In this paper we present a new segment-based stereo matching algorithm using graph cuts. In our approach, the reference image is divided into non-overlapping homogeneous segments and the scene structure is represented as a set of planes in the disparity space. The stereo matching problem is formulated as an energy minimization problem in the segment domain instead of the traditional pixel domain. Graph cuts technique is used to fast approximate the optimal solution, which assigns the corresponding disparity plane to each segment. Experiments demonstrate that the performance of our algorithm is comparable to the state-of-the-art stereo algorithms on various data sets. Furthermore, strong performance is achieved in the conventionally difficult areas such as: textureless regions, disparity discontinuous boundaries and occluded portions.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Segment-based stereo matching using graph cuts


    Contributors:
    Li Hong, (author) / Chen, G. (author)


    Publication date :

    2004-01-01


    Size :

    552921 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Segment-Based Stereo Matching Using Graph Cuts

    Hong, L. / Chen, G. / IEEE Computer Society | British Library Conference Proceedings | 2004


    Stereo Matching Using Iterated Graph Cuts and Mean Shift Filtering

    Chang, J. Y. / Lee, K. M. / Lee, S. U. | British Library Conference Proceedings | 2006


    Multi-view stereo via volumetric graph-cuts

    Vogiatzis, G. / Torr, P.H.S. / Cipolla, R. | IEEE | 2005


    Multi-label Depth Estimation for Graph Cuts Stereo Problems

    Papadakis, N. | British Library Online Contents | 2010


    GPU-friendly multi-view stereo reconstruction using surfel representation and graph cuts

    Chang, J. Y. / Park, H. / Park, I. K. et al. | British Library Online Contents | 2011