一种改进的SIFT图像立体匹配算法

李丹; 孙海涛; 王海莉

doi:10.3969/j.issn.0258-2724.2015.03.017

一种改进的SIFT图像立体匹配算法

doi: 10.3969/j.issn.0258-2724.2015.03.017

基金项目:

国家自然科学基金资助项目(51307003)

详细信息

作者简介:
李丹(1976-),女,副教授,博士,硕士生导师,研究方向为图像处理、计算机视觉、测控技术,电话:13965381975, E-mail:lidan@ahut.edu.cn

计量
- 文章访问数: 1522
- HTML全文浏览量: 115
- PDF下载量: 1508
- 被引次数: 33
出版历程
- 收稿日期: 2013-05-13
- 刊出日期: 2015-06-25

An Improved SIFT Algorithm for Image Stereo Matching

摘要

摘要: 针对SIFT算法复杂度高、计算时间长、影响立体匹配的实时性等问题,提出了一种改进的立体视觉特征点匹配算法该算法从两个方面对SIFT算法进行改进:首先利用24维特征描述符代替128维特征描述符,以降低计算复杂度;其次在图像对匹配过程中采用改进的BBF搜索算法,通过引入最小优先级队列的限制条件和匹配精度更高的马氏距离判断两幅图像特征点的匹配性.采用经典图像和未知的室外环境下拍摄的图像对本文算法进行实验验证,结果表明,本文提出的算法每100个特征点检测时间为0.01 s,正确匹配率平均为89.65%,相对于原算法,提高了匹配的准确度,并降低了匹配时间.
- 尺度不变特征变换 /
- 立体视觉 /
- 特征点匹配 /
- 相似性度量 /
- BBF搜索算法
Abstract: The high complexity and long computing time of SIFT (scale invariant feature transform) algorithm affect the real-time ability of stereo matching. To solve this problem, an improved feature-points matching algorithm of stereo vision was proposed. The SIFT algorithm was improved in two aspects. First, 24-dimensional feature descriptor instead of 128-dimensional feature descriptor was used to reduce computational complexity. Then the improved BBF search algorithm was used in the process of image matching, so that the feature point matching of the two images can be determined through the minimum priority queue restrictions and the Mahalanobis distance of higher matching accuracy. The classical images and images taken at unknown outdoor environment were used to validate this algorithm. Experimental results show that the proposed algorithm spends 0.01 s to detect 100 feature points, and the average correct matching rate is 89.65%. Compared with the original algorithm, it improves the matching accuracy and reduces the matching time.
- SIFT /
- stereo vision /
- feature point matching /
- similarity measure /
- BBF searching algorithm

HTML全文

参考文献(37)

刘小军,杨杰,孙坚伟,等. 基于SIFT的图像配准方法

CHANGLI K, SOONYONG P. Fast stereo matching of feature links

[J]. 红外与激光工程,2008,37(1): 156-160. LIU Xiaojun, YANG Jie, SUN Jianwei, et al. Image registration approach based on SIFT

[J]. Infrared and Laser Engineering, 2008, 37(1): 156-160.

谢凡,秦世引. 基于SIFT的单目移动机器人宽基线立体匹配

孙浩,王程,王润生. 局部不变特征综述

LOWE D G. Distinctive image features from scale-invariant key points

[C]//2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission. Hangzhou: IEEE Computer Society, 2011: 256-274.

YAN Ke, SUKTHANKAR R. PCA-SIFT: a more distinctive representation for local image descriptors

[J]. 仪器仪表学报,2008,29(11): 2247-2252. XIE Fan, QIN Shiyin. Wide baseline stereo vision matching approach for monocular mobile robot based on SIFT

MIKOLAJCZYK K, SCHMID C. A performance evaluation of local descriptors

[J]. Chinese Journal of Scientific Instrument, 2008, 29(11): 2247-2252.

DELLINGER F, DELON J, GOUSSEAU Y, et al. SAR-SIFT: a SIFT-like algorithm for SAR images

曾峦,王元钦,谭久彬. 改进的SIFT特征提取和匹配算法

刘立,彭复员,赵坤,等. 采用简化SIFT算法实现快速图像匹配

[J]. 中国图象图形学报,2011,16(2): 141-150. SUN Hao, WANG Cheng, WANG Runsheng. A review of local invariant features

[J]. Journal of Image and Graphics, 2011, 16(2): 141-150.

