首页 | 本学科首页   官方微博 | 高级检索  
     

实时鲁棒的特征点匹配算法
引用本文:陈天华,王福龙.实时鲁棒的特征点匹配算法[J].中国图象图形学报,2016,21(9):1213-1220.
作者姓名:陈天华  王福龙
作者单位:广东工业大学应用数学学院, 广州 510520,广东工业大学应用数学学院, 广州 510520
基金项目:广州市科学研究专项基金项目(201510010059)
摘    要:目的 针对传统的图像特征点匹配算法数据量大,计算耗时长的特点,提出一种实时鲁棒的特征点匹配算法(RRM)。方法 通过微分操作确定图像的边缘区域,找出边缘区域中很有可能成为特征点的锚点,即梯度局部最大的点。对于每个检测出来的特征点,通过计算Intensity Centroid来确定特征点的方向,并且使用改进的Brief来对特征点进行描述,使之具有旋转不变性。最后,结合Hamming距离和对称匹配检验对特征点进行匹配。结果 本文算法与多种算法进行对比,在光照发生变化的情况下,RRM表现出明显的优越性和稳定性,正确匹配率达到83%左右,而其他算法的准确匹配率随着光照的变暗明显下降;在视角、尺度和旋转变化条件下,RRM也具有较高的准确匹配率。结论 实验结果表明,RRM在保证匹配精度的前提下,有效地解决了传统特征点匹配方法中的缺点。因此,本文算法能更好地应用于图像拼接、目标跟踪和对象识别等领域。

关 键 词:特征点匹配  实时  鲁棒  锚点  对称匹配  图像拼接
收稿时间:2015/11/23 0:00:00
修稿时间:2016/4/19 0:00:00

Real-time robust feature-point matching algorithm
Chen Tianhua and Wang Fulong.Real-time robust feature-point matching algorithm[J].Journal of Image and Graphics,2016,21(9):1213-1220.
Authors:Chen Tianhua and Wang Fulong
Affiliation:School of Applied Mathematics, Guangdong University of Technology, Guangzhou 510520, China and School of Applied Mathematics, Guangdong University of Technology, Guangzhou 510520, China
Abstract:Objective Traditional image feature points matching algorithms of large amounts of data bring large computation burdens, particularly for real-time systems, such as visual odometry, or low-power devices, such as cellphones. This condition has led to an intensive search for replacements with lower computation cost. Method This paper proposes a robust real-time feature-point matching algorithm designated RRM. It first determines the edge area of the image by deviation operation, and then finds the anchor point or the gradient local maximum points, which are likely to be the feature points in the edge area. Next, it determines the direction of feature points by calculating Intensity Centroid, and then describes the feature points based on the improved Brief. Finally, it matches the feature points by combining Hamming distance with symmetrical match. Result Compared with a variety of feature-point matching algorithms, the proposed algorithm attains a higher success rate of 83% for images with complex backgrounds such as illumination changes, viewpoint changes, and scaling and rotation changes. The proposed algorithm is superior to and more stable than others. Conclusion Experimental results indicate that the proposed algorithm solves the limitation of traditional feature-point matching effectively, without losing accuracy. The proposed algorithm can be used for image stitching, object tracking, and object recognition.
Keywords:feature point matching  real-time  robust  anchor point  symmetrical match  image stitching
点击此处可从《中国图象图形学报》浏览原始摘要信息
点击此处可从《中国图象图形学报》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号