This paper presents the development of a robot car that can track the motion of an object by detecting its color through an Android device. The employed computer vision algorithm uses the OpenCV library, which is embedded into an Android application of a smartphone, for manipulating the captured image of the object. The captured image of the object is subjected to color conversion and is transformed to a binary image for further processing after color filtering. The desired object is clearly determined after removing pixel noise by applying image morphology operations and contour definition. Finally, the area and the center of the object are determined so that object's motion to be tracked. The smartphone application has been placed on a robot car and transmits by Bluetooth to an Arduino assembly the motion directives so that to follow objects of a specified color. The experimental evaluation of the proposed algorithm shows reliable color detection and smooth tracking characteristics.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Object Motion Tracking Based On Color Detection for Android Devices


    Beteiligte:

    Erscheinungsdatum :

    2015-05-04


    Anmerkungen:

    oai:zenodo.org:1106025



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629




    Active Motion Detection and Object Tracking

    Denzler, J. / Paulus, D. W. R. / IEEE; Signal Processing Society | British Library Conference Proceedings | 1994


    Interference Detection Algorithms for GNSS-enabled Android Devices

    Valles, E. L. / Yu, C. / Elasmar, R. | British Library Conference Proceedings | 2015


    Pearson-based mixture model for color object tracking

    Ketchantang, W. | British Library Online Contents | 2008



    Affine object tracking with kernel-based spatial-color representation

    Haihong Zhang, / Weimin Huang, / Zhiyong Huang, et al. | IEEE | 2005