Traffic light recognition is of great interest for advanced driver assistance systems and autonomous driving but still an unsolved problem. While a traffic light has few visual features for detection from camera images we believe the characteristic light represents a potentially very strong and stable feature. The traffic light is actively emitting light which is rarely influenced by weather or lighting condition. When using a color lookup table for an image segmentation-based object detector, the process of creating the lookup table is the crucial point. In this paper, we propose a method for generating a lookup table using real world data of a large dataset. The training data is sampled from labeled objects and stored as multisets. We contribute a frequency-based filtering method to clean the samples before using a k-nearest neighbor classifier to generalize. The result is stored as a three dimensional lookup table. The main contribution is a neighborhood-biasing technique that allows setting different operating points online without retraining. A challenging real world dataset containing several thousands of active lights is used to evaluate the process.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning Traffic Light Colors


    Beteiligte:


    Erscheinungsdatum :

    01.11.2018


    Format / Umfang :

    2690151 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Colors and forms of traffic signals

    Engineering Index Backfile | 1925



    Gratings separate the different colors of light

    Peach, L. A. | British Library Online Contents | 1997


    Automobile colors

    Hillick, M.C. | Engineering Index Backfile | 1910


    Inpainting the Colors

    Sapiro, G. | British Library Conference Proceedings | 2005