相位相关性增强的自适应低重叠率多光谱图像快速拼接算法  

Adaptive low overlap multispectral image fast mosaic algorithm based on phase correlation enhancement

作　　者：贾停停 王慧琴[1] 王可[1] 王展 甄刚 李源 JIA Ting-ting;WANG Hui-qin;WANG Ke;WANG Zhan;ZHEN Gang;LI Yuan(College of Information and Control Engineering,Xi’an University of Architecture and Technology,Xi’an 710055,China;Shanxi Provincial Institute of Cultural Relics Protection,Xi’an 710075,China;Xi’an Museum,Xi’an 710054,China)

机构地区：[1]西安建筑科技大学信息与控制工程学院,陕西西安710055 [2]陕西省文物保护研究院,陕西西安710075 [3]西安博物院,陕西西安710054

出　　处：《液晶与显示》2022年第4期483-493,共11页Chinese Journal of Liquid Crystals and Displays

基　　金：陕西省自然科学基础研究计划(No.2021JM-377);陕西省科技厅科技合作项目(No.2020KW-012);陕西省教育厅智库项目(No.18JT006);西安市科技局高校人才服务企业项目(No.GXYD10.1)。

摘　　要：在进行多光谱图像拼接时,由于成像需求及不同波段图像的信息差异,导致无法在低重叠率条件下完成全波段光谱图像快速拼接。针对该问题,本文提出一种相位相关性增强的自适应低重叠率多光谱图像快速拼接算法。以多光谱图像信息熵最大通道作为基准通道,设计图像相关性增强切分方法,切除基准通道下两幅相邻镜头光谱图像的特定步长,提高待匹配光谱图像重叠率;引入最小二乘法动态调整切分次数及切分步长,实现相对偏移量寻优的同时提高算法的自适应性和精确度;利用不同通道下两幅相邻分镜头图像偏移量一致原则,通过基准通道位移量定位映射,解决个别通道因信息量不足无法拼接问题的同时提高多光谱图像的拼接效率。实验表明,该方法可实现重叠率不低于5%的16个通道光谱图像的快速拼接,在整体拼接质量和时间成本上均优于Harris、SIFT、FAST-SURF、BRISK-ORB四种算法,具有一定的实用价值。In multispectral image mosaic,due to the imaging requirements and the information differences of different band images,it is impossible to complete the fast mosaic of full band spectral images under the condition of low overlap rate.To solve this problem,an adaptive low overlap multispectral image fast mosaic algorithm based on phase correlation enhancement is proposed in this paper.Taking the maximum information entropy channel of spectral image as the reference channel,an image correlation enhancement segmentation method is designed to cut off the specific step of two adjacent lens spectral images under the reference channel to improve the overlap rate of spectral images to be matched.The least square method is introduced to dynamically adjust the number of divisions and the division step length to realize the optimization of the relative offset while improving the realization and rationality of the algorithm.Using the principle of consistent offset of two adjacent sub lens images under different channels,through the positioning mapping of the displacement of the reference channel,the problem that individual channels cannot be spliced due to insufficient information is solved,and the splicing efficiency of multispectral images is improved.Experiments show that this method can realize the fast mosaic of 16 channel spectral images with an overlap rate of no less than 5%,which is superior to Harris,SURF and ORB algorithms in overall mosaic quality and time cost.

关 键 词：相位相关法 多光谱图像拼接 低重叠率 相关性增强 最小二乘法 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置] TP391.41[自动化与计算机技术—控制科学与工程]