SIFT matching method based on support description
-
摘要: 为减少局部结构相似等因素导致的图像匹配错误,提出一种基于支持描述的匹配判定方法.利用尺度不变特征变换(SIFT,Scale Invariant Feature Transform)算法获得初始匹配集,选取其中稳定性较高的特征点对建立支撑特征集;根据支撑特征点的分布,对初始匹配集的剩余特征点对进行支撑描述,并根据所生成支撑描述符的相似程度,判定剩余特征点对是否为正确匹配.经判定正确的匹配特征点对被加入支撑特征集,使支撑特征集动态扩展,保证了支撑特征点的分布密度及支撑描述的准确性.实验结果表明,该方法能够在保留正确匹配的同时,消除90%以上的错误匹配,有效提高正确匹配率.Abstract: To reduce the image matching errors caused by local structure similarity and other factors, a matching judgment method based on support description was proposed. An initial matching set was obtained by scale invariant feature transform(SIFT) algorithm, from which the more stable feature points were extracted to build a support feature set. According to the distribution of support feature points, a support description on the remaining feature points of the initial matching set was performed. And similarity degree between the generated descriptors was used to determine whether the feature points match correctly. After judgment the correct matching feature points were added to the support feature set, so that the support feature set expanded dynamically and distribution density of the support feature points and accuracy of the support description would be guaranteed. Experimental results show that the proposed method can preserve the correct matches while eliminating more than 90% mismatches and improve the correct matching rate effectively.
-
[1] 蔡晓东,叶培建. 基于特征点集的匹配算法应用于卫星姿态确定[J].北京航空航天大学学报,2006,32(2):171-175 Cai Xiaodong,Ye Peijian.Image matching algorithm based on feature point set for satellite attitude calculation[J].Journal of Beijing University of Aeronautics and Astronautics,2006, 32(2): 171-175(in Chinese) [2] Piccinini P, Prati A,Cucchiara R.Real-time object detection and localization with SIFT-based clustering[J].Image and Vision Computing,2012,30(8):573-587 [3] Ha S W, Moon Y H.Multiple object tracking using sift features and location matching[J].International Journal of Smart Home,2011,5(4):17-26 [4] 赵龙,肖军波. 一种改进的运动目标抗遮挡跟踪算法[J].北京航空航天大学学报,2013,39(4):517-520 Zhao Long,Xiao Junbo.Improved algorithm of tracking moving objects under occlusions[J].Journal of Beijing University of Aeronautics and Astronautics,2013,39(4):517-520(in Chinese) [5] 田越,张永梅, 李波.遥感图像的快速配准方法[J].北京航空航天大学学报,2008,34(11):1356-1359 Tian Yue,Zhang Yongmei,Li Bo.Fast remote sensing image registration algorithm[J].Journal of Beijing University of Aeronautics and Astronautics,2008,34(11):1356-1359(in Chinese) [6] Mikolajczyk K, Schmid C.A performance evaluation of local descriptors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630 [7] Lowe D G. Distinctive image features from scale-invariant key points[J].International Journal of Computer Vision,2004, 60(2): 91-110 [8] Chen J H, Chen C S,Chen Y S.Fast algorithm for robust template matching with M-estimators[J].IEEE Transactions on Signal Processing,2003,51(1):230-243 [9] Sidibe D, Montesinos P,Janaqi S.Fast and robust image matching using contextual information and relaxation[C]//Avenida D.Proceedings of 2nd International Conference on Computer Vision Theory and Applications.Esquerdo,Setubal,Portugal:INSTICC Press,2007:68-75 [10] Mortensen E N, Deng H,Shapiro L.A sift descriptor with global context[C]//Cordelia Schmid.IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Los Alamitos,CA:IEEE Computer Society,2005,1:184-190
点击查看大图
计量
- 文章访问数: 1146
- HTML全文浏览量: 26
- PDF下载量: 613
- 被引次数: 0