3D reconstruction technique based on SURF-OKG feature matching

ZHANG Lei; SHI Yan; LU Wenyong; XU Rui; JIN Zhan; LUO Weijie; CEHN Yi; ZHAO Chunliu; ZHAN Chunlian

doi:10.37188/OPE.20243206.0915

您当前的位置：

首页 >

文章列表页 >

3D reconstruction technique based on SURF-OKG feature matching

Information Sciences | 更新时间：2024-03-31

- 3D reconstruction technique based on SURF-OKG feature matching
- Optics and Precision Engineering Vol. 32, Issue 6, Pages: 915-929(2024)
- 作者机构：
  
  1.中国计量大学光学与电子科技学院，浙江杭州 310018
  2.浙江视觉智能创新中心有限公司，浙江杭州 311215
  3.浙江省北大信息技术高等研究院，浙江杭州 311215
- 作者简介：
- 基金信息：
- DOI：10.37188/OPE.20243206.0915
  CLC： TP391.4
- Published：25 March 2024，
  
  Received：21 August 2023，
  
  Revised：10 October 2023，
- 稿件说明：
移动端阅览
张蕾,石岩,卢文雍等.基于SURF-OKG特征匹配的三维重建技术[J].光学精密工程,2024,32(06):915-929.

ZHANG Lei,SHI Yan,LU Wenyong,et al.3D reconstruction technique based on SURF-OKG feature matching[J].Optics and Precision Engineering,2024,32(06):915-929.
张蕾,石岩,卢文雍等.基于SURF-OKG特征匹配的三维重建技术[J].光学精密工程,2024,32(06):915-929. DOI： 10.37188/OPE.20243206.0915.

ZHANG Lei,SHI Yan,LU Wenyong,et al.3D reconstruction technique based on SURF-OKG feature matching[J].Optics and Precision Engineering,2024,32(06):915-929. DOI： 10.37188/OPE.20243206.0915.

摘要

为了解决结构光三维重建中传统立体匹配存在的特征点匹配错误、匹配缺失和匹配重复等问题，本文将SURF算法中高斯滤波改进为自适应中值滤波结合小波变换，并提出了一种基于OKG算法的二次特征匹配方法。该算法首先使用自适应中值滤波结合小波变换算法对图像进行平滑和降噪处理，再进行初步特征点提取和匹配，然后将构建的尺度空间划分成多个网格，在每个网格内使用FAST算法提取尺度空间特征点，使用ORB算子提取左右图像的特征点，用BRIEF描述子对其进行描述，采用K-D树最近邻搜索法限制特征点选取，通过GMS算法剔除误匹配点。最后，将本文SURF-OKG算法与传统特征匹配算法进行对比分析，并对阶梯块进行三维重建来验证本文算法的有效性。实验结果表明：SURF-OKG算法的正确匹配率为92.47%；对阶梯宽度为40 mm，精度为0.02 mm的阶梯块进行三维重建，实验测得阶梯宽度的误差均值为1.312 mm，最大误差值不超过1.72 mm，基本满足结构光三维重建系统的实验要求。

Abstract

To address issues such as incorrect feature point matching， missing matches， and duplicate matches in the traditional stereo matching of structured light-based 3D reconstruction， this study introduced enhancements to the Gaussian filtering in the SURF algorithm through the integration of adaptive median filtering with wavelet transform. Additionally， a secondary feature matching approach based on the OKG algorithm was proposed. The proposed algorithm first employed adaptive median filtering in conjunction with the wavelet transform algorithm to achieve image smoothing and noise reduction. Subsequently， preliminary feature point extraction and matching were performed. The scale space was then divided into multiple grids. Within each grid， the FAST algorithm was employed to extract scale space feature points， the ORB operator was utilized to extract feature points from the left and right images， and these points were described using BRIEF descriptors. The K-D tree nearest neighbor search method was applied to constrain feature point selection， and the GMS algorithm was utilized to eliminate mismatches. Finally， a comparative analysis was conducted between the SURF-OKG algorithm proposed in this paper and traditional feature matching algorithms. The effectiveness of the proposed algorithm was verified through the 3D reconstruction of step blocks. Experimental results reveal that the correct matching rate of the SURF-OKG algorithm is 92.47%. In the case of step blocks with a width of 40 mm and an accuracy of 0.02 mm， the mean error in width measurement is 1.312 mm， with no maximum error exceeding 1.72 mm， meeting the experimental requirements of the structured light 3D reconstruction system.

关键词

三维重建特征点匹配SURF算法SURF-OKG算法阶梯块

Keywords

3D reconstructionfeature point matchingSpeeded-Up Robust Feature(SURF) algorithmSURF-OKG algorithmstep blocks

references

LV S Z， TANG D W， ZHANG X J， et al. Fringe projection profilometry method with high efficiency， precision， and convenience： theoretical analysis and development［J］. Optics Express， 2022， 30（19）： 33515-33537. doi: 10.1364/oe.467502http://dx.doi.org/10.1364/oe.467502

LOWE D G. Distinctive image features from scale-invariant keypoints［J］. International Journal of Computer Vision， 2004， 60（2）： 91-110. doi: 10.1023/b:visi.0000029664.99615.94http://dx.doi.org/10.1023/b:visi.0000029664.99615.94

BAY H， TUYTELAARS T， VAN GOOL L. SURF： Speeded up Robust Features［M］. Computer Vision – ECCV 2006. Berlin， Heidelberg： Springer Berlin Heidelberg， 2006： 404-417. doi: 10.1007/11744023_32http://dx.doi.org/10.1007/11744023_32

RUBLEE E， RABAUD V， KONOLIGE K， et al. ORB： an efficient alternative to SIFT or SURF［C］. 2011 International Conference on Computer Vision. Barcelona， Spain. IEEE， 2011： 2564-2571. doi: 10.1109/iccv.2011.6126544http://dx.doi.org/10.1109/iccv.2011.6126544

ALCANTARILLA P， NUEVO J， BARTOLI A. Fast explicit diffusion for accelerated features in nonlinear scale spaces［C］. Proceedings of the British Machine Vision Conference 2013. Bristol. British Machine Vision Association， 2013： 1281-1298. doi: 10.5244/c.27.13http://dx.doi.org/10.5244/c.27.13

BIAN J W， LIN W Y， LIU Y， et al. GMS： grid-based motion statistics for fast， ultra-robust feature correspondence［J］. International Journal of Computer Vision， 2020， 128（6）： 1580-1593. doi: 10.1007/s11263-019-01280-3http://dx.doi.org/10.1007/s11263-019-01280-3

刘明珠，陈瑞，陈俊羽，等. B-Spline-ORB特征点提取算法［J］. 哈尔滨理工大学学报， 2022， 27（3）： 97-104.

LIU M Z， CHEN R， CHEN J Y， et al. B-spline-ORB feature point extraction algorithm［J］. Journal of Harbin University of Science and Technology， 2022， 27（3）： 97-104.（in Chinese）

张龙，郑灿. 基于SURF和RANSAC的改进目标识别算法［J］. 中国设备工程， 2022（23）： 140-143. doi: 10.3969/j.issn.1671-0711.2022.23.060http://dx.doi.org/10.3969/j.issn.1671-0711.2022.23.060

ZHANG L， ZHENG C. Improved target recognition algorithm based on SURF and RANSAC［J］. China Plant Engineering， 2022（23）： 140-143.（in Chinese）. doi: 10.3969/j.issn.1671-0711.2022.23.060http://dx.doi.org/10.3969/j.issn.1671-0711.2022.23.060

刘惠中，余华富，彭志龙. 基于改进GMS特征匹配算法的浮选泡沫移动速度特征提取［J］. 计算机科学， 2022， 49（S2）： 585-590. doi: 10.11896/jsjkx.211000064http://dx.doi.org/10.11896/jsjkx.211000064

LIU H Z， YU H F， PENG Z L. Feature extraction of flotation foam moving speed based on improved GMS feature matching algorithm［J］. Computer Science， 2022， 49（S2）： 585-590.（in Chinese）. doi: 10.11896/jsjkx.211000064http://dx.doi.org/10.11896/jsjkx.211000064

朱世宇，陈志华. 基于改进运动网格统计的特征匹配算法［J］. 电光与控制， 2023， 30（7）： 51-56. doi: 10.3969/j.issn.1671-637X.2023.07.009http://dx.doi.org/10.3969/j.issn.1671-637X.2023.07.009

ZHU S Y， CHEN Z H. A feature matching algorithm based on improved GMS［J］. Electronics Optics & Control， 2023， 30（7）： 51-56.（in Chinese）. doi: 10.3969/j.issn.1671-637X.2023.07.009http://dx.doi.org/10.3969/j.issn.1671-637X.2023.07.009

李华，杨杨，陈雨杰. 基于非线性各向异性滤波的图像特征匹配算法［J/OL］.中国空间科学技术：1-9［2023-05-06］.

LI H， YANG Y， CHEN Y J. Image feature matching algorithm based on nonlinear anisotropic filtering［J/OL］. China Space Science and Technology： 1-9 ［2023-05-06］. （in Chinese）

赵明富，曹利波，宋涛，等. 针对间断纹理环境中的图像特征追踪和匹配算法研究［J］. 半导体光电， 2020， 41（1）： 128.

ZHAO M F， CAO L B， SONG T， et al. Research on image feature tracking and matching algorithms in intermittent texture environment［J］. Semiconductor Optoelectronics， 2020， 41（1）： 128.（in Chinese）

魏利波. 无人机视觉导航图像配准技术研究［D］. 沈阳：沈阳大学， 2022.

WEI L B. Research on Image Registration Technology of UAV Visual Navigation［D］. Shenyang： Shenyang University， 2022. （in Chinese）

何佳华，申冲，唐军，等. 基于改进ORB-GMS-SPHP算法的快速图像拼接方法［J］. 导航定位与授时， 2023， 10（2）： 108-116.

HE J H， SHEN C， TANG J， et al. Fast image mosaic method based on improved ORB-GMS-SPHP algorithm［J］. Navigation Positioning and Timing， 2023， 10（2）： 108-116.（in Chinese）

刘舜，卢洪义，张维维，等. 固体发动机实际成型药柱燃面退移快速算法［J］. 北京航空航天大学学报， 2023， 49（11）： 3115-3123.

LIU S， LU H Y， ZHANG W W， et al. Fast algorithm for grain burnback of actually shaped grains of solid motor［J］. Journal of Beijing University of Aeronautics and Astronautics， 2023， 49（11）： 3115-3123.（in Chinese）

崔建国，孙长库，李玉鹏，等. 基于SURF的快速图像匹配改进算法［J］. 仪器仪表学报， 2022， 43（8）： 47-53.

CUI J G， SUN C K， LI Y P， et al. An improved algorithm for fast image matching based on SURF［J］. Chinese Journal of Scientific Instrument， 2022， 43（8）： 47-53.（in Chinese）

杨昭辉，朱华炳，殷玉龙，等. 基于编码立体靶标的高精度双目相机标定［J］. 中国激光， 2023， 50（6）： 3788/CJL220523. doi: 10.3788/CJL220523http://dx.doi.org/10.3788/CJL220523

YANG Z H， ZHU H B， YIN Y L， et al. High-precision binocular camera calibration based on coding stereoscopic target［J］. Chinese Journal of Lasers， 2023， 50（6）： 3788/CJL220523.（in Chinese）. doi: 10.3788/CJL220523http://dx.doi.org/10.3788/CJL220523

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Review of multi-view stereo reconstruction methods based on deep learning

Fine 3D reconstruction methods with Gaofen-7 satellite stereo images

Research on 3D reconstruction of microscope imaging based on Harris-SIFT algorithm and full convolution depth prediction

Single-view 3D object reconstruction based on NFFD and graph convolution

Three-dimensional porous structure reconstruction for low-resolution monocular endoscopic images

Related Author

LIN Chuxin

LIU Cibo

HUANG Lü'er

XU Fangqi

YAN Huabiao

ZHANG Wei

HAN Yilong

LIU Songlin

Related Institution

School of Electrical Engineering and Automation，Jiangxi University of Science and Technology

School of Science， Jiangxi University of Science and Technology

Research Center of Engineering and Technology for "3S"-GPS， RS and GIS， Shandong University of Science and Technology

College of Geodesy and Geomatics， Shandong University of Science and Technology

Xi'an Research Institute of Surveying and Mapping

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