{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:14:39Z","timestamp":1776784479459,"version":"3.51.2"},"reference-count":50,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T00:00:00Z","timestamp":1748304000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>The homography matrix is essential for perspective transformation across consecutive video frames. While existing methods are effective when the visual content between paired images remains largely unchanged, they rely on substantial, high-quality annotated data for a multi-frame court sequence with content variation. To address this limitation and enhance homography matrix predictions in competitive sports images, a new symmetric stacked neural network model is proposed. The model first leverages the mutual invertibility of bidirectional homography matrices to improve prediction accuracy between paired images. Secondly, by theoretically validating and leveraging the decomposability of the homography matrix, the model significantly reduces the amount of data annotation required for continuous frames within the same shooting direction. Experimental evaluations on datasets for court homography transformations in sports, such as ice hockey, basketball, and handball, show that the proposed symmetric model achieves superior accuracy in predicting homography matrices, even when only one-third of the frames are annotated. Comparisons with seven related methods further highlight the exceptional performance of the proposed model.<\/jats:p>","DOI":"10.3390\/sym17060832","type":"journal-article","created":{"date-parts":[[2025,5,29]],"date-time":"2025-05-29T04:46:38Z","timestamp":1748493998000},"page":"832","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Symmetric Model for Predicting Homography Matrix Between Courts in Co-Directional Multi-Frame Sequence"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2860-7264","authenticated-orcid":false,"given":"Pan","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China"},{"name":"School of Artificial Intelligence, Neijiang Normal University, Neijiang 641100, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangtao","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xupeng","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Physical Education, Chongqing University of Posts and Telecommunications, Chongqing 400065, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,5,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1023\/A:1012471930694","article-title":"Self-Calibration of Rotating and Zooming Cameras","volume":"45","author":"Agapito","year":"2001","journal-title":"Int. J. Comput. Vis."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"106525","DOI":"10.1016\/j.optlaseng.2020.106525","article-title":"Calibration refinement for a fringe projection profilometry system based on plane homography","volume":"140","author":"Yu","year":"2021","journal-title":"Opt. Lasers Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.neucom.2021.03.099","article-title":"Image stitching via deep homography estimation","volume":"450","author":"Zhao","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1016\/j.neucom.2021.12.032","article-title":"Learning edge-preserved image stitching from multi-scale deep homography","volume":"491","author":"Nie","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1109\/TPAMI.2017.2760833","article-title":"Color Homography: Theory and Applications","volume":"41","author":"Finlayson","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhang, T., Zhu, D., Zhang, G., Shi, W., Liu, Y., Zhang, X., and Li, J. (2022, January 23\u201327). Spatiotemporally Enhanced Photometric Loss for Self-Supervised Monocular Depth Estimation. Proceedings of the 2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan.","DOI":"10.1109\/IROS47612.2022.9981595"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","article-title":"ORB-SLAM: A Versatile and Accurate Monocular SLAM System","volume":"31","author":"Montiel","year":"2015","journal-title":"IEEE Trans. Robot."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.1109\/TPAMI.2011.216","article-title":"Simultaneously Fitting and Segmenting Multiple-Structure Data with Outliers","volume":"34","author":"Wang","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2993","DOI":"10.1109\/TCSVT.2017.2731781","article-title":"A New Accurate and Fast Homography Computation Algorithm for Sports and Traffic Video Analysis","volume":"28","author":"Liu","year":"2018","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_10","first-page":"2849","article-title":"Content-Aware Unsupervised Deep Homography Estimation and its Extensions","volume":"45","author":"Liu","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_11","unstructured":"Murino, V., Castellani, U., Etrari, A., and Fusiello, A. (2002, January 22\u201325). Registration of very time-distant aerial images. Proceedings of the International Conference on Image Processing (ICIP), Rochester, NY, USA."