On the formulation, performance and design choices of Cost-Curve Occupancy Grids for stereo-vision based 3D reconstruction

Martim Brandão, Ricardo Ferreira, Kenji Hashimoto, José Santos-Victor, Atsuo Takanishi

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    We present a grid-based 3D reconstruction method which integrates all costs given by stereo vision into what we call a Cost-Curve Occupancy Grid (CCOG). Occupancy probabilities of grid cells are estimated in a Bayesian formulation, from the likelihood of stereo cost measurements taken at all distance hypotheses. This is accomplished with only a small set of probabilistic assumptions which we discuss in the paper. We quantitatively characterize the method's performance under different conditions of both image noise and number of used stereo pairs, compared also to traditional algorithms. We complement the study by giving insights on design choices of CCOGs such as likelihood model, window size of the cost function and use of a hole filling method. Experiments were made on a real-world outdoors dataset with ground-truth data.

    Original languageEnglish
    Title of host publicationIEEE International Conference on Intelligent Robots and Systems
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages1818-1823
    Number of pages6
    ISBN (Print)9781479969340
    DOIs
    Publication statusPublished - 2014 Oct 31
    Event2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2014 - Chicago
    Duration: 2014 Sep 142014 Sep 18

    Other

    Other2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2014
    CityChicago
    Period14/9/1414/9/18

    Fingerprint

    Stereo vision
    Costs
    Cost functions
    Experiments

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Software
    • Computer Vision and Pattern Recognition
    • Computer Science Applications

    Cite this

    Brandão, M., Ferreira, R., Hashimoto, K., Santos-Victor, J., & Takanishi, A. (2014). On the formulation, performance and design choices of Cost-Curve Occupancy Grids for stereo-vision based 3D reconstruction. In IEEE International Conference on Intelligent Robots and Systems (pp. 1818-1823). [6942801] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IROS.2014.6942801

    On the formulation, performance and design choices of Cost-Curve Occupancy Grids for stereo-vision based 3D reconstruction. / Brandão, Martim; Ferreira, Ricardo; Hashimoto, Kenji; Santos-Victor, José; Takanishi, Atsuo.

    IEEE International Conference on Intelligent Robots and Systems. Institute of Electrical and Electronics Engineers Inc., 2014. p. 1818-1823 6942801.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Brandão, M, Ferreira, R, Hashimoto, K, Santos-Victor, J & Takanishi, A 2014, On the formulation, performance and design choices of Cost-Curve Occupancy Grids for stereo-vision based 3D reconstruction. in IEEE International Conference on Intelligent Robots and Systems., 6942801, Institute of Electrical and Electronics Engineers Inc., pp. 1818-1823, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2014, Chicago, 14/9/14. https://doi.org/10.1109/IROS.2014.6942801
    Brandão M, Ferreira R, Hashimoto K, Santos-Victor J, Takanishi A. On the formulation, performance and design choices of Cost-Curve Occupancy Grids for stereo-vision based 3D reconstruction. In IEEE International Conference on Intelligent Robots and Systems. Institute of Electrical and Electronics Engineers Inc. 2014. p. 1818-1823. 6942801 https://doi.org/10.1109/IROS.2014.6942801
    Brandão, Martim ; Ferreira, Ricardo ; Hashimoto, Kenji ; Santos-Victor, José ; Takanishi, Atsuo. / On the formulation, performance and design choices of Cost-Curve Occupancy Grids for stereo-vision based 3D reconstruction. IEEE International Conference on Intelligent Robots and Systems. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 1818-1823
    @inproceedings{1c78f71ce7ff4bbbadb6738ad96600a6,
    title = "On the formulation, performance and design choices of Cost-Curve Occupancy Grids for stereo-vision based 3D reconstruction",
    abstract = "We present a grid-based 3D reconstruction method which integrates all costs given by stereo vision into what we call a Cost-Curve Occupancy Grid (CCOG). Occupancy probabilities of grid cells are estimated in a Bayesian formulation, from the likelihood of stereo cost measurements taken at all distance hypotheses. This is accomplished with only a small set of probabilistic assumptions which we discuss in the paper. We quantitatively characterize the method's performance under different conditions of both image noise and number of used stereo pairs, compared also to traditional algorithms. We complement the study by giving insights on design choices of CCOGs such as likelihood model, window size of the cost function and use of a hole filling method. Experiments were made on a real-world outdoors dataset with ground-truth data.",
    author = "Martim Brand{\~a}o and Ricardo Ferreira and Kenji Hashimoto and Jos{\'e} Santos-Victor and Atsuo Takanishi",
    year = "2014",
    month = "10",
    day = "31",
    doi = "10.1109/IROS.2014.6942801",
    language = "English",
    isbn = "9781479969340",
    pages = "1818--1823",
    booktitle = "IEEE International Conference on Intelligent Robots and Systems",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - On the formulation, performance and design choices of Cost-Curve Occupancy Grids for stereo-vision based 3D reconstruction

    AU - Brandão, Martim

    AU - Ferreira, Ricardo

    AU - Hashimoto, Kenji

    AU - Santos-Victor, José

    AU - Takanishi, Atsuo

    PY - 2014/10/31

    Y1 - 2014/10/31

    N2 - We present a grid-based 3D reconstruction method which integrates all costs given by stereo vision into what we call a Cost-Curve Occupancy Grid (CCOG). Occupancy probabilities of grid cells are estimated in a Bayesian formulation, from the likelihood of stereo cost measurements taken at all distance hypotheses. This is accomplished with only a small set of probabilistic assumptions which we discuss in the paper. We quantitatively characterize the method's performance under different conditions of both image noise and number of used stereo pairs, compared also to traditional algorithms. We complement the study by giving insights on design choices of CCOGs such as likelihood model, window size of the cost function and use of a hole filling method. Experiments were made on a real-world outdoors dataset with ground-truth data.

    AB - We present a grid-based 3D reconstruction method which integrates all costs given by stereo vision into what we call a Cost-Curve Occupancy Grid (CCOG). Occupancy probabilities of grid cells are estimated in a Bayesian formulation, from the likelihood of stereo cost measurements taken at all distance hypotheses. This is accomplished with only a small set of probabilistic assumptions which we discuss in the paper. We quantitatively characterize the method's performance under different conditions of both image noise and number of used stereo pairs, compared also to traditional algorithms. We complement the study by giving insights on design choices of CCOGs such as likelihood model, window size of the cost function and use of a hole filling method. Experiments were made on a real-world outdoors dataset with ground-truth data.

    UR - http://www.scopus.com/inward/record.url?scp=84911473761&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84911473761&partnerID=8YFLogxK

    U2 - 10.1109/IROS.2014.6942801

    DO - 10.1109/IROS.2014.6942801

    M3 - Conference contribution

    SN - 9781479969340

    SP - 1818

    EP - 1823

    BT - IEEE International Conference on Intelligent Robots and Systems

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -