This paper presents a framework for learning of system parameters for vision-based lane detection systems. Learning is achieved by ground-truth data based optimization of a performance measure evaluated on video sequences. Different options for evaluating the performance of lane detection systems are discussed, and in order to allow for a linear combination, we show how these performance measures can be normalized. The approach presented is applied to the optimization of the state noise variances of a Kalman filter. The surroundings around the located solutions are examined by 2D-grid analysis. It turns out that this approach leads to the same regions for robust parametrizations independent on the starting conditions for the optimization, and thereby a well generalizing parameter set can be obtained.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Learning of Kalman Filter Parameters for Lane Detection


    Contributors:
    Suttorp, T. (author) / Bucher, T. (author)


    Publication date :

    2006-01-01


    Size :

    4457006 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Learning of Kalman Filter Parameters for Lane Detection

    Suttorp, T. / Bucher, T. | British Library Conference Proceedings | 2006


    Lane Detection Using Hough Transform and Kalman Filter

    Megalingam, Rajesh Kannan / Pradeep, Nidhin Chuzhiyil / Reghu, Aswin et al. | IEEE | 2024


    Robust lane-markings tracking algorithm based on boundary detection and Kalman filter

    Sun, Tsung-Ying / Huang, Wei-Chih / Tsai, Shang-Jeng | Tema Archive | 2008


    Kalman Particle Filter for Lane Recognition on Rural Roads

    Loose, H. / Franke, U. / Stiller, C. | British Library Conference Proceedings | 2009


    Kalman Particle Filter for lane recognition on rural roads

    Loose, Heidi / Franke, Uwe / Stiller, Christoph | IEEE | 2009