Abstract
Cross view images matching and registration is to extract the images features from different views of the same scene, and measure the similarity between features by measuring the correspondence between images, then perform pixel-level registration. Cross-view images have problems such as poor stability of feature points and big difference in scale, resulting in low efficiency of matching and registration using traditional methods. In this paper, a novel image matching method based on deep learning is adopted. Firstly, a convolutional neural network is utilized for image matching to achieve the initial selection of the target, and then the pixel level registration is carried out for the successfully matched images. Considering the problem of small samples, four feature extraction networks are used for feature extraction to achieve knowledge transfer. In the aspect of image registration, considering the difference between feature descriptors and baselines of cross view images, deep learning is introduced to improve the traditional algorithm to achieve accurate registration.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Tsai, C.H., Lin, Y.C.: An accelerated image matching technique for UAV orthoimage registration. ISPRS J. Photogramm. Remote. Sens. 128, 130–145 (2017)
Ding, L., et al.: A practical cross-view image matching method between UAV and satellite for UAV-based geo-localization. Remote Sensing 13(1), 47 (2020)
Lv, G.: Self-similarity and symmetry with SIFT for multi-modal image registration. IEEE Access 7, 52202–52213 (2019)
Sreeja, G., Saraniya, O.: A comparative study on image registration techniques for SAR images. In: 2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS). IEEE (2019)
Luo, S., Zhou, H.-M., Xu, J.-H., Zhang, S.-Y.: Matching images based on consistency graph and region adjacency graphs. SIViP 11(3), 501–508 (2016). https://doi.org/10.1007/s11760-016-0987-1
Ansari, S.: A review on SIFT and SURF for underwater image feature detection and matching. In: 2019 IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT). IEEE (2019)
Moon, C.H., Lee, S.W.: Fast image-matching technique robust to rotation in spherical images. IEIE Trans. Smart Process. Comput. 9 (2020)
Zhang, B.B., Shu, H., Jiang, W.S.: Harris-SURF image matching algorithm constrained by delaunay triangulation. Geogr. Geo-Inform. Sci. (2019)
Zhuo, X., et al.: Automatic UAV image geo-registration by matching UAV images to georeferenced image data. Remote Sens. 9(4) (2017)
Hughes, L.H., et al.: Deep Learning for SAR-Optical Image Matching. IGARSS 2019 (2019)
Grewal, M., et al.: An end-to-end deep learning approach for landmark detection and matching in medical images. SPIE Med. Imaging (2020)
Memon, M.H., et al.: Localization in images matching through region-based similarity technique for content-based image retrieval. In: 2016 13th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP). IEEE (2017)
Feng, R., et al.: Robust registration for remote sensing images by combining and localizing feature-and area-based methods. ISPRS J. Photogramm. Remote Sens. 151, 15–26 (2019)
Zhou, M., et al.: Multi-sensor images registration based on SIFT and extended phase correlation. In: Twelfth International Conference on Digital Image Processing (2020)
Valmadre, J., et al.: End-to-end representation learning for correlation filter based tracking. IEEE (2017)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Santos, Fpd, Ponti, M. A.: Features transfer learning for image and video recognition tasks. In: Conference on Graphics, Patterns and Images (2020)
Liu, T, et al.: Deep learning and transfer learning for optic disc laterality detection: implications for machine learning in neuro-ophthalmology. J. Neuro-Ophthalmol. 40 (2020)
Li, X., et al.: Small-sample image classification method of combining prototype and margin learning. In: 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC). IEEE (2020)
Dixit, D., Tokekar, P.: Evaluation of Cross-View Matching to Improve Ground Vehicle Localization with Aerial Perception (2020)
Zhu, W., et al.: Investigation of transfer learning for image classification and impact on training sample size. Chemometr. Intel. Lab. Syst. 7639, 104269 (2021)
Schlett, T., Rathgeb, C., Busch, C.: Deep Learning-based Single Image Face Depth Data Enhancement (2020)
Bay, H., Tuytelaars, T., Gool, L.: SURF: Speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006). https://doi.org/10.1007/11744023_32
Wang, S., et al.: A deep learning framework for remote sensing image registration. ISPRS J. Photogramm. Remote Sens. 145, 148–164 (2018)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhou, Q., Zhu, R., Xu, Y., Zhang, Z. (2021). Cross-View Images Matching and Registration Technology Based on Deep Learning. In: Peng, Y., Hu, SM., Gabbouj, M., Zhou, K., Elad, M., Xu, K. (eds) Image and Graphics. ICIG 2021. Lecture Notes in Computer Science(), vol 12888. Springer, Cham. https://doi.org/10.1007/978-3-030-87355-4_60
Download citation
DOI: https://doi.org/10.1007/978-3-030-87355-4_60
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87354-7
Online ISBN: 978-3-030-87355-4
eBook Packages: Computer ScienceComputer Science (R0)