Despite the impressive progress brought by deep network in visual object recognition, robot vision is still far from being a solved problem. The most successful convolutional architectures are developed starting from ImageNet, a large scale collection of images of object categories downloaded from the Web. This kind of images is very different from the situated and embodied visual experience of robots deployed in unconstrained settings. To reduce the gap between these two visual experiences, this paper proposes a simple yet effective data augmentation layer that zooms on the object of interest and simulates the object detection outcome of a robot vision system. The layer, that can be used with any convolutional deep architecture, brings to an increase in object recognition performance of up to 7{\%}, in experiments performed over three different benchmark databases. An implementation of our robot data augmentation layer has been made publicly available.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Bridging Between Computer and Robot Vision Through Data Augmentation: A Case Study on Object Recognition



    Erscheinungsdatum :

    2017-01-01



    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Invariant Object Recognition Robot Vision System for Assembly

    Pena, M. / Lopez, I. / Osorio, R. | IEEE | 2006


    Computer Vision Based Object Tracking for Multiple Robot Collaboration

    Chikurtev, Denis / Yovchev, Kaloyan | TIBKAT | 2022


    Computer Vision Based Object Tracking for Multiple Robot Collaboration

    Chikurtev, Denis / Yovchev, Kaloyan | Springer Verlag | 2022


    Monocular Vision Based Object Recognition and Tracking for Intelligent Robot

    Gao, Qian / Zhang, Lilian / Hu, Xiaoping et al. | British Library Conference Proceedings | 2017


    Recognition of bus stops through computer vision

    Franke, U. / Ismail, A. | IEEE | 2003