YANG Zhengwei COHEN F S. Image registration and object recognition using affine invariants and convex hulls

王民,刘伟光. 基于改进SIFT特征的双目图像匹配算法

ZHANG Jing, SANG Hongshi, SHEN Xubang. Improved SIFT matching algorithm with adaptive matching direction and scale restriction

[J]. International Journal of Computer Vision, 2004, 60(2): 91-110.

刘健,张国华,黄琳琳. 基于改进SIFT的图像配准算法

BASTANLAR Y, TEMIZEL A, YARDIMCI Y. Improved SIFT matching for image pairs with scale difference

[C]//Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington D.C.: IEEE Press, 2004: 506-513.

[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10): 1615-1630.

[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(1): 453-466.

[J]. 光学精密工程,2011,19(6): 1391-1397. ZENG Luan, WANG Yuanqin, TAN Jiubin. Improved algorithm for SIFT feature extraction and matching

[J]. Optics and Precision Engineering, 2011, 19(6): 1391-1397.

[J]. 红外与激光工程,2008,37(1): 181-184. LIU Li, PENG Fuyuan, ZHAO Kun, et al. Simplified SIFT algorithm for fast image matching

[J]. Infrared and Laser Engineering, 2008, 37(1): 181-184.

[J]. IEEE Transactions on Image Processing, 1999: 934-946.

[J]. 计算机工程与应用,2013,49(2): 203-206. WANG Min, LIU Weiguang. Advanced algorithm based on SIFT and its application in binocular stereo vision

[J]. Computer Engineering and Application, 2013, 49(2): 203-206.

[J]. International Journal of Digital Content Technology and Its Applications, 2012, 6(22): 851-858.

[J]. 北京航空航天大学学报,2010,36(9): 1121-1124. LIU Jian, ZHANG Guohua, HUANG Linlin.Image registration approach based on improved SIFT

[J]. Journal of Beijing University of Aeronautics and Astronautics, 2010, 36(9): 1121-1124.

[J]. Electronics Letters, 2010, 46(5): 346-348.

施引文献

期刊类型引用(10)

1.	汤澳，许四祥，宋昱宸，任加琪. 基于二维熵与低维度描述符的双目视觉测量. 电子测量与仪器学报. 2025(03): 169-176 . 百度学术
2.	焦卫东，焦一哲. 基于CA-SIFT的图像特征两级匹配算法. 中国民航大学学报. 2025(02): 73-82 . 百度学术
3.	唐忠智，闫兵，黄燕，华春蓉，郑东. 一种基于双预筛选改进的SIFT图像立体匹配算法. 激光与光电子学进展. 2021(22): 190-199 . 百度学术
4.	王文正，吴德松，李千登. 钻井过程人员异常行为视频智能识别系统. 安全、健康和环境. 2020(02): 15-20 . 百度学术
5.	马庭田，叶文华，黄河，郭云霞. 基于视觉的目标识别中改进SIFT算法研究. 机械制造与自动化. 2019(02): 188-191 . 百度学术
6.	汤强. SIFT算法在VR场景拼接中的应用. 长春工业大学学报. 2018(02): 156-162 . 百度学术
7.	郑现，申萍，邱霁，夏顺盈. 视频拼接技术在列车安全监控中的应用. 机车电传动. 2018(05): 69-73 . 百度学术
8.	吴丽君，文吉成，陈志聪，陈金伙，林培杰，程树英. 改进SIFT算法实现图像的快速匹配. 福州大学学报(自然科学版). 2017(06): 801-809 . 百度学术
9.	赵岩，陈月，王世刚. 结合投影误差校正的快速SIFT图像拼接. 光学精密工程. 2017(06): 1645-1651 . 百度学术
10.	林陶，黄国荣，郝顺义，沈飞. 尺度不变特征转换算法在图像特征提取中的应用. 计算机应用. 2016(06): 1688-1691+1698 . 百度学术