Edge-Preserving Stereo Matching Using Minimum Spanning Tree

被引:5
|
作者
Zhang, Congxuan [1 ]
He, Chao [2 ]
Chen, Zhen [1 ]
Liu, Wen [3 ]
Li, Ming [1 ]
Wu, Junjie [1 ]
机构
[1] Nanchang Hangkong Univ, Key Lab Nondestruct Testing, Minist Educ, Nanchang 330063, Jiangxi, Peoples R China
[2] Nanjing Univ Aeronaut & Astronaut, Sch Automat, Nanjing 211106, Peoples R China
[3] Univ Kansas, Dept Phys Therapy & Rehabil Sci, Kansas City, KS 66160 USA
来源
IEEE ACCESS | 2019年 / 7卷
基金
中国博士后科学基金; 中国国家自然科学基金;
关键词
Stereo matching; minimum spanning tree; edge-preserving; brightness information; disparity range estimation; segmentation optimization; SUPPORT-WEIGHT APPROACH; COST AGGREGATION; ACCURATE;
D O I
10.1109/ACCESS.2019.2958527
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Despite that the accuracy and efficiency of stereo matching technology have significantly improved in the past decades, the issue of edge-blurring remains a challenge to most of the existing approaches. In this paper, we propose a minimum spanning tree (MST) based stereo matching method by using the image edge and segmentation optimization to preserve the image boundary. We first exploit a fast disparity range estimation method by combining the Surf and Akaze feature points to improve the computational efficiency. Second, we utilize the image edges and brightness information to generate a self-adaptive weight function, which is able to significantly improve the accuracy of MST aggregating in the regions of complex texture and boundaries with similar color distribution. Third, we employ the image segmentation to extract the invalid regions of the estimated disparity map, and propose a post-processing scheme to refine the disparity result. Finally, we run our method on several Middlebury and KITTI datasets. The comparison results between our method and other state-of-the-art approaches demonstrate that the proposed method has high accuracy for disparity computation and is especially robust to the edge-blurring.
引用
收藏
页码:177909 / 177921
页数:13
相关论文
共 50 条
  • [41] An Edge-Preserving Image Reconstruction Using Neural Network
    Paul Bao
    Dianhui Wang
    Journal of Mathematical Imaging and Vision, 2001, 14 : 117 - 130
  • [42] Depth edge detection using edge-preserving filter and morphological operations
    Thai Leang Sung
    Hyo Jong Lee
    International Journal of System Assurance Engineering and Management, 2020, 11 : 812 - 817
  • [43] Depth edge detection using edge-preserving filter and morphological operations
    Sung, Thai Leang
    Lee, Hyo Jong
    INTERNATIONAL JOURNAL OF SYSTEM ASSURANCE ENGINEERING AND MANAGEMENT, 2020, 11 (04) : 812 - 817
  • [44] Hierarchical Edge-Preserving Dense Matching by Exploiting Reliably Matched Line Segments
    Yue, Yi
    Fang, Tong
    Li, Wen
    Chen, Min
    Xu, Bo
    Ge, Xuming
    Hu, Han
    Zhang, Zhanhao
    REMOTE SENSING, 2023, 15 (17)
  • [45] Connectivity-Preserving Formation Stabilization of Unicycles in Local Coordinates Using Minimum Spanning Tree
    Aranda, Miguel
    Aragues, Rosario
    Lopez-Nicolas, Gonzalo
    Sagues, Carlos
    2016 AMERICAN CONTROL CONFERENCE (ACC), 2016, : 1968 - 1974
  • [46] MINIMUM SPANNING TREE
    ROSS, GJS
    THE ROYAL STATISTICAL SOCIETY SERIES C-APPLIED STATISTICS, 1969, 18 (01): : 103 - &
  • [47] AN ASYMPTOTIC DETERMINATION OF THE MINIMUM SPANNING TREE AND MINIMUM MATCHING CONSTANTS IN GEOMETRICAL-PROBABILITY
    BERTSIMAS, DJ
    VANRYZIN, G
    OPERATIONS RESEARCH LETTERS, 1990, 9 (04) : 223 - 231
  • [48] MINIMUM SPANNING TREE
    CAHIT, I
    CAHIT, R
    PROCEEDINGS OF THE INSTITUTION OF ELECTRICAL ENGINEERS-LONDON, 1975, 122 (05): : 496 - 496
  • [49] Image Segmentation Using Minimum Spanning Tree
    Dewi, M. P.
    Armiati, A.
    Alvini, S.
    2ND INTERNATIONAL CONFERENCE ON MATHEMATICS, SCIENCE, EDUCATION AND TECHNOLOGY, 2018, 335
  • [50] HIERARCHICAL CLUSTERING USING MINIMUM SPANNING TREE
    ROHLF, FJ
    COMPUTER JOURNAL, 1973, 16 (01): : 93 - 95