Abstract
The feature matching algorithm based on deep learning has achieved superior performance compared to traditional algorithms in terms of both matching quantity and accuracy, but there are still some high-error matching results in complex scenes, which adversely affects the subsequent work. Based on SuperGlue, we propose an accurate feature matching algorithm via outlier filtering. Firstly, DBSCAN real-time superpixel segmentation (RTSS-DBSCAN) is used to divide the image into regions, and then the outlier filtering module is designed according to the local similarity principle of feature matching. On the premise of not affecting the correct matching results, the matching results with high errors will be filtered to improve the matching accuracy. Meanwhile, due to the lag of traditional Exponential Moving Average algorithm (EMA), an adaptive EMA is designed and integrated into the SuperGlue training process to further improve the training speed and matching accuracy. We evaluate the overall performance of the matching method using the AUC of pose error at the thresholds (5°, 10°, 20°), a common evaluation metric, to provide a more detailed and intuitive evaluation of the matching effectiveness using precision and recall. The experimental results show that the method in this paper can effectively filter the matching results with large errors and has high accuracy and robustness. The AUC of pose error at thresholds (5°, 10°, 20°) reaches 36.53, 56.23, and 73.68, and the precision and recall reach 80.07 and 91.52, respectively, which have better matching results compared with other algorithms.
Similar content being viewed by others
Availability of data and materials
The datasets used or analyzed during the current study are available from the corresponding author on reasonable request.
Code availability
The codes used during the current study are available from the corresponding author on reasonable request.
References
Ma, J., Jiang, X., Fan, A., et al.: Image matching from handcrafted to deep features: a survey. Int. J. Comput. Vis. 129, 23–79 (2021). https://doi.org/10.1007/s11263-020-01359-2
Campos, C., Elvira, R., Rodríguez, J.J.G., et al.: Orb-slam3: an accurate open-source library for visual, visual–inertial, and multimap slam. IEEE Trans. Robot. 37(6), 1874–1890 (2021)
He, M., Zhu, C., Huang, Q., et al.: A review of monocular visual odometry. Vis. Comput. 36, 1053–1065 (2020). https://doi.org/10.1007/s00371-019-01714-6
Fu, Y., Yan, Q., Liao, J., et al.: Real-time dense 3D reconstruction and camera tracking via embedded planes representation. Vis. Comput. 36, 2215–2226 (2020). https://doi.org/10.1007/s00371-020-01899-1
Cai, Y., Li, L., Wang, D., et al.: GlcMatch: global and local constraints for reliable feature matching. Vis. Comput. (2022). https://doi.org/10.1007/s00371-022-02478-2
Balntas, V., Riba, E., Ponsa, D., et al.: Learning local feature descriptors with triplets and shallow convolutional neural networks. Bmvc. 1(2), 3 (2016)
Demarche, C., Harari, D.: Duality for complexes of tori over a global field of positive characteristic. Journal de l’École Polytechnique-Mathématiques 7, 831–870 (2020)
Corso, M.P., Perez, F.L., Stefenon, S.F., et al.: Classification of contaminated insulators using k-nearest neighbors based on computer vision. Computers 10(9), 112 (2021). https://doi.org/10.3390/computers10090112
Georgiou, T., Liu, Y., Chen, W., et al.: A survey of traditional and deep learning-based feature descriptors for high dimensional data in computer vision. Int. J. Multimed. Info. Retr. 9, 135–170 (2020). https://doi.org/10.1007/s13735-019-00183-w
Ma, S., Guo, P., You, H., et al.: An image matching optimization algorithm based on pixel shift clustering RANSAC. Inf. Sci. 562, 452–474 (2021). https://doi.org/10.1016/j.ins.2021.03.023
Rahman, M., Li, X., Yin, X.: DL-RANSAC: An improved RANSAC with modified sampling strategy based on the likelihood. In: 2019 IEEE 4th International Conference on Image, Vision and Computing (ICIVC). IEEE, pp. 463–468 (2019)
Sarlin, P, E., DeTone, D., Malisiewicz, T. et al.: Superglue: Learning feature matching with graph neural networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4938–4947 (2020). https://doi.org/10.1109/CVPR42600.2020.00499
Chen, H., Luo, Z., Zhang, J. et al.: Learning to match features with seeded graph matching network. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6301–6310 (2021). https://doi.org/10.1109/ICCV48922.2021.00624
Shi, Y., Cai, J, X., Shavit, Y. et al.: ClusterGNN: Cluster-based coarse-to-fine graph neural network for efficient feature matching. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12517–12526 (2022). https://doi.org/10.1109/CVPR52688.2022.01219
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. (2017). https://doi.org/10.48550/arXiv.1706.03762
Sinaga, K.P., Yang, M.S.: Unsupervised K-means clustering algorithm. IEEE Access. 8, 80716–80727 (2022). https://doi.org/10.1109/ACCESS.2020.2988796
Zhang, H., Goodfellow, I., Metaxas, D. et al.: Self-attention generative adversarial networks. In: International Conference on Machine Learning. PMLR, pp. 7354–7363 (2019). https://doi.org/10.48550/arXiv.1805.08318
