摘要
现有的彩色形态学梯度算子没有考虑RGB分量间的相关性,容易引入新的彩色值从而改变原始图像的信息,导致图像细节特征的丢失。提出一种基于彩色形态学的无人机航拍影像边缘检测算法。利用RGB颜色空间矢量标准化欧氏距离和夹角余弦相似度,结合人类视觉感知,定义彩色矢量互相关性度量函数;以此函数为准则定义结构单元内彩色像素集合的上确界和下确界,构建彩色形态学的基本算子;将提出的彩色形态学操作进一步应用于无人机航拍影像;通过实验对比验证边缘检测的效果,说明该算法的实用性和有效性。
The existing color morphological gradient operators do not consider the correlation between RGB components,so it is easy to introduce new color values to change the information of the original image,resulting in the loss of image details.An edge detection algorithm for UAV aerial image based on color morphology is proposed.Using RGB color space vector to standardize euclidean distance and angle cosine similarity,combining with human visual perception,the cross-correlation measure function of color vectors is defined.Based on this function,the upper and lower bounds of the set of color pixels in the structural unit are defined,and the basic operators of color mophology are constructed.Furthermore,the proposed color morphology operation is applied to UAV aerial photography.Then,the effectiveness of edge detection is verified by experimental comparison,indicating its practicality and effectiveness.
作者
秦娜
苏金凤
Qin Na;Su Jinfeng(College of Computer Science and Engineering,Northwest Normal University,Lanzhou 730070,China;College of Mathematics and Statistics,Northwest Normal University,Lanzhou 730070,China)
出处
《信息技术与网络安全》
2019年第4期56-62,共7页
Information Technology and Network Security
基金
国家自然科学基金资助项目(61861040)
甘肃省重点研发计划-社会发展类项目(17YF1FA119)
兰州市科技计划项目(2018-4-35)
