基于卷积神经网络的卫星遥感图像拼接  

Satellite Remote Sensing Image Mosaic Based on Convolutional Neural Network

作　　者：刘通 胡亮 王永军 初剑峰[1] LIU Tong;HU Liang;WANG Yongjun;CHU Jianfeng(College of Computer Science and Technology,Jilin University,Changchun 130012,China;Network Security Detachment of Changchun Public Security Bureau,Changchun 130051,China)

机构地区：[1]吉林大学计算机科学与技术学院,长春130012 [2]长春市公安局网安支队,长春130051

出　　处：《吉林大学学报（理学版）》2022年第1期99-108,共10页Journal of Jilin University:Science Edition

基　　金：吉林省发改委双十项目(批准号:2019FGWTZC001);吉林省省校共建示范基金(批准号:SXGJSF2017-4).

摘　　要：针对传统算法不适用于外观发生较大变化的图像拼接问题,提出一种基于卷积神经网络的遥感图像拼接方法,通过深度学习使模型实现对遥感图像的配准和拼接.通过两次实验将该算法与传统算法进行对比.首先,以欧氏距离作为评价指标,分别通过两种算法在不同图像数据集上进行统计,对它们的图像配准能力进行评估.其次,在真实的遥感图像拼接应用场景下对比两种算法实现的遥感图像拼接效果.实验结果表明,卷积神经网络模型对外观发生较大形变的图像具有更好的配准能力,因此对于外观产生较大变化的遥感图像,可采用该算法代替传统算法实现图像拼接,得到更精确的全景图像.Aiming at the problem that traditional algorithms were not suitable for image mosaic with large changes in appearance,we proposed a remote sensing image mosaic method based on convolutional neural network,which enabled the model to realize the registration and mosaic of remote sensing images through deep learning.The algorithm was compared with the traditional algorithms through two experiments.Firstly,the Euclidean distance was used as the evaluation indicator,and statistics of two methods were performed on different remote sensing image data sets to evaluate their image registration abilities.Secondly,effects of remote sensing image mosaic realized by two algorithms in the real remote sensing image mosaic application scene were compared.The experimental results show that the convolutional neural network model has a better registration ability for images with large external deformations.Therefore,for the remote sensing images with large changes in appearance,the proposed algorithm can be used to replace the traditional algorithm to realize image mosaic and obtain a more accurate panoramic image.

关 键 词：卫星遥感 卷积神经网络 图像拼接 尺度不变特征转换 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]