Gadipudi, N., Elamvazuthi, I., Izhar, L.I., et al.: A review on monocular tracking and mapping: from model-based to data-driven methods. Vis. Comput. (2022). https://doi.org/10.1007/s00371-022-02702-z
Toft, C., Maddern, W., Torii, A., et al.: Long-term visual localization revisited. IEEE Trans. Pattern Anal. Mach. Intell. 44(4), 2074–2088 (2020). https://doi.org/10.1109/TPAMI.2020.3032010
Chen, C., Wang, B., Lu, C.X. et al.: A survey on deep learning for localization and mapping: Towards the age of spatial machine intelligence. arXiv preprint. (2020). https://doi.org/10.48550/arXiv.2006.12567
Carrasco, M., Barbot, A.: Spatial attention alters visual appearance. Curr. Opin. Psychol. 29, 56–64 (2019). https://doi.org/10.1016/j.copsyc.2018.10.010
Shi, W., Rajkumar, R.: Point-gnn: Graph neural network for 3D object detection in a point cloud. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1711–1719 (2020). https://doi.org/10.48550/arXiv.2003.01251
Luo, H., Li, L., Zhang, Y., et al.: Link prediction in multiplex networks using a novel multiple-attribute decision-making approach. Knowl. Based Syst. 219, 106904 (2021). https://doi.org/10.1016/j.knosys.2021.106904
Ngo, D., Lee, S., Kang, B.: Robust single-image haze removal using optimal transmission map and adaptive atmospheric light. Remote Sens. 12(14), 2233 (2020). https://doi.org/10.3390/rs12142233
Chizat, L., Roussillon, P., Léger, F., et al.: Faster Wasserstein distance estimation with the Sinkhorn divergence. Adv. Neural Inf. Process. Syst. 33, 2257–2269 (2020)
DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperPoint: self-supervised interest point detection and description. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). (2018). https://doi.org/10.48550/arXiv.1712.07629
Viniavskyi, O., Dobko, M., Mishkin, D. et al.: Openglue: Open source graph neural net based pipeline for image matching. arXiv preprint. (2022). https://doi.org/10.48550/arXiv.2204.08870
Bian, J., Lin, W, Y., Matsushita, Y. et al.: GMS: grid-based motion statistics for fast, ultra-robust feature correspondence. In: IEEE Conference on Computer Vision & Pattern Recognition. IEEE. (2017). https://doi.org/10.1109/CVPR.2017.302
Xu, Q., Zeng, Y., Tang, W., et al.: Multi-task joint learning model for segmenting and classifying tongue images using a deep neural network. IEEE J. Biomed. Health Inform. 24(9), 2481–2489 (2020). https://doi.org/10.1109/JBHI.2020.2986376
Deng, D.: DBSCAN clustering algorithm based on density. In: 2020 7th IEEE International Forum on Electrical Engineering and Automation (IFEEA), pp 949–953 (2020). https://doi.org/10.1109/IFEEA51475.2020.00199
Shen, J., Hao, X., Liang, Z., et al.: Real-Time Superpixel Segmentation by DBSCAN Clustering Algorithm[J]. IEEE Trans. Image Process. 25(12), 5933–5942 (2016). https://doi.org/10.1109/TIP.2016.2616302
Van den Bergh, M., Boix, X., Roig, G., et al.: SEEDS: superpixels extracted via energy-driven sampling. Int. J. Comput. Vis. 111, 298–314 (2015). https://doi.org/10.1007/s11263-014-0744-2
Achanta, R., Shaji, A., Smith, K., et al.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012). https://doi.org/10.1109/TPAMI.2012.120
Li, Z., Chen, J.: Superpixel segmentation using linear spectral clustering. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE. (2015). https://doi.org/10.1109/CVPR.2015.7298741
Zhang, Y., Hartley, R.I., Mashford, J. et al.: Superpixels via pseudo-Boolean optimization. In: IEEE International Conference on Computer Vision. (2012). https://doi.org/10.1109/ICCV.2011.6126393
Liu, M.Y., Tuzel, O., Ramalingam, S. et al.: Entropy rate superpixel segmentation. In: The 24th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011, pp 20–25 (2011). https://doi.org/10.1109/CVPR.2011.5995323
Shen, J., Du, Y., Wang, W., et al.: Lazy random walks for superpixel segmentation. IEEE Trans. Image Process. 23(4), 1451–1462 (2014). https://doi.org/10.1109/TIP.2014.2302892
Lin, TY. et al. (2014). Microsoft COCO: Common Objects in Context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds) Computer Vision–ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol 8693. Springer, Cham. https://doi.org/10.1007/978-3-319-10602-1_48
Funding
This work was partially supported by China Postdoctoral Science Foundation (Grant No. 2021M702030) and Shandong Provincial Transportation Science and Technology Project (Grant No. 2021B120).
Author information
Authors and Affiliations
Contributions
WH contributed significantly to analysis and wrote the manuscript, PW contributed to the conception of the study, CN and GZ contributed to performed the data analyses and manuscript preparation, and WH performed the experiment.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that there is no conflict of interests or competing interests regarding the publication of this article.
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
The work described has not been published before, and its publication has been approved by the responsible authorities at the institution where the work is carried out.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Hao, W., Wang, P., Ni, C. et al. SuperGlue-based accurate feature matching via outlier filtering. Vis Comput 40, 3137–3150 (2024). https://doi.org/10.1007/s00371-023-03015-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-023-03015-5