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1023\/B:VISI.0000011204.89453.4d","article-title":"Multiple View Geometry of General Algebraic Curves","volume":"56","author":"Kaminski","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/MSP.2009.934181","article-title":"How the Hough transform was invented [DSP History]","volume":"26","author":"Hart","year":"2009","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1109\/TMM.2010.2100373","article-title":"Robust Camera Calibration and Player Tracking in Broadcast Basketball Video","volume":"13","author":"Hu","year":"2011","journal-title":"IEEE Trans. Multimed."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1007\/s11042-009-0434-1","article-title":"Camera calibration using court models for real-time augmenting soccer scenes","volume":"51","author":"Battikh","year":"2011","journal-title":"Multimed. Tools Appl."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/s100440170020","article-title":"Robust image mosaicing of soccer videos using self-calibration and line tracking","volume":"4","author":"Kim","year":"2001","journal-title":"Pattern Anal. Appl."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1109\/LSP.2023.3238274","article-title":"Deep Image Registration With Depth-Aware Homography Estimation","volume":"30","author":"Huang","year":"2023","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_18","unstructured":"DeTone, D., Malisiewicz, T., and Rabinovich, A. (2016). Deep image homography estimation. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_20","unstructured":"Derpanis, K. (2004). The Harris Corner Detector, York University."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vis."},{"key":"ref_22","unstructured":"Yan, K., and Sukthankar, R. (July, January 27). PCA-SIFT: A more distinctive representation for local image descriptors. Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), Washington, DC, USA."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","article-title":"Multiresolution gray-scale and rotation invariant texture classification with local binary patterns","volume":"24","author":"Ojala","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Bay, H., Tuytelaars, T., and Van, G.L. (2006, January 7\u201313). Surf: Speeded up robust features. Lecture notes in computer science. In Proceeding of the 9th European Conference on Computer Vision (ECCV), Graz, Austria.","DOI":"10.1007\/11744023_32"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Yao, Q., Kubota, A., Kawakita, K., Nonaka, K., Sankoh, H., and Naito, S. (2017, January 2\u20139). Fast camera self-calibration for synthesizing Free Viewpoint soccer Video. Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), New Orleans, LA, USA.","DOI":"10.1109\/ICASSP.2017.7952429"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zeng, R., Lakemond, R., Denman, S., Sridharan, S., Fookes, C., and Morgan, S. (2018, January 6\u201311). Calibrating Cameras in Poor-Conditioned Pitch-Based Sports Games. Proceedings of the 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, AB, Canada.","DOI":"10.1109\/ICASSP.2018.8461667"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Bozorgpour, A., Fotouhi, M., and Kasaei, S. (2015, January 10\u201314). Robust homography optimization in soccer scenes. Proceedings of the 2015 23rd Iranian Conference on Electrical Engineering, Tehran, Iran.","DOI":"10.1109\/IranianCEE.2015.7146320"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2780","DOI":"10.1109\/TPAMI.2020.2977644","article-title":"Rolling Shutter Homography and its Applications","volume":"43","author":"Lao","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, C., Bai, X., Liu, Y., and Zhou, J. (2018, January 17\u201319). Deep homography estimation with pairwise invertibility constraint. Proceedings of the Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR International Workshop, Beijing, China.","DOI":"10.1007\/978-3-319-97785-0_20"},{"key":"ref_30","unstructured":"Czolbe, S., Krause, O., and Feragen, A. (2020). DeepSim: Semantic similarity metrics for learned image registration. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Ghassab, V., Maanicshah, K., Bouguila, N., and Green, P. (December, January 29). REP-Model: A deep learning framework for replacing ad billboards in soccer videos. Proceedings of the 2020 IEEE International Symposium on Multimedia (ISM), Naples, Italy.","DOI":"10.1109\/ISM.2020.00032"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Molina-Cabello, M., Garcia-Gonzalez, J., Luque-Baena, R., Thurnhofer-Hemsi, K., and Lopez-Rubio, E. (2021, January 10\u201315). Adaptive estimation of optimal color transformations for deep convolutional network based homography estimation. Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), Milan, Italy.","DOI":"10.1109\/ICPR48806.2021.9412912"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1821","DOI":"10.1109\/JSTARS.2020.3047656","article-title":"A Novel Region-Based Image Registration Method for Multisource Remote Sensing Images Via CNN","volume":"14","author":"Zeng","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"ref_34","unstructured":"Wang, G., You, Z., An, P., Yu, J., and Chen, Y. (2018, January 20\u201321). Efficient and robust homography estimation using compressed convolutional neural network. Proceedings of the Digital TV and Multimedia Communication: 15th International Forum, Shanghai, China."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Ding, T., Yang, Y., Zhu, Z., Robinson, D., Vidal, R., Kneip, L., and Tsakiris, M. (2020, January 13\u201319). Robust Homography Estimation via Dual Principal Component Pursuit. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00612"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Li, B., Zhang, J., Yang, R., and Li, H. (2022). FM-Net: Deep Learning Network for the Fundamental Matrix Estimation from Biplanar Radiographs. Comput. Meth. Programs Biomed., 220.","DOI":"10.1016\/j.cmpb.2022.106782"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2346","DOI":"10.1109\/LRA.2018.2809549","article-title":"Unsupervised deep homography: A fast and robust homography estimation model","volume":"3","author":"Nguyen","year":"2018","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/j.patrec.2019.09.021","article-title":"Self-Supervised deep homography estimation with invertibility constraints","volume":"128","author":"Wang","year":"2019","journal-title":"Pattern Recognit. Lett."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Koguciuk, D., Arani, E., and Zonooz, B. (2021, January 19\u201325). Perceptual loss for robust unsupervised homography estimation. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, Online.","DOI":"10.1109\/CVPRW53098.2021.00483"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Jiang, H., Li, H., Lu, Y., Han, S., and Liu, S. (2023, January 7\u201314). Semi-supervised deep large-baseline homography estimation with progressive equivalence constraint. Proceedings of the AAAI Conference on Artificial Intelligence, Washington, DC, USA.","DOI":"10.1609\/aaai.v37i1.25183"},{"key":"ref_41","unstructured":"(2025, May 21). Youku. Available online: https:\/\/v.youku.com\/video?spm=a2hkm.8166622.PhoneSokuUgc_1.dscreenshot&&vid=XNTEzNjY3NzU4MA==&playMode=pugv&frommaciku=1."},{"key":"ref_42","unstructured":"(2025, May 21). Tencent Video. Available online: https:\/\/v.qq.com\/x\/cover\/mzc00200q077ncj\/m0046rerfdq.html."},{"key":"ref_43","unstructured":"(2025, May 21). Youku. Available online: https:\/\/v.youku.com\/video?spm=a2hkm.8166622.PhoneSokuUgc_1.dscreenshot&&vid=XNDA1NDc1NDA1Mg==&playMode=pugv&frommaciku=1."},{"key":"ref_44","first-page":"522","article-title":"Pixel-wise visible image registration based on deep neural network","volume":"48","author":"Huang","year":"2022","journal-title":"J. Beijing Univ. Aeronaut. Astronaut."},{"key":"ref_45","first-page":"252","article-title":"Registration method for power equipment infrared and visible images based on contour feature","volume":"41","author":"Jiang","year":"2022","journal-title":"Chin. J. Sci. Instrum."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1900","DOI":"10.1109\/TBME.2018.2822826","article-title":"Deformable Image Registration Using a Cue-Aware Deep Regression Network","volume":"65","author":"Cao","year":"2018","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1016\/j.neucom.2013.10.037","article-title":"Rapid multimodality registration based on MM-SURF","volume":"131","author":"Zhao","year":"2014","journal-title":"Neurocomputing"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"4460","DOI":"10.1109\/TCSVT.2021.3125736","article-title":"Depth-Aware Multi-Grid Deep Homography Estimation With Contextual Correlation","volume":"32","author":"Nie","year":"2022","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1403","DOI":"10.1049\/ipr2.12722","article-title":"Multi-scale homography estimation based on dual feature aggregation transformer","volume":"17","author":"Li","year":"2023","journal-title":"IET Image Process."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Zhu, H., Cao, S.Y., Hu, J., Zuo, S., Yu, B., and Ying, J. (2024, January 17\u201321). MCNet: Rethinking the core ingredients for accurate and efficient homography estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02450"}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/6\/832\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:41:17Z","timestamp":1760031677000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/6\/832"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,27]]},"references-count":50,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["sym17060832"],"URL":"https:\/\/doi.org\/10.3390\/sym17060832","relation":{},"ISSN":["2073-8994"],"issn-type":[{"value":"2073-8994","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,27]]}}}