摘要
经典LSD直线提取算法仅采用图像的灰度信息,未充分考虑R,G,B彩色通道中的梯度差异,导致部分重要直线检测率低且连续性较差的问题,文中提出基于多通道梯度特征的彩色图像直线提取方法。首先计算彩色图像的R,G,B通道的梯度值及其对应的灰度图像的梯度值,然后取梯度的最大值及其对应的梯度方向作为初始梯度值,最后通过区域生长和直线拟合完成直线检测。采用多幅York城市图像数据库中的图像和真实影像进行实验,结果表明文中方法在彩色图像中的直线提取效果优于经典LSD直线提取算法,提取结果中直线信息更丰富,连续性更好。
Aiming at the problem that the classic LSD line extraction algorithm only uses the gray information of the image,and does not fully consider the gradient difference in the RGB color channel,leading to the low detection rate and poor continuity of some important lines,a method of color image line extraction based on multi-channel gradient features is proposed.First it calculates the gradient values of the R,G,and B channels of the color image and the corresponding gradient values of the grayscale image,and then takes the maximum value of the gradient and its corresponding gradient direction as the initial gradient value,and finally completes straight line detection through area growth and straight line fitting.Experiments are carried out using multiple images from the York city image database and real images.The result shows the method in this paper is better than the classic LSD line extraction algorithm in the line extraction effect of the color image,and the line information in the extraction results is more abundant and the continuity is better.
作者
徐辛超
李涵坤
XU Xinchao;LI Hankun(College of Surveying and Geography Science,Laoning Technical Universitty,Fuxin 123000,China)
出处
《测绘工程》
CSCD
2022年第3期40-45,共6页
Engineering of Surveying and Mapping
基金
辽宁省教育厅基础研究资助项目(LJ2019JL021)
辽宁省自然科学基金资助项目(20180550849)
国家自然科学基金资助项目(42071447,41401535)。
关键词
直线提取
彩色图像
多通道
梯度最大值
straight line extraction
color image
multi-channel
maximum gradient
