摘要
图像之间存在光照变化、旋转、仿射变换,使得局部特征匹配后,误匹配无法避免.在正确匹配过半的前提下,提出一种简化的误匹配去除算法FastRanDSac,用于在极短时间内解决图像匹配对之间误匹配点的问题.初步实验表明,在平移、旋转、尺度缩放、视角以及光照变化的图像中,FastRanDSac能保存近100%的正确匹配对,而运行速度与RANSAC相比有大幅度的提高.
Mismatching always exists after matching with local features due to the influences of illumi-nation change, rotation,as well as affine transformation. This work focuses on improving the efficiency of mismatching elimination providing more than half of matching - pairs are correct. A fast random double sample consensus algorithm,called FastRanDSac,is proposed to eliminate the mismatching in a very short time. The power of the methods is that it can keep most correct matching-points while re-moves all the mismatching-points,and greatly improves the efficiency against RANSAC.
作者
文吉成
吴丽君
陈金伙
林培杰
程树英
WEN Jicheng WU Lijun CHEN Jinhuo LIN Peijie CHENG Shuying(Institute of Micro-Nano Devices and Solar Cells,College of Physics and Information Engineering,Fuzhou University,Fuzhou,Fujian 350116,China)
出处
《福州大学学报（自然科学版）》
CAS
北大核心
2017年第3期336-341,共6页
Journal of Fuzhou University(Natural Science Edition)
基金
国家自然科学基金资助项目(51508105
61601127)
教育部留学归国人员科研启动经费资助项目(LXKQ201504)
福建省自然科学基金资助项目(2015J05124)
福建省科技厅高校产学合作资助项目(206H6012)
福建省科技厅工业引导性重点资助项目(2015H0021)
福建省经信委省级技术创新重点资助项目(830020
83016006)
福州大学贵重仪器设备开放测试基金资助项目(2016T042)
福建省教育厅产学研资助项目(JA14038)
