[1]唐坤,韩斌.一种基于参考点距离的SIFT特征点匹配算法[J].智能系统学报,2015,10(03):376-380.[doi:10.3969/j.issn.1673-4785.201311020]
 TANG Kun,HAN Bin.A SIFT matching algorithm based on the distance to reference point[J].CAAI Transactions on Intelligent Systems,2015,10(03):376-380.[doi:10.3969/j.issn.1673-4785.201311020]
点击复制

一种基于参考点距离的SIFT特征点匹配算法(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第10卷
期数:
2015年03期
页码:
376-380
栏目:
出版日期:
2015-06-25

文章信息/Info

Title:
A SIFT matching algorithm based on the distance to reference point
作者:
唐坤1 韩斌2
1. 东南大学 交通学院, 江苏 南京 210096;
2. 江苏科技大学 计算机科学与工程学院, 江苏 镇江 212000
Author(s):
TANG Kun1 HAN Bin2
1. School of Transportation, Southeast University, Nanjing 210096, China;
2. School of Computer Science and Engineering, Jiangsu University of Science and Technology, Zhenjiang 212000, China
关键词:
SIFTDRP算法特征点匹配最近邻参考点
Keywords:
scale invariant feature transform (SIFT)distance to reference point (DRP) algorithmfeature point matchingnearest neighborreference point
分类号:
TP319
DOI:
10.3969/j.issn.1673-4785.201311020
文献标志码:
A
摘要:
针对SIFT特征点匹配时间消耗大的问题,提出了一种基于参考点距离的SIFT特征点匹配算法—DRP算法.该算法首先计算一次所有待匹配特征点到参考点之间的距离,对之进行快速排序并保存.然后计算待查询特征点到参考点的距离,并在已排序的距离中使用二分法搜索返回此距离的最近邻.最后以此最近邻为中心,在有限范围内搜索待查询特征点的近似最近邻.VGG实验室ACF图片库的测试结果表明,相比于经典的SIFT算法,DRP算法可以在不损失匹配效果的前提下,有效降低SIFT特征点匹配的时间消耗.
Abstract:
To address the high time cost of feature point matching in scale invariant feature transform (SIFT), a new SIFT feature point matching algorithm based on the distance to reference point—DRP algorithm is put forward. Firstly, distances from the reference point to every feature point to be matched is computed using DRP algorithm. Then, these distances computed previously is ordered and saved in a dataset named as distance of ordering. Next, distances from the reference point to the feature point to be queried is also computed. After that, the nearest neighbor of the distance in distance of ordering is retrieved with binary search and returned as index of center. Finally, the nearest neighbor of feature point to be queried is searched one by one in a certain range whose center is index of center. It is proven by experiment tested on ACF (affine covariant features) pictures from VGG(visual geometry group) laboratory that DRP algorithm can effectively decrease the time cost of SIFT feature points matching without loss of matching results compared with the classical SIFT algorithm.

参考文献/References:

