Research on Adaptive RANSAC Panoramic Stitching Optimization for Virtual Reality Vision Generation_Vol. 4 No. 3 (JES 2026)_Journal of Engineering System (ISSN: 2959-0604)

Home > Journal of Engineering System (ISSN: 2959-0604) > Vol. 4 No. 3 (JES 2026) >

Research on Adaptive RANSAC Panoramic Stitching Optimization for Virtual Reality Vision Generation

Download PDF

DOI: https://doi.org/10.62517/jes.202602321

Author(s)

Mei Huang

Affiliation(s)

Changsha Normal University, Hunan, Changsha, China

Abstract

Aiming at the high standard requirements for real-time generation of visual content in virtual reality (VR) scene construction, as well as the efficiency bottlenecks and robustness deficiencies of traditional image stitching methods in dealing with complex environments, this paper proposes an improved random sampling consistency (M-RANSAC) algorithm based on adaptive enhancement strategy. The algorithm aims to optimize the model parameter estimation in the panoramic stitching process. Specifically, this study first uses the HARRIS operator to extract image feature points, and introduces a priority ranking mechanism based on the distance of matching point pairs to realize the preprocessing of the feature point set; on this basis, the sampling scale of the minimum sample set is dynamically adjusted according to the real-time ratio of the internal and external points, and the invalid model is effectively filtered by combining the double threshold data inspection strategy. The experimental data show that the improved strategy significantly shortens the time consumption of model sampling and data verification through feature point sorting and pretest screening, and reduces the estimation deviation of homography matrix, which greatly improves the operation efficiency and stability of the algorithm under the premise of ensuring the splicing accuracy. The research results provide an efficient and reliable technical solution for the real-time construction of immersive virtual reality visual content, which has broad application value.

Keywords

Virtual Reality; RANSAC; Image Stitching; Feature Point Matching; Feature Ranking

References

[1]Fu M, Liang H, Zhu C, et al. Image Stitching Techniques Applied to Plane or 3-D Models: A Review. IEEE Sensors Journal, 2023, 23(8): 8060-8079. [2]Soltanpour S, Joslin C. A Survey on Feature-Based and Deep Image Stitching//Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. 2025: 777-788. [3]Yan Y, Xu L, Liu Y, et al. Larynx Ultrasound Image Stitching Based on Multiconstraint Super-Pixel Feature. IEEE Transactions on Instrumentation and Measurement, 2023, 72: 1-11. [4]Lang W, Wen Y, Bao Li. Multi-scenes image stitching based on autonomous driving. in Proc. IEEE 4th Inf. Technol., Netw., Electron. Autom. Control Conf. (ITNEC), 2020: 694–698. [5]Zhu S, Zhang Y, Zhang J, et al. ISGTA: an effective approach for multi-image stitching based on gradual transformation matrix. Signal, Image and Video Processing, 2023, 17(7): 3811-3820. [6]Wu H, Bao C, Hao Q, et al. Improved Unsupervised Stitching Algorithm for Multiple Environments Super UDIS. Sensors, 2024, 24(16): 5352. [7]Li Y, Wei B, Zhong Y, et al. A bibliometric analysis of global research on spinal cord injury: 1999–2019. Spinal Cord, 2021, 60(4): 281-287. [8]Jiayi M, Xingyu J, Aoxiang F, et al. Image matching from handcrafted to deep features: a survey. International Journal of Computer Vision, 2021, 129(1): 23-79. [9]Atokari M, Viitanen M, Mercat A, et al. Parallax-Tolerant 360 Live Video Stitcher//2019 IEEE Visual Communications and Image Processing (VCIP). IEEE, 2019: 1-4. [10]Khamiyev I, Issa D, Akhtar Z, et al. Panoramic image generation using deep neural networks. Soft Computing, 2023, 27(13): 8679-8695. [11]Jia Y, Wang R, Jiang X. A Real-Time Image Stitching and Fusion Algorithm Circuit Design Based on FPGA. Electronics, 2024, 13(2): 271. [12]Lee H, Lee S, Choi O. Improved method on image stitching based on optical flow algorithm. International Journal of Engineering Business Management, 2020, 12: 184797902098092. [13]Xiao J. Research of different feature detection and matching algorithms on panoramic image. Applied and Computational Engineering, 2023, 15(1): 38-51. [14]Raguram R, Chum O, Pollefeys M, et al. USAC: A Universal Framework for Random Sample Consensus. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8): 2022-2038. [15]Zhang J, Liu S, Sun L, et al. Plane-based content-preserving warps for image stitching. IEEE Transactions on Visualization and Computer Graphics, 2016, 22(7): 1848-1859. [16]Hongxing C, Jiahang J. Image Stitching Based on Corner Point Transformation Matrix. Science Technology and Engineering. 2008, 8(16):4536-4529. [17]Yao L, Lizhuang M. A Fast and Robust Image Stitching Algorithm. Proceeding of the 6th World Congress on Intelligent Control and Automation Dalian, China. October, 23rd, 2006. [18]Lifang W, Linlin H,Lin P, Lun Y. The Retinal Image Mosaic Based on Invariant Feature and Hierachical Transformation Mdels The 2nd International Congress on Image and Signal Processing. Tianjin, China, October 30th, 2009. [19]Cheng B, Tang X. Research on Harris scale-invariant keypoint detector. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2010, 11(10): 755-762. [20]Bangsheng C, Xiaowei T. Study of Harris scale invariant keypoint detector. Journal of Zhejiang University (Engineering Science), 2009, 43(5):855-859. [21]David G. Lowe. Disctinctive Image Features Form Scale-Invariant Keypoints. International Journal of Computer Vison, 2004, 60(2):91-110. [22]Krystian Mikolajczyk, Cordelia Schmid. Scale & Affine Invariant Interest Point Detectors. International Journal of Computer Vistion, 2004, 60(1):63-86 [23]Barbara Zitiva, Jan Flusser. Image registration methods: a survey. Image and Vision Computing, 2003, 21(11):977-1000. [24]Jiangning W, Baolong G, Zongzhong F. An Image Mosaic Method Based on Interest Point Matching. Journal of Computer Applications, 2006, 26(3): 610-612.