帮助 关于我们

返回检索结果

多模态鲁棒的局部特征描述符
Multimodality robust local feature descriptors

查看参考文献16篇

文摘 针对基于灰度的局部特征匹配方法对图像对比度变化敏感,导致在多模态图像配准应用中性能大幅下降的问题,提出了一种多模态鲁棒的局部特征描述符和匹配方法。首先,基于对比度变化不敏感的相位一致性和局部方向信息,提出一种多模态鲁棒的角点和线段特征提取方法,在对比度差异显著的多模态图像之间提取较多的共性角点和线段特征;然后,以角点为中心选择48个均匀分布的圆形特征子区域,利用角点与特征子区域内线段的距离和线段长度信息,构建96维的特征向量;最后,将归一化相关函数作为匹配测度函数进行特征匹配,并采用基于位置约束的随机抽样一致(RANSAC)方法进行匹配提纯。实验表明,本文提出的多模态匹配方法匹配正确率和重复率分别高达80%和13%,分别为对称-尺度不变特征变换算法(S-SIFT)、多模态-快速鲁棒特征算法(MM-SURF)等基于灰度方法的2~4倍和4~7倍,显著优于同类方法。
其他语种文摘 The intensity-based local feature matching methods are sensitive to image contrast variations,so the performance declines significantly when they are applied in multimodal image registration.To solve the above problem,a multimodality robust local feature descriptor was proposed and the corresponding feature matching method was developed.Firstly,an extraction method for the multimodality robust corner and line segment was proposed based on the phase congruency and local direction information insensitive to contrast variants.Compared with intensitybased method,more equivalent corners and line segments were extracted between multimodal images with more contrast differences.Then,the feature region containing of 48circular sub-regions was selected by using the corner for a center and the 96dimensional feature vectors were generated by using the distance values of corners and the length values of line segments located in feature subregions. Finally,the feature matching method based on normalized correlation function was proposed and the location constraint-based RANdom SAmple Consensus(RANSAC)algorithm was used to remove false matching point pairs.The experimental results indicate that the precision and repeatability on multimodal image matching of the proposed method reach 80%and 13%respectively. As compared with the other intensity-based image matching methods,the precision and repeatability of proposed method are 2-4times and 4-7times respectively those of Symmetric-Scale Invariable Feature Transformation(S-SIFT)and Multimodal-Speeded-up Robust Features(MM-SURF).It concludes that the proposed method outperforms many state-of-the-art methods significantly.
来源 光学精密工程 ,2015,23(5):1474-1483 【核心库】
DOI 10.3788/ope.20152305.1474
关键词 图像配准 ; 多模态配准 ; 多模态鲁棒特征 ; 相位一致性 ; 局部方向 ; 归一化相关
地址

中国科学院沈阳自动化研究所, 中国科学院光电信息处理重点实验室, 辽宁, 沈阳, 110016

语种 中文
文献类型 研究性论文
ISSN 1004-924X
学科 自动化技术、计算机技术
基金 中国科学院光电信息处理重点实验室开放基金资助项目 ;  国家973计划
文献收藏号 CSCD:5431773

参考文献 共 16 共1页

1.  曹晓倩. 一种光照度不一致鲁棒立体匹配算法. 机器人,2014,36(5):634-640 被引 1    
2.  刘志文. 应用尺度不变特征变换的多源遥感影像特征点匹配. 光学精密工程,2013,21(8):2146-2153 被引 18    
3.  杨桄. 基于多特征的红外与可见光图像融合. 光学精密工程,2014,22(2):489-496 被引 27    
4.  Suri S. Mutual-information-based registration of TerraSAR-X and Ikonos imagery in urban areas. IEEE Transaction Geoscience Remote Sensing,2010,48(2):939-949 被引 37    
5.  Zou Y B. Image thresholding based on template matching with arctangent Hausdorff distance measure. Optics and Lasers in Engineering,2013,51(5):600-609 被引 6    
6.  Bodensteiner C. Local multi-modal image matching based on self-similarity. IEEE International Conference on Image Processing,2010:937-940 被引 1    
7.  Lowe D. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision,2004,60(2):91-110 被引 4559    
8.  Bay H. SURF:Speeded Up Robust Features. European Conference on Computer Vision,2006:404-417 被引 112    
9.  Chen J. Real-time multi-modal rigid registration based on a novel symmetric-SIFT descriptor. Progress in Natural Science,2009,19(5):643-651 被引 8    
10.  Zhao D. Rapid multimodality registration based on MM-SURF. Neurocomputing,2014,131(5):87-97 被引 3    
11.  Wang Zh H. MSLD:A robust descriptor for line matching. Pattern Recognition,2009,42(5):941-953 被引 36    
12.  Pang G. The Gixel Array Descriptor(GAD)for multi-modal image matching. IEEE Workshop on Applications of Computer Vision,2013:497-504 被引 1    
13.  Kovesi P. Phase congruency:a low-level image invariant. Psychological Research,2000,64(2):136-148 被引 25    
14.  Kovesi P. Phase congruency detects corners and edges. The Australian Pattern Recognition Society Conference:DICTA,2003:309-318 被引 3    
15.  Felsberg M. The monogenic signal. IEEE Transactions on Signal Processing,2001,49(12):3136-3144 被引 27    
16.  Gioi R G V. LSD:A fast line segment detector with a false detection control. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,4(32):722-732 被引 205    
引证文献 6

1 屈玉福 自适应变尺度特征点提取方法 光学精密工程,2017,25(1):188-197
被引 7

2 董强 基于改进BRISK的图像拼接算法 电子与信息学报,2017,39(2):444-450
被引 14

显示所有6篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护:中国科学院文献情报中心
地址:北京中关村北四环西路33号 邮政编码:100190 联系电话:(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号