摘要
为提高无人机影像特征点的提取质量与拼接精度,建立高斯金字塔实现多尺度变化进行粗差剔除,利用卷积神经网络(Convolutional Neural Network,CNN)提取影像特征点并通过最邻近值匹配特征点完成影像拼接,最后通过拼接一组无人机影像从粗差剔除率、匹配准确率、匹配时间3个方面来验证影像质量。验证结果表明,匹配点粗差剔除率提升了33.08%,匹配精度提升了12.17%,整体匹配效率有所提升,效果良好。
In order to improve the extraction quality and stitching accuracy of UAV image feature points,this paper establishes a Gaussian pyramid to realize multi-scale change for gross error elimination,uses Convolution Neural Network(CNN)to extract image feature points,and completes image stitching by matching the feature points with the nearest values.Finally,a group of UAV images are stitched from gross error elimination rate,matching accuracy Match time to evaluate image quality.The verification results show that the gross error elimination rate of matching points is improved by 33.08%,the matching accuracy is improved by 12.17%,the matching efficiency is improved,and good results are obtained.
作者
石斌斌
闵曹文
SHI Binbin;MIN Caowen(Jiangxi V&T College of Communications,Nanchang Jiangxi 330000)
出处
《河南科技》
2021年第34期8-10,共3页
Henan Science and Technology
关键词
多尺度
卷积神经网络(CNN)
影像匹配拼接
匹配精度
multiscale
Convolutional Neural Network(CNN)
image matching and splicing
matching accuracy
作者简介
石斌斌(1991-),男,硕士,研究方向:摄影测量与3S技术;闵曹文(1991-),男,硕士,助教,研究方向:3S技术应用。
