基于Middlebury数据库的光流算法计算精度和性能分析
Analysis of Optical Flow Algorithm Accuracy and Performance Based on the Middlebury Database
DOI: 10.12677/jisp.2026.154055, PDF,   
作者: 黄 岚, 李同奋：广州赛宝认证中心服务有限公司，广东 广州
关键词: 光流算法；计算精度；Middlebury数据库；仿真；Optical Flow Algorithm； Calculation Accuracy； Middlebury Database； Simulation
摘要: 本章首先介绍HS、LK、PLK、基于SIFT、SF五种光流计算方法的基本原理；然后通过计算机构图和Middlebury数据库中的标准图像，对各光流算法在不同位移情况下的计算精度进行研究，为光流算法弹载应用提供技术支撑。
Abstract: Firstly, this chapter introduces the basic principles of five optical flow calculation methods, which include HS, LK, PLK, SIFT-based, and SF. Then, the calculation accuracy of each optical flow algorithm under different displacements is studied based on computer graphics and standard images in the Middlebury database, which provides technical support for the missile-borne application of optical flow algorithms.
文章引用：黄岚, 李同奋. 基于Middlebury数据库的光流算法计算精度和性能分析[J]. 图像与信号处理, 2026, 15(4): 632-639. https://doi.org/10.12677/jisp.2026.154055

参考文献

[1] Guo, J., Dong, X.M., Wang, L., Li, H.B. and Chen, Y. (2012) Control and Robust Vision Relative Navigation for Autonomous Aerial Refueling. Advanced Materials Research, 383, 1953-1959.
https://doi.org/10.4028/www.scientific.net/amr.383-390.1953
[2] Zhu, Z., Su, A., Liu, H., Shang, Y. and Yu, Q. (2015) Vision Navigation for Aircrafts Based on 3D Reconstruction from Real-Time Image Sequences. Science China Technological Sciences, 58, 1196-1208.
https://doi.org/10.1007/s11431-015-5828-x
[3] Guo, J., Li, L., Li, K. and Wang, R. (2013) An Adaptive Fuzzy-Sliding Lateral Control Strategy of Automated Vehicles Based on Vision Navigation. Vehicle System Dynamics, 51, 1502-1517.
https://doi.org/10.1080/00423114.2013.811789
[4] Yu, M., Cui, H. and Tian, Y. (2014) A New Approach Based on Crater Detection and Matching for Visual Navigation in Planetary Landing. Advances in Space Research, 53, 1810-1821.
https://doi.org/10.1016/j.asr.2013.04.011
[5] Johnson-Roberson, M., Bryson, M., Friedman, A., Pizarro, O., Troni, G., Ozog, P., et al. (2017) High-Resolution Underwater Robotic Vision-Based Mapping and Three-Dimensional Reconstruction for Archaeology. Journal of Field Robotics, 34, 625-643.
https://doi.org/10.1002/rob.21658
[6] Holt, R.S. and Beard, R.W. (2010) Vision-Based Road-Following Using Proportional Navigation. Journal of Intelligent and Robotic Systems, 57, 193-216.
https://doi.org/10.1007/s10846-009-9353-7
[7] Manchester, I.R., Savkin, A.V. and Faruqi, F.A. (2008) Method for Optical-Flow-Based Precision Missile Guidance. IEEE Transactions on Aerospace and Electronic Systems, 44, 835-851.
https://doi.org/10.1109/taes.2008.4655347
[8] Horn, B.K.P. and Schunck, B.G. (1981) Determining Optical Flow. Artificial Intelligence, 17, 185-203.
https://doi.org/10.1016/0004-3702(81)90024-2
[9] Lucas, B.D. and Kanade, T. (1981) An Iterative Image Registration Technique with an Application to Stereo Vision. Proceedings of the 7th International Joint Conference on Artificial Intelligence, Vancouver, 24-28 August 1981, 674-679.
[10] Bouguet, J.Y. (2001) Pyramidal Implementation of the Affine Lucas Kanade Feature Tracker Description of the Algorithm. Intel Corporation, Technical Report, 1-10.
[11] Lowe, D.G. (2004) Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 60, 91-110.
https://doi.org/10.1023/b:visi.0000029664.99615.94
[12] Timofte, R. and Van Gool, L. (2015) Sparse Flow: Sparse Matching for Small to Large Displacement Optical Flow. 2015 IEEE Winter Conference on Applications of Computer Vision, Waikoloa, 5-9 January 2015, 1100-1106.
https://doi.org/10.1109/wacv.2015.151