基于ORB算法和OECF模型的快速图像拼接研究  

Fast image stitching algorithm based on ORB algorithm and OECF model

作　　者：张莹[1,2] 闫璠 高赢[1] 涂勇涛[1] ZHANG Ying;YAN Fan;GAO Ying;TU Yongtao(College of Information Engineering, Xiangtan University, Xiangtan, Hunan 411105, China;Institute of Control Engineering, Xiangtan University, Xiangtan, Hunan 411105, China)

机构地区：[1]湘潭大学信息工程学院,湖南湘潭411105 [2]湘潭大学控制工程研究所,湖南湘潭411105

出　　处：《计算机工程与应用》2017年第1期183-189,共7页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61175075);湖南省教育厅重点项目(No.14A137)

摘　　要：为了增加移动机器人视觉导航中的成像范围,提出了一种基于ORB算法和OECF模型的图像拼接算法,获取的图像进行预处理后,先利用SIFT算法提取特征点,再用ORB算法获取特征点的二进制码串描述子进行匹配,而后通过投影变换模型获取参数,最后估计摄像机的光电转换函数OECF(Opto-Electronic Conversion Function),利用Laguerre OECF模型参数对拼接图像进行色彩调整,解决了多幅图像拼接中颜色不一致的问题。实验结果表明,该算法能有效地对图像进行拼接,配准速度和拼接视觉效果和优于其他算法。In order to expand the viewing angle for robot visual navigation, this paper presents a fast image stitchingalgorithm based on ORB algorithm and OECF model. Firstly, feature points are extracted by SIFT algorithm after imagespre-processing. Secondly, the binary descriptors of the feature points are obtained by ORB algorithm to achieve imagesmatches. The project transformation model matrix between two matching images is calculated. Finally, to solve the colorinconsistency problem of images stitching, the Opto-Electronic Conversion Function of the camera is estimated to conductcolor adjustment. Experimental results show that the proposed algorithm is effective for image stitching, moreover thestitching quality and stitching speed are much better than other image stitching algorithms.

关 键 词：ORB算法 OECF模型 图像拼接 色彩平衡 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]