Due to the low matching accuracy and efficiency of the chessboard caused by its similar feature points in binocular vision measurement, this study proposes a matching method based on homography matrix. Inner corner points of the chessboard are utilized to generate a homography matrix, with similarity evaluated through a cost matrix and optimized using the Hungarian algorithm to achieve optimal matching feature points, effectively addressing feature point confusion. Compared with other chessboard feature matching methods, higher accuracy and efficiency are demonstrated. The homography matrix-based method ensures strong pose robustness by maintaining stable feature matching across varied chessboard and camera poses, adapting to complex positional changes. The feature matching method is applied to visual vibration measurement using dual measurement points, successfully identifying the vibration characteristics of the beam with high precision and reliability. A theoretical basis and technical support are provided for non-contact health inspection of structures, advancing vibration monitoring in large-scale structural applications.
LvYZhouLLiuZ, et al. Structural vibration frequency monitoring based on event camera. Meas Sci Technol2024; 35: 085007.
2.
YeXWDongCZ. Review of computer vision-based structural displacement monitoring. China J Highw Transp2019; 32: 20–39.
3.
DongCZCatbasFN. A review of computer vision–based structural health monitoring at local and global levels. Struct Health Monit2021; 20: 692–743.
4.
Arellano-GonzálezJCMedellín-CastilloHICervantes-SánchezJJ, et al. Assessment of computer vision methods for motion tracking of planar mechanisms. Proc Inst Mech Eng Part C-J Eng Mech Eng Sci2022; 236: 4093–4104.
5.
BhowmickSNagarajaiahSLaiZ. Measurement of full-field displacement time history of a vibrating continuous edge from video. Mech Syst Signal Process2020; 144: 106847.
6.
ChenLZhongGHanZ, et al. Binocular visual dimension measurement method for rectangular workpiece with a precise stereoscopic matching algorithm. Meas Sci Technol2023; 34: 035010.
7.
WangXHeZLiuJ, et al. Binocular vision vibration measurement based on pixel coordinate matching of inner corner points in a chequerboard. OR Insight2023; 65: 551–558.
8.
LiHZhangB. Application of integrated binocular stereo vision measurement and wireless sensor system in athlete displacement test. Alex Eng J2021; 60: 4325–4335.
9.
DengHXWangJZhangJ, et al. A stereovision measurement for large deformation of light structures. Measurement2019; 136: 387–394.
10.
TangYCLiLJFengWX, et al. Binocular vision measurement and its application in full-field convex deformation of concrete-filled steel tubular columns. Measurement2018; 130: 372–383.
11.
JiangSYouKLiY, et al. 3D reconstruction of spherical images: a review of techniques, applications, and prospects. Geo Spatial Inf Sci2024; 27: 1959–1988.
12.
LiuYGaoXLiZ. Remote sensing image feature matching via graph classification with local motion consistency. Int J Digit Earth2024; 17: 2308713.
13.
MaJJiangXFanA, et al. Image matching from handcrafted to deep features: A survey. Int J Comput Vis2021; 129: 23–79.
14.
LiuZShaoF. Feature point matching based on multi-scale local relative motion consistency. IEEE Access2023; 11: 124845–124854.
15.
ChaiYCaoX. Stereo matching algorithm based on joint matching cost and adaptive window. In: 2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)2018 October, pp. 442–446. IEEE.
16.
PaulSDUNaiduY, et al. An efficient SIFT-based matching algorithm for optical remote sensing images. Remote Sens Lett2022; 13: 1069–1079.
17.
DongCZCatbasFN. A non-target structural displacement measurement method using advanced feature matching strategy. Adv Struct Eng2019; 22: 3461–3472.
18.
EtezadifarPFarsiH. A new sample consensus based on sparse coding for improved matching of SIFT features on remote sensing images. IEEE Trans Geosci Remote Sens2020; 58: 5254–5263.
19.
DuWLeiDHangZ, et al. Short-distance and long-distance bridge displacement measurement based on template matching and feature detection methods. J Civ Struct Health Monit2023; 13: 343–360.
20.
LiZXuZYuD, et al. Vision-based super large-span suspension bridge displacement measurement method with enhanced super-resolution and Speeded-Up robust features. Measurement2025; 255: 118077.
21.
ParkJWKimYTShinDK. Feature points matching based on the condition of triangle similarity. J Korean Inst Inform Technol2010; 8: 91–100.
22.
DongYFanDMaQ, et al. Image feature matching via parallax mapping for close range photogrammetric application. IEEE Access2020; 8: 32601–32616.
23.
XieZYangC. Binocular visual measurement method based on feature matching. Sensors2024; 24: 1807.
24.
TangZZhangZFengJ, et al. A fast image stitching algorithm based on texture classification and improved SIFT. IEEE Access2024; 12: 124183–124208.
25.
BeiyiWXiaohongZWeibingW. Feature matching method based on SURF and fast library for approximate nearest neighbor search. Integr Ferroelectr2021; 218: 147–154.
26.
HanLWangJZhangY, et al. Research on adaptive ORB-SURF image matching algorithm based on fusion of edge features. IEEE Access2022; 10: 109488–109497.
27.
ZhangDYangGYuG, et al. ORB-SLAM3 and dense mapping algorithm based on improved feature matching. Signal Process2025; 137: 117322.
28.
LiuXLiQHuY, et al. Feature-matching method based on keypoint response constraint using binary encoding of phase congruency. Pattern Recognit2025; 159: 111078.
29.
ZhangHWuSLuoX, et al. Efficient matching of transformer-enhanced features for accurate vision-based displacement measurement. Autom Constr2025; 171: 105962.
30.
ZhangZY. A flexible new technique for camera calibration. IEEE Trans Pattern Anal Mach Intell2000; 22: 1330–1334.
31.
WangYRuiJZhangX, et al. Method for online matching of multiple identical targets using local homography matrix based on moving DLT. Meas Sci Technol2022; 33: 055009.
32.
JiangBDuXWuL, et al. Visual measurement of the bearing diameter based on the homography matrix and partial area effect. Proc Inst Mech Eng Part C-J Eng Mech Eng Sci2024; 238: 2034–2043.
33.
ChengXLiuZZengZ, et al. Precise camera calibration method based on eccentricity correction of circular target. Meas Sci Technol2025; 36: 035007.
34.
LiuJLiangAZhaoE, et al. Homography matrix-based local motion consistent matching for remote sensing images. Remote Sens2023; 15: 3379.
35.
JoBWLeeYSJoJH, et al. Computer vision-based bridge displacement measurements using rotation-invariant image processing technique. Sustainability2018; 10: 1785.
36.
WangYPengLLiWT, et al. Research on loaded frequency for simply supported bridge. J Shanghai Normal Univ (Nat Sci)2021; 50: 433–440.
