计算机科学 ›› 2026, Vol. 53 ›› Issue (6A): 250800043-5.doi: 10.11896/jsjkx.250800043
张奔1, 朱灯林2
ZHANG Ben1, ZHU Denglin2
摘要： 为了实现实时有效的立体匹配,在现有的局部立体匹配算法的基础上,提出了一种基于加权引导滤波的局部立体匹配算法。首先,在代价计算阶段采用多测度融合的方法。其次,在成本聚集阶段,采用加权引导滤波方法进行滤波,利用Canny算法自适应调整正则化参数,实现了更精确的成本聚集。最后,对WTA优化策略得到的视差图进行左右一致性检测(LRC)的致密化处理。通过对Middlebury数据库的图像采用该算法进行立体匹配,结果验证了算法的有效性和鲁棒性。
中图分类号:
| [1] DANIEL S,SZELISKI R.A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms[J].Internatio-nal Journal of Computer Vision,2002,47(1/2/3):7-42. [2] STEPHEN P,MAYHEW B J E,FRISBY J P.PMF:A stereo correspondence algorithm using a disparity gradient limit[J].Perception,1985,14(4):449. [3] VEKSLER O.Stereo correspondence by dynamic programming on a tree[C]//Computer Vision and Pattern Recognition(CVPR 2005).IEEE,2005:384-390. [4] FELZENSZWALB P F,HUTTENLOCHER D P.Efficient Belief Propagation for Early Vision[J].International Journal of Computer Vision,2006,70(1):41-54. [5] VLADIMIR K,ZABIH R.Computing Visual Correspondencewith Occlusions using Graph Cuts[C]//Computer Vision－ICCV 2001.IEEE,2001:508-515. [6] TOMBARI F,MATTOCCIA S,DI STEFANOL,et al.Classification and evaluation of cost aggregation methods for stereo correspondence[C]//Computer Vision and Pattern Recognition(CVPR 2008).IEEE,2008:1-8. [7] STEPHEN P,MAYHEW B J E,FRISBY J P.PMF:A stereo correspondence algorithm using a disparity gradient limit[J].Perception,1985,14(4):449. [8] RAMIN Z,WOODFILL J.Non-parametric local transforms for computing visual correspondence[C]//Computer Vision－ ECCV '94.1994:151-158. [9] POOJA M,MOGHE A A.An Application of Machine Learning in Empirical and Variational Mode Decomposition with SVM Classifier to Enhance Diagnostic Accuracy for Disease Detection in Soldier's Eyes[J].Defence Science Journal,2025,75(1):8. [10] VEKSLER O.Fast variable window for stereo correspondence using integral images.Computer Vision and Pattern Recognition[C]//Proceedings of 2003 IEEE Computer Society Conference on IEEE.2003:I-556-I-561. [11] YOON K J,KWEON I S.Adaptive support-weight approach for correspondence search[J].IEEE Transactions on Pattern Analysis Machine Intelligence,2006,28(4):650-656. [12] WANG S Q,LI B,DAI Y.Efficient Multi-View Stereo by Dynamic Cost Volume and Cross-Scale Propagation[J].IEEE Transactions on Circuits and Systems for Video Technology,2024,10(1):34. [13] LI Z G,ZHENG J H,ZHU Z J,et al.Weighted Guided Image Filtering[J].IEEE Transactions on Image Processing,2015,24(1):120-129. [14] WANG F,GALLIANI S,VOGEL C,et al.Itermvs:Iterativeprobability estimation for efficient multi-view stereo[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.2022:8606-8615. [15] LIU T,YE X,ZHAO W,et al.When epipolar constraint meetsnon-local operators in multi-view stereo[C]//Proceedings of the IEEE/CVF International Conference onComputer Vision.2023:18088-18097. [16] Middlebury stereo benchmarks[EB/OL].http://vision.middlebury.edu/stereo/. [17] The KITTI vision benchmark suite[EB/OL].http://www.cvlibs.net/datasets/kitti/. |
|
||
首页