm is introduced.The measures to deal with sharp tips and small noise are presented.The results of test show that the algorithm can locate the target object contour of sharp tips accurately by a few user interactions and the algorithm can be a good solution for extraction contour。

关 键 词：轮廓提取 粒子滤波 重要性采样 

分 类 号：P237[天文地球—摄影测量与遥感]