计算机工程 ›› 2019, Vol. 45 ›› Issue (8): 230-235.doi: 10.19678/j.issn.1000-3428.0053924

• 人工智能及识别技术 • 上一篇    下一篇

基于KCF与改进ORB的增强现实方法

李一1, 冯楠2, 谭顺成3   

  1. 1. 中国人民解放军 92493部队13分队, 辽宁 葫芦岛 125000;
    2. 中国人民解放军 92941部队41分队, 辽宁 葫芦岛 125000;
    3. 海军航空大学 信息融合研究所, 山东 烟台 264001
  • 收稿日期:2019-02-16 修回日期:2019-06-19 出版日期:2019-08-15 发布日期:2019-08-08
  • 作者简介:李一(1980-),男,高级工程师,主研方向为装备数据工程;冯楠,工程师、硕士;谭顺成,工程师、博士。
  • 基金项目:
    国家自然科学基金(61671462)。

Augmented Reality Method Based on KCF and Improved ORB

LI Yi1, FENG Nan2, TAN Shuncheng3   

  1. 1. The 13 th Unit of 92493 PLA Troops, Huludao, Liaoning 125000, China;
    2. The 41 st Unit of 92491 PLA Troops, Huludao, Liaoning 125000, China;
    3. Research Institute of Information Fusion, Naval Aeronautical University, Yantai, Shandong 264001, China
  • Received:2019-02-16 Revised:2019-06-19 Online:2019-08-15 Published:2019-08-08

摘要: 针对增强现实(AR)系统在进行虚拟信息叠加时待注册区域被遮挡的情况,提出一种基于实时特征检测与目标跟踪的AR系统三维注册方法。使用KCF算法对待注册目标区域与模板进行实时FAST特征匹配,通过改进ORB算法,提出SIFT-ORB-MRANSAC融合算法,完成特征点的提取、匹配以及误匹配去除。在此基础上,根据特征点之间的匹配关系计算注册矩阵,通过注册矩阵叠加虚拟信息实现对现实世界的增强。实验结果表明,该方法在光照变化、遮挡以及旋转变换的情况下,可将虚拟信息快速、准确地叠加到待注册区域,提高AR系统的运算效率。

关键词: ORB算法, KCF算法, 增强现实, 三维注册, 特征点

Abstract: Aiming at the situation that the area to be resigistered in the Augmented Reality(AR) system is occluded when the virtual information is superimposed,a three-dimensional registration method for AR system based on real-time feature detection and target tracking is proposed.KCF algorithm is used to perform real-time FAST feature matching on the target area and the template.By improving the ORB algorithm,SIFT-ORB-MRANSAC fusion algorithm is proposed to extract and match feature remove mismatches.On this basis,the registration matrix is calculated by the matching relationship between the feature points,and virtual information is overlaid to the registration matrix to augment the real world.Experimental results show that the proposed method can quickly and accurately overlay the virtual information to the registered area under the conditions of illumination change,occlusion and rotation transformation,and improve the points as well as computation efficiency of AR systems.

Key words: ORB algorithm, KCF algorithm, Augmented Reality(AR), three-dimensional registration, feature point

中图分类号: