Abstract
Incorporating correspondences geometric consistency constraints into feature mismatch removal is known to enable robust matching. Most existing methods often take a long computational time or have high requirements for equipment, limiting their use in real-time applications. This paper attempts to remove the mismatches from the putative correspondence set at high speed. We propose a dynamic-scale grid structure into the mismatch removal stage to reduce the time complexity of neighborhood construction. We use descriptor size to simulate the relative scale between two images, then make the grid structure scale dynamic. Furthermore, we put forward a Gaussian-based weighted scoring strategy to combine the descriptor matching stability with geometric consistency. This strategy uses a Gaussian function to give each putative correspondence a different stability score, making the model more robust in complex scenarios. Finally, compared with other real-time or sophisticated models, our model achieves better performance and intensively reduces time cost.
Similar content being viewed by others
References
Sturm J, Engelhard N, Endres F, Burgard W, Cremers D (2012) A benchmark for the evaluation of RGB-D SLAM systems. In: 2012 IEEE/RSJ international conference on intelligent robots and systems. https://doi.org/10.1109/iros.2012.6385773
Geiger A, Lenz P, Urtasun R (2012) Are we ready for autonomous driving? the kitti vision benchmark suite. In: 2012 IEEE conference on computer vision and pattern recognition. https://doi.org/10.1109/cvpr.2012.6248074
Knapitsch A, Park J, Zhou Q -Y, Koltun V (2017) Tanks and temples: benchmarking Large-Scale scene reconstruction. ACM Transactions on Graphics 36:78. https://doi.org/10.1145/3072959.3073599
Wilson K, Snavely N (2014) Robust global translations with 1dsfm. In: European Conference on Computer Vision. https://doi.org/10.1007/978-3-319-10578-9_5
Pauline C N, Steven H (2003) SIFT: Predicting amino acid changes that affect protein function. Nucleic Acids Research 31:3812–3814. https://doi.org/10.1093/nar/gkg509
Bian J, Lin W, Liu Y, Zhang L, Yeung S, Cheng M, Reid L (2020) GMS: Grid-based motion statistics for fast, ultra-robust feature correspondence. Int J Comput Vis 128(6):1580–1593. https://doi.org/10.1007/s11263-019-01280-3
Ma J, Jiang X, Jiang J, Zhao J, Guo X (2019) LMR: Learning a Two-Class classifier for mismatch removal. IEEE Trans Image Process 2:4045–4059. https://doi.org/10.1109/TIP.2019.2906490
Ma J, Zhao J, Jiang J, Zhou H, Guo X (2019) Locality preserving matching. Int J Comput Vis 127:512–531. https://doi.org/10.24963/ijcai.2017/627
Liu Y, Li Y, Dai L, Yang C, Wei L, Lai T, Chen R (2021) Robust feature matching via advanced neighborhood topology consensus. Neurocomputing 421:273–284. https://doi.org/10.1016/j.neucom.2020.09.047
Sarlin P-E, DeTone D, Malisiewicz T, Rabinovich A (2020) Superglue: Learning feature matching with graph neural networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. https://doi.org/10.1109/cvpr42600.2020.00499
Morel J-M, Yu GJSjois (2009) . ASIFT: A new framework for fully affine invariant image comparison 2:438–469. https://doi.org/10.1137/080732730
Mainali P, Lafruit G, Yang Q, Geelen B, Van Gool L, Lauwereins R (2013) SIFER: Scale-invariant feature detector with error resilience. Int J Comput Vis 104:172–197. https://doi.org/10.1007/s11263-013-0622-3
Rublee E, Rabaud V, Konolige K, Bradski G (2012) ORB: An efficient alternative to SIFT or SURF. In: International Conference on Computer Vision. https://doi.org/10.1109/iccv.2011.6126544
Aldana-Iuit J, Mishkin D, Chum O, Matas J (2016) In the saddle: chasing fast and repeatable features. In: 2016 23rd International Conference on Pattern Recognition (ICPR)
DeTone D, Malisiewicz T, Rabinovich A (2018) SuperPoint: Self-supervised interest point detection and description. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops. https://doi.org/10.1109/cvprw.2018.00060
Bhowmik A, Gumhold S, Rother C, Brachmann E (2020) Reinforced feature points: Optimizing feature detection and description for a high-level task. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. https://doi.org/10.1109/cvpr42600.2020.00500
Dai J, Jin S, Zhang J, Nguyen T Q (2020) Boosting feature matching accuracy with pairwise affine estimation. IEEE Trans Image Process 29:8278–8291. https://doi.org/10.1109/tip.2020.3013384
