基于MSCR与CS-LBP的鱼眼图像特征区域匹配方法  

Matching method of fish-eye image based on CS-LBP and MSCR regions

作　　者：万丽[1] 李晓芬[2] 冯为嘉[3] 龙帮强[4] 朱均超[1] WAN Li1;LI Xiaofen;FENG Weijia;LONG Bangqiang;ZHU Junchao(School of Electrical Engineering, Tianjin University of Technology, Tianjin 300384, China;Low Carbon Development, Tianjin International Engineering Consultants Corporation, Tianjin 300074, China;College of Computer and Information Engineering, Tianjin Normal University, Tianjin 300387, China;State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China)

机构地区：[1]天津理工大学自动化学院,天津300384 [2]天津国际工程咨询公司低碳发展部,天津300074 [3]天津师范大学计算机信息与工程学院,天津300387 [4]天津大学精密测试技术及仪器国家重点实验室,天津300072

出　　处：《计算机工程与应用》2017年第12期208-213,共6页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61172185);天津市高等学校科技发展基金(No.20100705);天津市应用基础与前沿技术研究计划项目(No.15JCQNJC01400);天津市科技特派员项目(No.15JCTPJC58300)

摘　　要：相比普通镜头,鱼眼镜头拥有更大的视场角,甚至可以直接获取半球域的图像信息,在立体视觉领域,应用鱼眼镜头来采集全景图像可减少镜头及图像采集模块数目,简化系统、提高运算速度、降低成本。但同时鱼眼镜头图像也存在一定程度的畸变,越靠近边缘畸变越严重。因此,在光轴正交或是角度更大的立体视觉系统中,进行相关图像的特征点匹配存在困难,直接影响立体视觉系统的应用效果。然而采用一种具有仿射不变性的图像匹配算法即可解决这个问题,首先提取原始图像的MSCR特征区域,其次引进CS-LBP算子对各个MSCR区域进行特征描述,应用特征权重的卡方距离比较法进行唯一匹配,最后进行椭圆拟合及连线标记使得匹配结果可视化。且通过实验验证了此方法的稳定一致性,可应用于大旋转角度的鱼眼图像的特征匹配。Compared with ordinary lens,fish-eye lens has larger field of view,and even direct access to the image informationof the hemisphere domain.In the field of stereoscopic vision,using fish-eye lens to get a panoramic image canreduce the number of lens and image acquisition modules,simplifying the system,increase speed,and reduce costs.Butimages taken with a fisheye lens will produce a certain amount of distortion,and the more closer to the edge of image themore larger to the distortion.Therefore,it is difficult to match the feature points of the image in the stereo vision systemwith the orthogonal or the angle of the optical axis,which directly affects the application effect of the stereo vision system.However,the problem can be solved by an image matching algorithm based on affine invariants.This paper firstextracts the characteristics of MSCR regions from the original image,and then introduces the CS-LBP operator to describethe characteristics of each MSCR regions and finds the only matching by the application of the chi square distance comparisonmethod,which based on feature weights.Finally,the ellipse fitting and connection mark makes the matchingresult visualization.The stability and consistency of this method can be verified by the experiments,so this method can beapplied to the matching of the fish-eye images with large rotation angle.

关 键 词：鱼眼图像 特征区域匹配 最大稳定色彩区域 中心对称局部二值模式 卡方距离 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]