一种适用于仿生复眼系统的多路图像拼接算法研究  

Research on a Multi-Channel Image Mosaic Algorithm for Bionic Compound Eye System

作　　者：陈起帆 聂亮[1] 于祖阳 刘嘉昕 CHEN Qi-fan;NIE Liang;YU Zu-yang;LIU Jia-xin(College of Information Science and Engineering,Xi'an Technological University,Xi'an 710021,China)

机构地区：[1]西安工业大学光电工程学院,陕西西安710021

出　　处：《光学与光电技术》2023年第2期43-50,共8页Optics & Optoelectronic Technology

基　　金：基础加强计划技术领域基金(2021-JCJQ-JJ-0727);陕西省教育厅重点科学计划研究(20jy029)资助项目。

摘　　要：仿生复眼系统解决了传统单孔径光学系统中视场与分辨率的矛盾关系,兼具了较大的视场和高分辨率。但随着视场和分辨率的增加,图像信息增多,随之带来了图像拼接中效率和质量问题。针对该问题,提出一种基于改进尺度不变特征转换(SIFT)算法和主成分分析(PCA)算法的仿生复眼多路图像拼接融合方法。该方法缩小了特征点提取区域,减少了多路图像特征点匹配次数,降低了图像特征点描述符的维度。再利用改进的自适应迭代随机抽样一致(RANSAC)算法对特征点进行提纯增加鲁棒性,最后通过加权平均算法来完成对多幅子图像的高质量融合。实验结果表明,该算法设计合理,且随着图像信息的复杂程度增加,相较传统算法的拼接效率不断提升,同时保证了较好的拼接质量,可有效拼接融合仿生复眼系统多路图像,对多路图像类系统拼接融合提供借鉴。The bionic compound eye system solves the contradiction between the field of view and resolution in the traditional singlc-apcrturc optical system,and has both large field of view and high resolution.However,with the increase of field of view and resolution,the image information increases,which brings the problem of efficiency and quality in image Mosaic.To solve this problem,a bionic compound eye multi-channel image Mosaic fusion method based on improved scale-invariant feature transformation(SIFT)algorithm and principal component analysis(PCA)algorithm is proposed.The method reduces the feature point extraction area,reduces the number of multiplexed image feature point matching,and decreases the dimensionality of image feature point descriptors.The improved adaptive iterative random sampling consistent(RANSAC)algorithm is used to purify the feature points to increase the robustness,and finally the high-quality fusion of multiple sub-images by the weighted average algorithm is completed.The experimental results show that the proposed algorithm is reasonable in design,and with the increase of the complexity of image information,the Mosaic efficiency is improved compared with the traditional algorithm,and at the same time,the Mosaic quality is better.It can effectively Mosaic and integrate the multi-channel images of the bionic compound eye system,and provides a reference for the mosaic and fusion of the multi-channel image system.

关 键 词：图像处理 仿生复眼系统 多图像迭代拼接 描述符降维 随机抽样一致性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]