This paper presents a vision-based approach with unsupervised learning for robust, accurate and stable detection of the drivable road to deal with autonomous driving in changing environments. This approach is based on a formulation of stereo with homography as a Maximum A Posteriori (MAP) problem in a Markov Random Field (MRF). Under this formulation, we develop an alternating optimization algorithm that alternates between computing the binary labeling and learning the optimal parameters from the stereo pair itself. The labeling is optimized by minimizing a well-defined energy function that consists of matching energy, smoothness energy and tracking energy. The parameters, including nine homography parameters and four MRF parameters, are learned online by applying a hard Expectation Maximization (EM) algorithm to maximize conditional likelihood. The proposed automatic parameter tuning procedure not only improves the accuracy of road detection but also makes the approach adaptive to changing environments without any a priori knowledge of the road. Experimental results show the optimality as well as adaptability of the proposed approach on a wide variety of challenging roads with changing environments.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    MRF-based road detection with unsupervised learning for autonomous driving in changing environments


    Contributors:


    Publication date :

    2010-06-01


    Size :

    1087233 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    MRF-Based Road Detection with Unsupervised Learning for Autonomous Driving in Changing Environments, pp. 361-368

    Guo, C. / Mita, S. / McAllester, D. et al. | British Library Conference Proceedings | 2010


    Deep Learning-based Road Object Detection for Collision Avoidance in Autonomous Driving

    Sharma, Teena / Chehri, Abdellah / Fofana, Issouf et al. | IEEE | 2024


    LEARNING UNSUPERVISED WORLD MODELS FOR AUTONOMOUS DRIVING VIA DISCRETE DIFFUSION

    ZHANG LUNJUN / XIONG YUWEN / YANG ZE et al. | European Patent Office | 2025

    Free access

    Autonomous driving control parameter changing device and autonomous driving control parameter changing method

    SHIMOTANI MITSUO / NAKAMURA YOSHITAKA / MIYAHARA TADASHI et al. | European Patent Office | 2021

    Free access

    Off-road autonomous driving

    LU JIANBO / HROVAT DAVOR DAVID / TSENG HONGTEI ERIC | European Patent Office | 2017

    Free access