基于DoG检测图像特征点的快速二进制描述子

刘凯; 汪侃; 杨晓梅; 郑秀娟

doi:10.3788/OPE.20202802.0485

您当前的位置：

首页 >

文章列表页 >

基于DoG检测图像特征点的快速二进制描述子

信息科学 | 更新时间：2020-07-16

- 基于DoG检测图像特征点的快速二进制描述子
- DoG keypoint detection based fast binary descriptor
- 光学精密工程 2020年28卷第2期页码：485-496
- 作者机构：
  
  四川大学电气工程学院，四川成都 610065
- 作者简介：
  
  [ "刘凯 (1973—)，男，江苏无锡人，教授，博士生导师，2001年于四川大学获得硕士学位，2010年于美国肯塔基大学获得博士学位，主要从事结构光三维成像、机器视觉、数字图像/信号处理方面的研究。E-mail:kailiu@scu.edu.cn" ]
  [ "汪侃 (1993—)，男，安徽桐城人，硕士研究生，2016年于四川大学获得学士学位，主要研究方向：图像处理，SFM三维重建。E-mail: kanwang112358@qq.com" ]
  [ "杨晓梅 (1973—)，女，四川乐山人，博士，副教授，硕士生导师，1997年于四川大学获得硕士学位，2003年于四川大学获得博士学位，主要从事检测技术与装置、医学成像、电能质量数据智能分析和深度学习方面的研究。E-mail: yangxiaomei@scu.edu.cn" ]
  郑秀娟 (1981—)，女，福建福州人，副教授，2006年于浙江大学获得硕士学位，2011年于香港理工大学获得博士学位，主要从事医学图像处理、生物医学工程、实现跟踪技术等方面的研究。E-mail: xiujuanzheng@scu.edu.cn ZHENG Xiu-juan, E-mail: xiujuanzheng@scu.edu.cn
- 基金信息：
  
  国家自然科学基金资助项目(NSFC61473198);；四川省科技厅重点研发项目资助(2018GZ0198);；成都市科技局重点研发支撑计划资助项目(2018-YFYF-00029-GX);；四川大学自贡市校地科技合作重点研发项目资助(2018CDZG-12)
- DOI：10.3788/OPE.20202802.0485
  中图分类号： TP391.9
- 收稿日期：2019-07-12，
  
  修回日期：2019-09-06，
  
  录用日期：2019-9-6，
  
  纸质出版日期：2020-02-25
- 稿件说明：
移动端阅览
刘凯, 汪侃, 杨晓梅, 等. 基于DoG检测图像特征点的快速二进制描述子[J]. 光学精密工程, 2020,28(2):485-496.

Kai LIU, Kan WANG, Xiao-mei YANG, et al. DoG keypoint detection based fast binary descriptor[J]. Optics and precision engineering, 2020, 28(2): 485-496.
刘凯, 汪侃, 杨晓梅, 等. 基于DoG检测图像特征点的快速二进制描述子[J]. 光学精密工程, 2020,28(2):485-496. DOI： 10.3788/OPE.20202802.0485.

Kai LIU, Kan WANG, Xiao-mei YANG, et al. DoG keypoint detection based fast binary descriptor[J]. Optics and precision engineering, 2020, 28(2): 485-496. DOI： 10.3788/OPE.20202802.0485.

摘要

针对SIFT描述子实时性差和传统二进制描述子对尺度、旋转和视角变化鲁棒性差的问题，本文通过优化采样模式和添加灰度差分不变量比较测试进行改进，提出了一种鲁棒性更高的二进制描述子。首先，设计了一种尺度关联、编号标记的采样模式；然后，旋转采样模式中各采样点到特定位置，确保描述子尺度、旋转不变性；接着，分析了采样点点对模式对描述子的影响，选择使用机器学习训练后的128对采样点对；最后，选择灰度值比较测试及梯度绝对值和比较测试构建二进制描述子。实验中采用DoG检测图像关键点，结果表明：本文提出的描述子在描述子构建和描述子匹配上比SIFT描述子分别快84%和67%；在有视角变化的图像匹配上，准确率比传统的二进制描述子高3%~5%，召回率平均要高30%以上。本文提出的特征点描述方法适用于时间要求高的图像匹配领域。

