检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:付璐 樊彦国[1] 李国胜[1] 禹定峰 柴江龙 Fu Lu;Fan Yanguo;Li Guosheng;Yu Dingfeng;Chai Jianglong(College of Oceanography and Space Informatics,China University of Petroleum,Qingdao,Shandong 266580,China;Institute of Oceanographic Instrumentation,Qilu University of Technology,Shandong Academy of Sciences,Qingdao,Shandong 266061,China;Hisense,Qingdao,Shandong 266071,China)
机构地区:[1]中国石油大学(华东)海洋与空间信息学院,山东青岛266580 [2]齐鲁工业大学(山东省科学院)山东省科学院海洋仪器仪表研究所,山东青岛266061 [3]海信集团,山东青岛266071
出 处:《激光与光电子学进展》2021年第12期105-113,共9页Laser & Optoelectronics Progress
基 金:山东省重点研发计划(2019GHY112017)。
摘 要:为了解决网格运动统计(GMS)算法在图像发生旋转时特征匹配时间过长的问题,提出一种改进的快速GMS图像匹配算法。首先采用快速特征点提取和描述算法对图像进行暴力匹配以得到初始匹配点对,根据汉明距离选取其中匹配质量较高的特征匹配对。然后通过计算匹配对特征点主方向的差值得到两个图像的近似旋转角度,根据旋转角度直接确定运动核的最佳形态。最后采用GMS算法根据运动核来实现正确匹配与错误匹配的区分,避免循环计算不同形态运动核的匹配结果,减少算法运行时间。实验结果表明,改进算法正确匹配点的数目比传统特征点匹配算法至少提高28%,在匹配速度方面较GMS算法至少可提高36%。To solve the problem of the extensive feature-matching time of the grid motion statistics(GMS)algorithm when the image is rotated,an improved fast GMS image matching algorithm is proposed herein.First,a fast feature point extraction and description algorithm is used to violently match the image to obtain the initial matching point pair.The feature matching pair with a higher matching quality is selected according to the Hamming distance.Second,the approximate rotation angle of the two images is obtained by calculating the difference between the main directions of the matching and the feature points.The best form of the motion core is directly determined according to the rotation angle.Finally,the GMS algorithm is used to distinguish between correct and wrong matching points according to the motion core,avoiding the loop calculation of the matching results of different forms of motion cores and reducing the running time of the algorithm.The experimental results show that the number of correct matching points of the improved algorithm is at least 28% higher than that of the traditional feature point matching algorithm,and the matching speed can be at least 36% higher than that of the GMS algorithm.
关 键 词:图像处理 特征匹配 网格运动统计 主方向 运动核
分 类 号:TP391.4[自动化与计算机技术—计算机应用技术]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:18.219.241.228