改进的变长夹角链码算法及在码头识别中的应用

发布时间：2018-03-14 07:49

本文选题：夹角链码　切入点：变长夹角链码　出处：《国土资源遥感》2016年04期 　论文类型：期刊论文

【摘要】：针对变长夹角链码对曲线近似时的角度信息损失问题,提出了一种变长夹角链码的改进方法,并将该方法应用于码头目标的特征提取。该方法改变了变长夹角链码算法在折线终点选取时的规则,在继承变长夹角链码优点的基础上,保留了曲线曲率较大的拐角,略去了曲线的较小波动,使有较小波动的曲线近似为直线。改进后的方法使折线能更好地逼近曲线,应用折线逼近并表示曲线,有利于提取曲线的角度特征和线特征。应用该方法提取图像特征,用于码头目标的检测,针对水陆分割后的海岸线使用改进的夹角链码提取海岸线的几何特征。实验表明,该方法能够有效地提取码头的直角、平行线特征,再依据码头先验知识,标记出码头区域。
[Abstract]:An improved method of variable length angle chain code is proposed to solve the problem of loss of angle information when variable length angle chain code is approximate to curve. The method is applied to the feature extraction of the wharf target. The method changes the rules of the variable length angle chain code algorithm in the selection of the end point of the broken line, and retains the corner with large curve curvature on the basis of inheriting the advantages of the variable length angle chain code. The smaller fluctuation of the curve is omitted and the curve with the smaller wave is approximated to a straight line. The improved method enables the broken line to approach the curve better, and the curve is approximated and represented by the broken line. The method is used to extract the image features for the detection of the wharf targets, and the improved angle chain code is used to extract the geometric features of the coastline after the coastline is segmented. The experimental results show that the proposed method can be used to extract the geometric features of the coastline. This method can effectively extract the characteristics of the right angle and parallel line of the wharf, and then mark the wharf area according to the prior knowledge of the wharf.
【作者单位】：北方工业大学计算机学院;广东省普及型高性能计算机重点实验室深圳市服务计算与应用重点实验室;北方工业大学电子信息工程学院;
【基金】：国家自然科学基金项目“多源遥感图像识别关键技术研究”(编号:61371143) 北京市自然科学基金项目“物联网接入端信息采集与可靠高速传输关键技术研究”(编号:4132026) 广东省普及型高性能计算机重点实验/深圳市服务计算与应用重点实验室开放课题“遥感图像特征提取和挖掘方法研究”(编号:SZU-GDPHPCL2014) 北京市教委项目“面向虚实融合的多源图像配准与识别科研平台”(编号:PXM2015_014212_000024);北京市教委“多源遥感图像配准与识别科研平台”项目(编号:XN081)共同资助
【分类号】：TP391.41

【相似文献】