Abstract

The SIFT descriptor has poor real-time performance and conventional binary descriptors are poorly robust to scale

rotation

and viewpoint changes. They can be improved by optimizing the sampling pattern and adding gray-value differential invariant comparisons. This study proposed a binary descriptor with a higher robustness. First

a sampling pattern with scale association and number marking was presented. Then

each sampling point of the sampling pattern was rotated to a specific position to ensure that the descriptor was invariant to scale and rotation. Subsequently

the influence of sampling pairs on the descriptor was analyzed

and 128 sampling pairs after machine learning were chosen. Finally

intensity comparison and gradient absolute value comparison were selected to build the descriptor. The image keypoint detection was based on the difference of Gaussians method. Experiment results show that the proposed descriptor is 84% and 67% faster than the SIFT descriptor in descriptor construction and descriptor matching

respectively. Its accuracy is 3% to 5% higher than that of the conventional binary descriptor in image matching with view change

and the recall rate is more than 30%. The descriptor presented in this study is suitable for time-critical image matching.

关键词

Keywords

references

LU D X, SHI H J. A SIFT-Based image fusion method[C]. Proceedings of the 14th IEEE International Conference on Signal Processing, Beijing, China: ICSP , 2018: 375-378.

樊彦国 , 柴江龙 , 许明明 , 等 . 基于ORB与RANSAC融合改进的图像拼接方法 . 光学精密工程 , 2019 . 27 ( 3 ): 702 - 717 . http://www.eope.net/CN/abstract/abstract17946.shtml http://www.eope.net/CN/abstract/abstract17946.shtml .

Y G FAN , J L CHAI , M M XU , 等 . Improved fast Image registration algorithm based on ORB and RANSAC fusion . Opt. Precision Eng , 2019 . 27 ( 3 ): 702 - 717 . http://www.eope.net/CN/abstract/abstract17946.shtml http://www.eope.net/CN/abstract/abstract17946.shtml .

Y Q DUAN , J LU , J J FENG , 等 . Context-aware local binary feature learning for face recognition . IEEE Transaction on Pattern Analysis and Machine Intelligence , 2018 . 40 ( 5 ): 1139 - 1153 . http://cn.bing.com/academic/profile?id=b6ff69c64f02fc013c95abdda8595e86&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=b6ff69c64f02fc013c95abdda8595e86&encoded=0&v=paper_preview&mkt=zh-cn .

蔡怀宇 , 武晓宇 , 卓励然 , 等 . 结合边缘检测的快速SIFT图像拼接方法 . 红外与激光工程 , 2018 . 47 ( 11 ): 1126003 - 1126003 . http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201811061 http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201811061 .

H Y CAI , X Y WU , L R ZHUO , 等 . Fast SIFT image stitching algorithm combining edge detection . Infrared and Laser Engineering , 2018 . 47 ( 11 ): 1126003 - 1126003 . http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201811061 http://d.old.wanfangdata.com.cn/Periodical/hwyjggc201811061 .

M VERMA , B RAMAN . Local neighborhood difference pattern: A new feature descriptor for natural and texture image retrieval . Multimedia Tools and Applications , 2018 . 77 ( 10 ): 11843 - 11866 . http://cn.bing.com/academic/profile?id=66859d330bb67fd85f5459e9309d7d68&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=66859d330bb67fd85f5459e9309d7d68&encoded=0&v=paper_preview&mkt=zh-cn .

王健 , 于鸣 , 任洪娥 . 一种用于图像拼接的改进ORB算法 . 液晶与显示 , 2018 . 33 ( 6 ): 520 - 527 . http://d.old.wanfangdata.com.cn/Periodical/yjyxs201806011 http://d.old.wanfangdata.com.cn/Periodical/yjyxs201806011 .

J WANG , M YU , H E REN . Improved ORB algorithm used in image stitching . Chinese Journal of Liquid Crystals and Displays , 2018 . 33 ( 6 ): 520 - 527 . http://d.old.wanfangdata.com.cn/Periodical/yjyxs201806011 http://d.old.wanfangdata.com.cn/Periodical/yjyxs201806011 .

M J WESTOBY , J BRASINGTON , N F GLASSER , 等 . Structure from motion photogrammetry: A low-cost, effective tool for geoscience applications . Geomorphology , 2012 . 179 300 - 314 . http://cn.bing.com/academic/profile?id=b8006e9be765e90184d8ab4c4fdb00ad&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=b8006e9be765e90184d8ab4c4fdb00ad&encoded=0&v=paper_preview&mkt=zh-cn .

