基于轮廓特征点的高精度识别目标方法  

An Approach of Recognition in High Precision Based on the Contour Feature Points

作　　者：刘永禄[1] 邵龙潭[2] 

机构地区：[1]海军大连舰艇学院,辽宁大连116018 [2]大连理工大学,辽宁大连116023

出　　处：《电脑与信息技术》2009年第3期1-5,66,共6页Computer and Information Technology

基　　金：国家自然科学基金项目(50527803)

摘　　要：为了实现高成功率、高精度和快速识别跟踪目标,提出对基于轮廓特征点的目标精确识别方法。在识别过程中采用了轮廓提取和多边形拟合算法自动搜寻到图像中要识别和跟踪的目标,同时对目标物轮廓的多边形角点进行亚像素分辨率的定位,从而可以利用目标轮廓角点的精确定位来实现对多边形目标的识别与跟踪。试验结果以及特征点亚像素算法分辨率的分析表明,采用这种自动识别与跟踪目标的方法,其精度可以达到0.02像素。In order to achieve a high success rate, high precision and fast track the identification of objectives, accurate identification method is put forward. In the process of identification, the extraction and the outline of the polygon fitting algorithm are used to automatically search for images to identify and track targets. The comers of the polygon target are positioned in sub-pixel resolution of the position. The polygons can be replaced with these comers which describe the goals in high precision. The experiment result shows that the identification and tracking method is robust and resolution can be reached 0.02 pixels.

关 键 词：轮廓 多边形拟合 目标跟踪 亚像素 目标识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]