3D Recognition and Segmentation of Objects in Cluttered Scenes

    Research output: Chapter in Book/Conference paperConference paper

    Abstract

    In this paper we present a novel viewpoint independent range image segmentation and recognition approach. We generate a library of 3D models off-line and represent each model with our tensor-based representation. Tensors represent local surface patches of the models and are indexed by a 4D hash table. During the online phase, a seed point is randomly selected from the range image and its neighbouring surface is represented with a tensor. This tensor is simultaneously matched with all the tensors of the library models using a voting scheme. The model which receives the most votes is hypothesized to be present in the scene. The model from the library is then transformed to the range image coordinates. If the model aligns accurately with a portion of the range image, that portion is recognized, segmented and removed. Another seed point is picked from the remaining range image and the matching process is repeated until the entire scene is segmented or no further library objects can be recognized in the scene. Our experiments show that this novel algorithm is efficient and it gives accurate results for cluttered and occluded range images
    Original languageEnglish
    Title of host publicationSeventh IEEE Workshop on Applications of Computer Vision
    EditorsDeeber Azada
    Place of PublicationLos Alamitos, California USA
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages8-13
    Volume1
    ISBN (Print)0769522718
    Publication statusPublished - Jan 2005
    Event3D Recognition and Segmentation of Objects in Cluttered Scenes - Breckenridge, Colorado, USA
    Duration: 1 Jan 2005 → …

    Conference

    Conference3D Recognition and Segmentation of Objects in Cluttered Scenes
    Period1/01/05 → …

    Fingerprint

    Tensors
    Seed
    Image recognition
    Image segmentation
    Experiments

    Cite this

    Mian, A., Bennamoun, M., & Owens, R. (2005). 3D Recognition and Segmentation of Objects in Cluttered Scenes. In D. Azada (Ed.), Seventh IEEE Workshop on Applications of Computer Vision (Vol. 1, pp. 8-13). Los Alamitos, California USA: IEEE, Institute of Electrical and Electronics Engineers.
    Mian, Ajmal ; Bennamoun, Mohammed ; Owens, Robyn. / 3D Recognition and Segmentation of Objects in Cluttered Scenes. Seventh IEEE Workshop on Applications of Computer Vision. editor / Deeber Azada. Vol. 1 Los Alamitos, California USA : IEEE, Institute of Electrical and Electronics Engineers, 2005. pp. 8-13
    @inproceedings{74b179a299bc42159827a0727e368e91,
    title = "3D Recognition and Segmentation of Objects in Cluttered Scenes",
    abstract = "In this paper we present a novel viewpoint independent range image segmentation and recognition approach. We generate a library of 3D models off-line and represent each model with our tensor-based representation. Tensors represent local surface patches of the models and are indexed by a 4D hash table. During the online phase, a seed point is randomly selected from the range image and its neighbouring surface is represented with a tensor. This tensor is simultaneously matched with all the tensors of the library models using a voting scheme. The model which receives the most votes is hypothesized to be present in the scene. The model from the library is then transformed to the range image coordinates. If the model aligns accurately with a portion of the range image, that portion is recognized, segmented and removed. Another seed point is picked from the remaining range image and the matching process is repeated until the entire scene is segmented or no further library objects can be recognized in the scene. Our experiments show that this novel algorithm is efficient and it gives accurate results for cluttered and occluded range images",
    author = "Ajmal Mian and Mohammed Bennamoun and Robyn Owens",
    year = "2005",
    month = "1",
    language = "English",
    isbn = "0769522718",
    volume = "1",
    pages = "8--13",
    editor = "Deeber Azada",
    booktitle = "Seventh IEEE Workshop on Applications of Computer Vision",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    address = "United States",

    }

    Mian, A, Bennamoun, M & Owens, R 2005, 3D Recognition and Segmentation of Objects in Cluttered Scenes. in D Azada (ed.), Seventh IEEE Workshop on Applications of Computer Vision. vol. 1, IEEE, Institute of Electrical and Electronics Engineers, Los Alamitos, California USA, pp. 8-13, 3D Recognition and Segmentation of Objects in Cluttered Scenes, 1/01/05.

    3D Recognition and Segmentation of Objects in Cluttered Scenes. / Mian, Ajmal; Bennamoun, Mohammed; Owens, Robyn.

    Seventh IEEE Workshop on Applications of Computer Vision. ed. / Deeber Azada. Vol. 1 Los Alamitos, California USA : IEEE, Institute of Electrical and Electronics Engineers, 2005. p. 8-13.

    Research output: Chapter in Book/Conference paperConference paper

    TY - GEN

    T1 - 3D Recognition and Segmentation of Objects in Cluttered Scenes

    AU - Mian, Ajmal

    AU - Bennamoun, Mohammed

    AU - Owens, Robyn

    PY - 2005/1

    Y1 - 2005/1

    N2 - In this paper we present a novel viewpoint independent range image segmentation and recognition approach. We generate a library of 3D models off-line and represent each model with our tensor-based representation. Tensors represent local surface patches of the models and are indexed by a 4D hash table. During the online phase, a seed point is randomly selected from the range image and its neighbouring surface is represented with a tensor. This tensor is simultaneously matched with all the tensors of the library models using a voting scheme. The model which receives the most votes is hypothesized to be present in the scene. The model from the library is then transformed to the range image coordinates. If the model aligns accurately with a portion of the range image, that portion is recognized, segmented and removed. Another seed point is picked from the remaining range image and the matching process is repeated until the entire scene is segmented or no further library objects can be recognized in the scene. Our experiments show that this novel algorithm is efficient and it gives accurate results for cluttered and occluded range images

    AB - In this paper we present a novel viewpoint independent range image segmentation and recognition approach. We generate a library of 3D models off-line and represent each model with our tensor-based representation. Tensors represent local surface patches of the models and are indexed by a 4D hash table. During the online phase, a seed point is randomly selected from the range image and its neighbouring surface is represented with a tensor. This tensor is simultaneously matched with all the tensors of the library models using a voting scheme. The model which receives the most votes is hypothesized to be present in the scene. The model from the library is then transformed to the range image coordinates. If the model aligns accurately with a portion of the range image, that portion is recognized, segmented and removed. Another seed point is picked from the remaining range image and the matching process is repeated until the entire scene is segmented or no further library objects can be recognized in the scene. Our experiments show that this novel algorithm is efficient and it gives accurate results for cluttered and occluded range images

    M3 - Conference paper

    SN - 0769522718

    VL - 1

    SP - 8

    EP - 13

    BT - Seventh IEEE Workshop on Applications of Computer Vision

    A2 - Azada, Deeber

    PB - IEEE, Institute of Electrical and Electronics Engineers

    CY - Los Alamitos, California USA

    ER -

    Mian A, Bennamoun M, Owens R. 3D Recognition and Segmentation of Objects in Cluttered Scenes. In Azada D, editor, Seventh IEEE Workshop on Applications of Computer Vision. Vol. 1. Los Alamitos, California USA: IEEE, Institute of Electrical and Electronics Engineers. 2005. p. 8-13