N SNAVELY , S M SEITZ , R SZELISKI . Photo tourism: exploring photo collection in 3D . ACM Transactions on Graphics , 2006 . 25 ( 3 ): 835 - 846 .

T TUYTELAARS , K MIKOLAJCZYK . Local invariant feature detectors: a survey . Foundations and Trends in Computer Graphics and Vision , 2008 . 3 ( 3 ): 177 - 280 . http://d.old.wanfangdata.com.cn/NSTLHY/NSTL_HYCC0214006632/ http://d.old.wanfangdata.com.cn/NSTLHY/NSTL_HYCC0214006632/ .

K MIKOLAJCZYK , C SCHMID . A performance evaluation of local descriptors . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2005 . 27 ( 10 ): 1615 - 1630 .

HEINLY J, DUNN E, FRAHM J M. Comparative evaluation of binary features[C]. Proceedings of the 12th European Conference on Computer Vision, Florence, Italy: ECCV , 2012: 759-773.

D G LOWE . Distinctive image features from scale-invariant keypoints . International Journal of Computer Vision , 2004 . 60 ( 2 ): 91 - 110 . http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ025429678/ http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ025429678/ .

H BAY , A ESS , T TUYTELAARS , 等 . SURF: speeded up robust features . Computer Vision and Image Understanding , 2008 . bf110 ( 3 ): 346 - 359 . http://d.old.wanfangdata.com.cn/Periodical/hwyjggc200901035 http://d.old.wanfangdata.com.cn/Periodical/hwyjggc200901035 .

KE Y, SUKTHANKAR R. PCA-SIFT: a more distinctive representation for local image descriptors[C]. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: CVPR , 2004: 506-513.

颜雪军 , 赵春霞 , 袁夏 . 2DPCA-SIFT:一种有效的局部特征描述方法 . 自动化学报 , 2014 . 40 ( 4 ): 675 - 682 . http://d.old.wanfangdata.com.cn/Periodical/zdhxb201404011 http://d.old.wanfangdata.com.cn/Periodical/zdhxb201404011 .

X J YAN , CH X ZHAO , X YUAN . 2DPCA-SIFT: an efficient local feature descriptors . Acta Automatica Sinica , 2014 . 40 ( 4 ): 675 - 682 . http://d.old.wanfangdata.com.cn/Periodical/zdhxb201404011 http://d.old.wanfangdata.com.cn/Periodical/zdhxb201404011 .

E TOLA , V LEPETIT , P FUA . DAISY: an efficient dense descriptor applied to wide-baseline stereo . IEEE Transaction on Pattern Analysis and Machine Intelligence , 2010 . 32 ( 5 ): 815 - 830 . http://d.old.wanfangdata.com.cn/Periodical/jsjkx201411056 http://d.old.wanfangdata.com.cn/Periodical/jsjkx201411056 .

曾峦 , 顾大龙 . 一种基于扇形区域分割的SIFT特征描述符 . 自动化学报 , 2012 . 38 ( 9 ): 1513 - 1519 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdhxb201209013 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdhxb201209013 .

L ZENG , D L GU . A SIFT feature descriptor based on sector area partitioning . Acta Automatica Sinca , 2012 . 38 ( 9 ): 1513 - 1519 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdhxb201209013 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=zdhxb201209013 .

耿庆田 , 赵浩宇 , 王宇婷 , 等 . 基于改进SIFT特征提取的车标识别 . 光学精密工程 , 2018 . 26 ( 5 ): 1267 - 1274 . http://www.eope.net/CN/abstract/abstract17623.shtml http://www.eope.net/CN/abstract/abstract17623.shtml .

Q T GENG , H Y ZHAO , Y T WANG , 等 . A vehicle logo recognition algorithm based on the improved SIFT feature . Opt. Precision Eng , 2018 . 26 ( 5 ): 1267 - 1274 . http://www.eope.net/CN/abstract/abstract17623.shtml http://www.eope.net/CN/abstract/abstract17623.shtml .

唐永鹤 , 卢焕章 , 胡谋法 . 基于Laplacian的局部特征描述算法 . 光学精密工程 , 2011 . 19 ( 12 ): 2999 - 3006 . http://www.eope.net/CN/abstract/abstract13870.shtml http://www.eope.net/CN/abstract/abstract13870.shtml .

Y H TANG , H Z LU , M F HU . Local feature description algorithm based on laplacian . Opt. Precision Eng , 2011 . 19 ( 12 ): 2999 - 3006 . http://www.eope.net/CN/abstract/abstract13870.shtml http://www.eope.net/CN/abstract/abstract13870.shtml .

C SCHMID , R MOHR . Local grayvalue invariants for image retrieval . IEEE Transactions on Pattern Analysis and Machine Intelligence , 1997 . 19 ( 5 ): 530 - 535 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=24ec0fa7240d3e52c557692c5b57dfde http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=24ec0fa7240d3e52c557692c5b57dfde .

M CALONDER , V LEPETIT , M OZUYSAL , 等 . BRIEF: computing a local binary descriptor very fast . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2012 . 34 ( 7 ): 1281 - 1298 . http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ0232614204/ http://d.old.wanfangdata.com.cn/NSTLQK/NSTL_QKJJ0232614204/ .

RUBLEE E, RABAUD V, KONOLIGE K, et al .. ORB: an efficient alternative to SIFT or SURF[C]. Proceedings of the 2011 International Conference on Computer Vision. Barcelona Spain: ICCV , 2011: 2564-2571.

LEUTENEGGER S, CHLI M, SIEGWIET R. BRISK: binary robust invariant scalable keypoints[C]. Proceedings of the 2011 International Conference on Computer Vision. Barcelona, Spain: ICCV , 2011: 2548-2555.

ALAHI A, ORTIZ R, VANDERGHEYNST P. FREAK: fast retina keypoint[C]. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. Rhode Island, Providence, USA: CVPR , 2012: 2069-2076.

TRZCINSKI T, CHRISTOUDIAS M, FUA P, et al .. Boosting binary keypoint descriptors[C]. Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Washington, D.C., USA: CVPR , 2013: 2874-2881.

V BALNTAS , L Tang , K MIKOLAJCZYK . Binary online learned descriptors . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2018 . 40 ( 3 ): 555 - 567 . http://cn.bing.com/academic/profile?id=514b6329b2e6e15a9dfd54e642aed42f&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=514b6329b2e6e15a9dfd54e642aed42f&encoded=0&v=paper_preview&mkt=zh-cn .

LIN K, LU J, CHEN C S, et al .. Learning compact binary descriptors with unsupervised deep neural networks[C]. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA: CVPR , 2016: 1183-1192.

ZIEBA M, SEMBERECKI P, EI-GAALY T, et al .. BinGAN: learning compact binary descriptors with a regularized GAN[C]. Proceedings of the 2018 Conference on Neural Information Processing Systems, Montreal, Canada: NIPS , 2018: 3608-3618.

Y Q DUAN , J W LU , Z W WANG , 等 . Learning deep binary descriptor with multi-quantization . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2018 . 41 ( 8 ): 1924 - 1938 . http://cn.bing.com/academic/profile?id=69a639d52e22a9b8465cdcaff64e3f7b&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=69a639d52e22a9b8465cdcaff64e3f7b&encoded=0&v=paper_preview&mkt=zh-cn .

惠国保 , 李东波 , 童一飞 . 基于优化采样模式的紧凑而快速的二进制描述子 . 自动化学报 , 2014 . 40 ( 2 ): 255 - 266 .

G B HUI , D B LI , Y F TONG . A binary descriptor based on both optimized sampling pattern and image sub-patches . Acta Automatica Sinica , 2014 . 40 ( 2 ): 255 - 266 .

T OJALA , M PIETIKAINEN , T MAENPAA . Multiresolution gray-scale and rotation invariant texture classification with local binary patterns . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2002 . 24 ( 7 ): 971 - 987 . http://cn.bing.com/academic/profile?id=bbab6ef5dd30d698066c963f5602e424&encoded=0&v=paper_preview&mkt=zh-cn http://cn.bing.com/academic/profile?id=bbab6ef5dd30d698066c963f5602e424&encoded=0&v=paper_preview&mkt=zh-cn .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

LightDiffu-DCE：基于光照强度扩散的低光照图像增强

多级图特征融合引导相机位姿回归

基于机载的红外动态目标视频实时超分辨率重建

基于知识蒸馏的Transformer视觉跟踪器

3D-CNN与Transformer混合结构的高光谱图像空谱联合分类