[1] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.
[2] 吴伟交, 王敏, 黄心汉, 等. 基于向量夹角的SIFT特征点匹配算法[J]. 模式识别与人工智能, 2013, 26(1): 123-127.WU Weijiao, WANG Min, HUANG Xinhan, et al. SIFT feature matching algorithm based on vector angle. Pattern Recognition and Artificial Intelligence, 2013, 26(1): 123-127.
[3] KRYSTIAN M, CORDELIA S. A performance evaluation of local descriptors[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630.
[4] GIONIS A, INDYK P, MOTWANI R. Similarity search in high dimensions via hashing[C]//Proceedings of the 25th International Conference on Very Large Data Bases. San Francisco, USA, 1999: 518-529.
[5] BEIS J S, LOWE D G. Shape indexing using approximate nearest-neighbor search in high-dimensional spaces[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. San Juan, Puerto Rico, 1997: 1000-1006.
[6] FERHATOSMANOGLU H, TUNCEL E, AGRAWAL D, et al. Vector approximation based indexing for non-uniform high dimensional data sets[C]//Proceedings of the International Conference on Information and Knowledge Management. McLean, USA, 2000: 202-209.
[7] WEBER R, SCHEK H J, BLOTT S. A quantitative analysis and performance study for similarity-search methods in high dimensional spaces[C]//Proceedings of the International Conference on Very Large Databases. New York, 1998: 194-205.
[8] JAGADISH H V, OOI B C, TAN K L, et al. IDistance: an adaptive B+-tree based indexing method for nearest neighbor search[J]. ACM Transactions on Database Systems, 2005, 30(2): 364-398.
[9] AUCLAIR A, COHEN L D, VINCENT N. How to use SIFT vectors to analyze an image with database templates[C]//Proceedings of the 5th International Workshop on Adaptive Multimedia Retrieval. Paris, France, 2008: 224-236.
[10] SLANEY M, CASEY M. Locality-sensitive hashing for finding nearest neighbors[J]. IEEE Signal Processing Magazine, 2008, 25(2): 128-131.
[11] 张军旗, 周向东, 王梅, 等. 基于聚类分解的高维度量空间索引B+-tree[J]. 软件学报, 2008, 19(6): 1401-1412.ZHANG Junqi, ZHOU Xiangdong, WANG Mei, et al. Cluster splitting based high dimensional metric space index B+-tree[J]. Journal of Software, 2008, 19(6): 1401-1412.
[12] 杨恒, 王庆, 何周灿. 面向高维图像特征匹配的多次随机子向量量化哈希算法[J]. 计算机辅助设计与图形学学报, 2010, 22(3): 494-502.YANG Heng, WANG Qing, HE Zhoucan. Mutiple randomized sub-vectors quantization hashing for high-dimensional image feature matching[J]. Journal of Computer-Aided Deasign & Computer Graphics, 2010, 22(3): 494-502.
[13] LOWE D. OpenSIFT—An open-source SIFT library.[2013-11-15]. http://robwhess.github.io/opensift/.
[14] The Visual Geometry Group. Affine covariant features. (2007-07-15)[2013-11-15]. http://www.robots.ox.ac.uk/~vgg/research/affine/index.html.

相似文献/References:

[1]许可乐,唐涛,蒋咏梅.一种SAR图像稳健特征点提取方法[J].智能系统学报,2013,8(04):287.[doi:10.3969/j.issn.1673-4785.201304038]
 XU Kele,TANG Tao,JIANG Yongmei.A stable feature point extraction approach for SAR image registration[J].CAAI Transactions on Intelligent Systems,2013,8(03):287.[doi:10.3969/j.issn.1673-4785.201304038]
[2]唐坤,韩斌.一种自适应搜索范围的SIFT特征点快速匹配算法[J].智能系统学报,2014,9(06):723.[doi:10.3969/j.issn.1673-4785.201309037]
 TANG Kun,HAN Bin.A new fast algorithm of self-adaptive search scope for SIFT matching[J].CAAI Transactions on Intelligent Systems,2014,9(03):723.[doi:10.3969/j.issn.1673-4785.201309037]
[3]张文超,吕岳,文颖,等.几何信息与SIFT特征相结合的特定人手写关键词检测[J].智能系统学报,2014,9(05):544.[doi:10.3969/j.issn.1673-4785.201402032]
 ZHANG Wenchao,LYU Yue,WEN Ying,et al.Specific handwritten keyword spotting using geometric information and SIFT feature[J].CAAI Transactions on Intelligent Systems,2014,9(03):544.[doi:10.3969/j.issn.1673-4785.201402032]

备注/Memo

备注/Memo:
收稿日期:2013-11-28;改回日期:。
基金项目:国家自然科学基金资助项目(61374195);中央高校基本科研业务费专项资金资助项目;江苏省普通高校研究生科研创新计划资助项目(KYLX_0180).
作者简介:唐坤,男,1988年生,博士研究生,主要研究方向为数字图像处理、智能交通.韩斌,男,1968年生,教授,博士,主要研究方向为数字图像处理、智能检测、并行计算.
通讯作者:唐坤. E-mail: tkpaperzc@sina.cn.
更新日期/Last Update: 2015-07-15