Increasing Accuracy of Correspondences in Stereo Vision by Implementing Image Registering Technique
Keywords:3D reconstruction, stereo vision, point correspondences, image registration, Euclidian distance, descriptive vector
3D reconstruction on stereo vision is widely used mainly for measuring distances of objects in a scene or sizes of the object. It is based on the triangulation of point correspondences in stereo images. The accuracy of point correspondences as well their number has great impact in the performance of 3D reconstruction of the object in a scene. In many cases stereo images are obtained by handheld cameras, with same parameters or not. The vertical camera axes are assumed to be parallel, but usually they are approximately parallel or not parallel, obtained stereo images are rotated related to each other. The paper considers the pixel correspondences in case where cameras have different parameters, and the vertical axes of stereo images create an angle between them. Images are first aligned according to each other by a transformation function defined by control points. Point correspondences between reference and registered image are defined, and their similarity is calculated based on respective normalized descriptive vector. Statistics about correspondences in registered images is compared with the ones in rotated images. Experimental results show that accuracy of correspondences is increased.
Cheng, Yong-Qing & Wang, Xiaoguang & Collins, Robert & Riseman, Edward & Hanson, Allen. (2001). Three-Dimensional Reconstruction of Points and Lines with Unknown Correspondence across Images. International Journal of Computer Vision. 45. 129-156. 10.1023/A:1012424014764.
Bhandari, Piyush & Wu, Meiqing & Aslam, Nazia & Lam, Siew Kei & Kolekar, Maheshkumar. (2020). Efficient Sparse to Dense Stereo Matching Technique. 10.1007/978-981-32-9088-4_14.
Ahmed, Dr. Tasneem & Singh, Dharmendra & Raman, Balasubramanian. (2016). Potential application of Kanade-Lucas-Tomasi tracker on satellite images for automatic change detection. Journal of Applied Remote Sensing. 10. 026018. 10.1117/1.JRS.10.026018.
Dall'Asta, E., & Roncella, R. (2014). A comparison of semiglobal and local dense matching algorithms for surface reconstruction. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XL-5, 187-194. doi:10.5194/isprsarchives-xl-5-187-2014
Pitiot, A. (2021). Multimodal Image registration. Imaging Modalities for Biological and Preclinical Research: A Compendium, Volume 2. doi:10.1088/978-0-7503-3747-2ch25
Indrit Enesi, Miranda Harizaj, Betim Çiço, "Implementing Fusion Technique Using Biorthogonal Dwt to Increase the Number of Minutiae in Fingerprint Images", Journal of Sensors, vol. 2022, Article ID 3502463, 13 pages, 2022. https://doi.org/10.1155/2022/3502463
Pataky TC, Yagi M, Ichihashi N, Cox PG. 2021. Landmark-free, parametric hypothesis tests regarding two-dimensional contour shapes using coherent point drift registration and statistical parametric mapping. PeerJ Computer Science 7:e542 https://doi.org/10.7717/peerj-cs.542
Fathy GM, Hassan HA, Sheta W, Omara FA, Nabil E. 2021. A novel no-sensors 3D model reconstruction from monocular video frames for a dynamic environment. PeerJ Computer Science 7:e529 https://doi.org/10.7717/peerj-cs.529
Ke, F., Liu, H., Zhao, D., Sun, G., Xu, W., & Feng, W. (2020). A high precision image registration method for measurement based on the Stereo Camera System. Optik, 204, 164186. doi:10.1016/j.ijleo.2020.164186
Vladimir A. G. (2016). POINT CLOUDS REGISTRATION AND GENERATION FROM STEREO IMAGES. International Journal "Information Content and Processing", Volume 3, Number 2.
Waizenegger, Wolfgang & Feldmann, Ingo & Eisert, Peter. (2011). Depth Driven Photometric and Geometric Image Registration for Real-Time Stereo Systems.. VMV 2011 - Vision, Modeling and Visualization. 25-32. 10.2312/PE/VMV/VMV11/025-032.
D. Moolchandani, N. Shrivastava, A. Kumar and S. R. Sarangi, "PredStereo: An Accurate Real-time Stereo Vision System," 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 4078-4087, doi: 10.1109/WACV51458.2022.00413.
Jayasena, A. (2021). Register Transfer Level Disparity generator with Stereo Vision. Journal of Open Research Software, 9(1), 18. DOI: http://doi.org/10.5334/jors.339
S. Zhang, F. Huang, B. Liu, G. Li, Y. Chen, L. Sun, and Y. Zhang, "Robust registration for ultra-field infrared and visible binocular images," Opt. Express 28, 21766-21782 (2020).
Achmad, M.S. & Bayuaji, Luhur & Daud, Mohd & Pebrianti, Dwi & Ann, Nurnajmin. (2019). Study on 3D Scene Reconstruction in Robot Navigation using Stereo Vision. 10.1109/I2CACIS.2016.7885292.
Costineanu, D., Fosalau, C., Damian, C., & Plopa, O. (2008). Triangulation-based 3D image processing method and system with compensating shadowing errors. In 16th IMEKO TC4 Int. Symp.: Exploring New Frontiers of Instrum. and Methods for Electrical and Electronic Measurements; 13th TC21 Int. Workshop on ADC Modelling and Testing—Joint Session, Proc (pp. 460-3).
Gao, L. et al. (2022) “Research on multi-view 3D reconstruction technology based on SFM,” Sensors, 22(12), p. 4366. Available at: https://doi.org/10.3390/s22124366.
O' Riordan, Andrew & Newe, Thomas & Toal, Daniel & Dooly, Gerard. (2018). Stereo Vision Sensing: Review of existing systems. 10.1109/ICSensT.2018.8603605.
Mingyou Chen, Yunchao Tang, Xiangjun Zou, Kuangyu Huang, Lijuan Li, Yuxin He. High-accuracy multi-camera reconstruction enhanced by adaptive point cloud correction algorithm. Optics and Lasers in Engineering. Volume 122, 2019, Pages 170-183, ISSN 0143-8166, https://doi.org/10.1016/j.optlaseng.2019.06.011.
Ms. Ritu Singh Phogat, Mr. Hardik Dhamecha, Dr. Manoj Pandya, Mr. Bharat Chaudhary, Dr. Madhukar Potdar. Different Image Registration Methods – An Overview. International Journal of Scientific & Engineering Research, Volume 5, Issue 12, December-2014 44 ISSN 2229-5518.
Balluff B, Heeren RMA, Race AM. An overview of image registration for aligning mass spectrometry imaging with clinically relevant imaging modalities. J Mass Spectrom Adv Clin Lab. 2021 Dec 18;23:26-38. doi: 10.1016/j.jmsacl.2021.12.006. PMID: 35156074; PMCID: PMC8821033.
Cournet, M. et al. (2016) “2D sub-pixel disparity measurement using QPEC / Medicis,” ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLI-B1, pp. 291–298. Available at: https://doi.org/10.5194/isprsarchives-xli-b1-291-2016.
Gueguen, Lionel & Pesaresi, Martino. (2011). Multi scale Harris corner detector based on Differential Morphological Decomposition. Pattern Recognition Letters. 32. 1714-1719. 10.1016/j.patrec.2011.07.021.
Danielsson, M. et al. (2016) “Feature detection and description using a harris-hessian/freak combination on an embedded GPU,” Proceedings of the 5th International Conference on Pattern Recognition Applications and Methods [Preprint]. Available at: https://doi.org/10.5220/0005662005170525.
How to Cite
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.