The development of any robotics application relying on visual information always raises the key question of what image features would be most informative about the motion to be performed. In this paper, we address this question in the context of visual robot positioning, where a neural network is used to learn the mapping between image features and robot movements, and global image descriptors are preferred to local geometric features. Using a statistical measure of variable interdependence called Mutual Information, subsets of image features most relevant for determining pose variations along each of the six degrees of freedom (dof's) of camera motion are selected. Four families of global features are considered: geometric moments, eigenfeatures, Local Feature Analysis vectors, and a novel feature called Pose-Image Covariance vectors. The experimental results described show the quantitative and qualitative benefits of performing this feature selection prior to training the neural network: Less network inputs are needed, thus considerably shortening training times; the dof's that would yield larger errors can be determined beforehand, so that more informative features can be sought; the order of the features selected for each dof often accepts an intuitive explanation, which in turn helps to provide insights for devising features tailored to each dof. ; This work was supported by the project 'Navegación basada en visión de robots autónomos en entornos no estructurados.' (070-724). This research has been partially supported by the research grant CICYT TAP97-1209 of the Spanish Science and Technology Council. ; Peer Reviewed


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Assessing image features for vision-based robot positioning


    Beteiligte:
    Wells, Gordon (Autor:in) / Torras, Carme (Autor:in)

    Erscheinungsdatum :

    2001-01-01


    Anmerkungen:

    doi:10.1023/A:1008198321503



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Vision-based robot positioning using neural networks

    Wells, G. / Venaille, C. / Torras, C. | British Library Online Contents | 1996


    Selection of image features for robot positioning using mutual information

    Wells, Gordon / Torras, Carme | BASE | 1998

    Freier Zugriff

    Vision-based robot positioning by an exact distance between histograms

    Serratosa, Francesc / Sanfeliu, Alberto | BASE | 2006

    Freier Zugriff

    Electric vehicle charging port positioning device based on robot vision

    HE YANG / SUN HUAIJUN / YAN GUOHUA | Europäisches Patentamt | 2021

    Freier Zugriff

    Binocular vision positioning method for target grabbing of underwater robot

    LUO WENBO / CAO YANCHAO / CHEN YUXING et al. | Europäisches Patentamt | 2024

    Freier Zugriff