Wang C, Wang L, Liu L (2014) Progressive mode-seeking on graphs for sparse feature matching. In: European conference on computer vision. https://doi.org/10.1007/978-3-319-10605-2_51
FM A, Bolles R C (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 26(6):381–395. https://doi.org/10.1016/b978-0-08-051581-6.50070-2
Fragoso V, Sen P, Rodriguez S, Turk M (2013) EVSAC: accelerating hypotheses generation by modeling matching scores with extreme value theory. In: Proceedings of the IEEE international conference on computer vision. https://doi.org/10.1109/iccv.2013.307
Barath D, Ivashechkin M, Japa MJ (2019) Progressive NAPSAC: sampling from gradually growing neighborhoods. arXiv:1906.022951906.02295
Ma J, Jiang X, Fan A, Jiang J, Yan JJIJoCV (2021) . Image matching from handcrafted to deep features: A survey 129:23–79. https://doi.org/10.1007/s11263-020-01359-2
Leordeanu M, Hebert M (2005) A spectral technique for correspondence problems using pairwise constraints. In: Tenth IEEE international conference on computer vision. https://doi.org/10.1109/ICCV.2005.20
Liu H, Yan S (2010) Common visual pattern discovery via spatially coherent correspondences. In: 2010 IEEE computer society conference on computer vision and pattern recognition. https://doi.org/10.1109/cvpr.2010.5539780
Lin W-YD, Cheng M-M, Lu J, Yang H, Do MN, Torr P (2014) Bilateral functions for global motion modeling. European conference on computer vision. https://doi.org/10.1007/978-3-319-10593-2_23
Lin W, Wang F, Cheng M, Yeung S, Torr P H S, Do M N, Lu J (2018) CODE: coherence based decision boundaries for feature correspondence. IEEE Trans Pattern Anal Mach Intell 40:34–47. https://doi.org/10.1109/tpami.2017.2652468
Bian J, Lin W, Matsushita Y, Yeung S-K, Nguyen T-D, Cheng M (2017) GMS: Grid-based motion statistics for fast, ultra-robust feature correspondence. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). https://doi.org/10.1109/cvpr.2017.302
Wang G, Chen Y (2021) Robust feature matching using guided local outlier factor. Pattern Recogn 117:107986. https://doi.org/10.1016/j.patcog.2021.107986
Sun J, Shen Z, Wang Y, Bao H, Zhou X (2021) LoFTR: Detector-free local feature matching with transformers. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition
Zhou Q, Sattler T, Leal-Taixe L (2021) Patch2pix: Epipolar-guided pixel-level correspondences. In: Proceedings of the IEEE/ CVF conference on computer vision and pattern recognition
Moore A (1991) An introductory tutorial on kd-trees. IEEE colloquium on quantum computing: theory, applications & implications
Beis JS, Lowe DG (1997) Shape indexing using approximate nearest-neighbour search in high-dimensional spaces. Proceedings of IEEE computer society conference on computer vision and pattern recognition. https://doi.org/10.1109/cvpr.1997.609451
Muja M, Lowe D (2009) Flann: Fast library for approximate nearest neighbors user manual. Computer Science Department 5 https://doi.org/10.1109/icscn.2017.8085676
Li Y, Huang Q, Liu Y, Huang Y, Sun X (2019) Robust feature matching via multi-scale grid structure. In: 2019 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA/BDCloud/ SocialCom/SustainCom). https://doi.org/10.1109/ispa-bdcloud-sustaincom-socialcom48970.2019.00169
Zheng Z, Ma Y, Zheng H, Ju J, Lin MJIA (2018) . UGC: Real-time, ultra-robust feature correspondence via unilateral grid-based clustering 6:55501–55508. https://doi.org/10.1109/access.2018.2871729
Bian J, Wu Y, Zhao J, Liu Y, Zhang L, Cheng M, Reid L (2019) An evaluation of feature matchers for fundamental matrix estimation. British machine vision conference (BMVC)
Jin Y, Mishkin D, Mishchuk A, Matas J, Fua P, Yi K M, Trulls E (2021) Image matching across wide baselines: from paper to practice. Int J Comput Vis 129:517–547. https://doi.org/10.1007/s11263-020-01385-0
Sloane NJA (2001) Information Sciences Research Center, AT&T Shannon Labs http://neilsloane.com/oadir/
Acknowledgment
This work is partly supported by the National Key Research and Development Program of China under grant no. 2018YFC0407905, and the fundamental research funds of China for central universities under grant no. B200202188.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Yang, L., Huang, Q., Li, X. et al. Dynamic-scale grid structure with weighted-scoring strategy for fast feature matching. Appl Intell 52, 10576–10590 (2022). https://doi.org/10.1007/s10489-021-02990-3
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-021-02990-3