摘要
针对移动设备弱处理能力和低内存等局限性,导致增强现实技术不能在移动设备上普及,提出一种新的增强现实技术方案。采用SURF算法提取视频帧图像的特征点,接着使用FREAK算法进行特征点描述;在汉明距离强制匹配之后,采用改进的RANSAC算法剔除了误匹配点,然后通过计算比较匹配特征点占样本图像特征点的比重,判断是否成功匹配目标物体;最后渲染对应的三维模型完成增强现实三维注册。通过在Android移动设备上的验证,结果表明该技术方案满足移动设备对实时性、准确性和鲁棒性的要求,为移动增强现实的推广奠定了良好的基础。
In view of the limitations of mobile devices such as weak processing capacity and low not be popularized on mobile devices. In this paper a new augmented reality technology scheme is proposed. Using the SURF algoritlim to extractthe feature points of video frames,and then using the FREAKalgorithm for feature description. After Hamming distathe improved RANSAC algorithim to remove the false matching points,by judging the matching feature points accounted for sample image feature points,to determine whethier successful object matching and ensure the recognition accucorresponding three-dimensional model to complete the three-dimensional registration of augmented realimobile devices, the results show that the proposed scheme meets the requirements of real-time, accuracy and robustness of mobile dev ice s,which lays a good foundation for the realization of mobile augmented reality.
作者
苏泽荫
林志贤
郭太良
Su Zeyin Lin Zhixian Guo Tailiang(College of Physics and Information Engineering,Fuzhou University,Fuzhou 350100, China)
出处
《微型机与应用》
2017年第9期11-14,共4页
Microcomputer & Its Applications
基金
国家重点研发计划课题(2016YFB0401503)
广东省科技重大专项(2016B090906001)
福建省科技重大专项(2014HZ0003-1)
福建省资助省属高校专项课题(JK2014002)
