Simultaneous dense scene reconstruction and Object Labeling

    Research output: Chapter in Book/Conference paperConference paper

    5 Citations (Scopus)

    Abstract

    This paper presents an efcient system for simultaneous dense scene reconstruction and object labeling in real-world environments (captured with an RGB-D sensor). The proposed system starts with the generation of object proposals in the scene. It then tracks spatio-temporally consistent object proposals across multiple frames and produces a dense reconstruction of the scene. In parallel, the proposed system uses an efcient inference algorithm, where object class probabilities are computed at an object-level and fused into a voxel-based prediction hypothesis modeled on the voxels of the reconstructed scene. Our extensive experiments using challenging RGB-D object and scene datasets, and live video streams from Microsoft Kinect show that the proposed system achieved competitive 3D scene reconstruction and object labeling results compared to the state-of-the-art methods.
    Original languageEnglish
    Title of host publication2016 IEEE International Conference on Robotics and Automation (ICRA)
    EditorsDanica Kragic, Allison Okamura
    Place of PublicationUSA
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages2255-2262
    Number of pages8
    ISBN (Print)9781467380256
    DOIs
    Publication statusPublished - 2016
    Event2016 IEEE International Conference on Robotics and Automation: ICRA 2016 - Stockholm, Sweden
    Duration: 16 May 201621 May 2016

    Conference

    Conference2016 IEEE International Conference on Robotics and Automation
    CountrySweden
    CityStockholm
    Period16/05/1621/05/16

    Fingerprint

    Labeling
    Sensors
    Experiments

    Cite this

    Asif, U., Bennamoun, M., & Sohel, F. (2016). Simultaneous dense scene reconstruction and Object Labeling. In D. Kragic, & A. Okamura (Eds.), 2016 IEEE International Conference on Robotics and Automation (ICRA) (pp. 2255-2262). [ 7487374] USA: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICRA.2016.7487374
    Asif, Umar ; Bennamoun, Mohammed ; Sohel, Ferdous. / Simultaneous dense scene reconstruction and Object Labeling. 2016 IEEE International Conference on Robotics and Automation (ICRA). editor / Danica Kragic ; Allison Okamura. USA : IEEE, Institute of Electrical and Electronics Engineers, 2016. pp. 2255-2262
    @inproceedings{4e04002771914b9db05a47cc5259620b,
    title = "Simultaneous dense scene reconstruction and Object Labeling",
    abstract = "This paper presents an efcient system for simultaneous dense scene reconstruction and object labeling in real-world environments (captured with an RGB-D sensor). The proposed system starts with the generation of object proposals in the scene. It then tracks spatio-temporally consistent object proposals across multiple frames and produces a dense reconstruction of the scene. In parallel, the proposed system uses an efcient inference algorithm, where object class probabilities are computed at an object-level and fused into a voxel-based prediction hypothesis modeled on the voxels of the reconstructed scene. Our extensive experiments using challenging RGB-D object and scene datasets, and live video streams from Microsoft Kinect show that the proposed system achieved competitive 3D scene reconstruction and object labeling results compared to the state-of-the-art methods.",
    author = "Umar Asif and Mohammed Bennamoun and Ferdous Sohel",
    year = "2016",
    doi = "10.1109/ICRA.2016.7487374",
    language = "English",
    isbn = "9781467380256",
    pages = "2255--2262",
    editor = "Danica Kragic and Allison Okamura",
    booktitle = "2016 IEEE International Conference on Robotics and Automation (ICRA)",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    address = "United States",

    }

    Asif, U, Bennamoun, M & Sohel, F 2016, Simultaneous dense scene reconstruction and Object Labeling. in D Kragic & A Okamura (eds), 2016 IEEE International Conference on Robotics and Automation (ICRA)., 7487374, IEEE, Institute of Electrical and Electronics Engineers, USA, pp. 2255-2262, 2016 IEEE International Conference on Robotics and Automation, Stockholm, Sweden, 16/05/16. https://doi.org/10.1109/ICRA.2016.7487374

    Simultaneous dense scene reconstruction and Object Labeling. / Asif, Umar; Bennamoun, Mohammed; Sohel, Ferdous.

    2016 IEEE International Conference on Robotics and Automation (ICRA). ed. / Danica Kragic; Allison Okamura. USA : IEEE, Institute of Electrical and Electronics Engineers, 2016. p. 2255-2262 7487374.

    Research output: Chapter in Book/Conference paperConference paper

    TY - GEN

    T1 - Simultaneous dense scene reconstruction and Object Labeling

    AU - Asif, Umar

    AU - Bennamoun, Mohammed

    AU - Sohel, Ferdous

    PY - 2016

    Y1 - 2016

    N2 - This paper presents an efcient system for simultaneous dense scene reconstruction and object labeling in real-world environments (captured with an RGB-D sensor). The proposed system starts with the generation of object proposals in the scene. It then tracks spatio-temporally consistent object proposals across multiple frames and produces a dense reconstruction of the scene. In parallel, the proposed system uses an efcient inference algorithm, where object class probabilities are computed at an object-level and fused into a voxel-based prediction hypothesis modeled on the voxels of the reconstructed scene. Our extensive experiments using challenging RGB-D object and scene datasets, and live video streams from Microsoft Kinect show that the proposed system achieved competitive 3D scene reconstruction and object labeling results compared to the state-of-the-art methods.

    AB - This paper presents an efcient system for simultaneous dense scene reconstruction and object labeling in real-world environments (captured with an RGB-D sensor). The proposed system starts with the generation of object proposals in the scene. It then tracks spatio-temporally consistent object proposals across multiple frames and produces a dense reconstruction of the scene. In parallel, the proposed system uses an efcient inference algorithm, where object class probabilities are computed at an object-level and fused into a voxel-based prediction hypothesis modeled on the voxels of the reconstructed scene. Our extensive experiments using challenging RGB-D object and scene datasets, and live video streams from Microsoft Kinect show that the proposed system achieved competitive 3D scene reconstruction and object labeling results compared to the state-of-the-art methods.

    U2 - 10.1109/ICRA.2016.7487374

    DO - 10.1109/ICRA.2016.7487374

    M3 - Conference paper

    SN - 9781467380256

    SP - 2255

    EP - 2262

    BT - 2016 IEEE International Conference on Robotics and Automation (ICRA)

    A2 - Kragic, Danica

    A2 - Okamura, Allison

    PB - IEEE, Institute of Electrical and Electronics Engineers

    CY - USA

    ER -

    Asif U, Bennamoun M, Sohel F. Simultaneous dense scene reconstruction and Object Labeling. In Kragic D, Okamura A, editors, 2016 IEEE International Conference on Robotics and Automation (ICRA). USA: IEEE, Institute of Electrical and Electronics Engineers. 2016. p. 2255-2262. 7487374 https://doi.org/10.1109/ICRA.2016.7487374