A system and method that includes training a classifier using uniquely defined landmark points along the windshield region based on an elastic deformation model. The deformation model uses mixtures of trees with a shared pool of parts and can be globally optimized with dynamic programming and still capture much relevant global elastic structure. Once a candidate area is identified in the scene, a learned threshold is applied to the classification score of the candidate area to determine if the candidate area is a windshield. The identified area is then cropped out for further downstream process.


    Access

    Download


    Export, share and cite



    Title :

    Robust windshield detection via landmark localization


    Contributors:
    XU BEILEI (author) / ARTAN YUSUF O (author) / PAUL PETER (author)

    Publication date :

    2017-04-25


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    G06K Erkennen von Daten , RECOGNITION OF DATA / G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS / H04N PICTORIAL COMMUNICATION, e.g. TELEVISION , Bildübertragung, z.B. Fernsehen



    ROBUST WINDSHIELD DETECTION VIA LANDMARK LOCALIZATION

    XU BEILEI / ARTAN YUSUF O / PAUL PETER | European Patent Office | 2017

    Free access

    Robust Facial Landmark Localization for Automotive Applications

    Schäfer, Manuel / Tarayan, Emin / Kreßel, Ulrich | Springer Verlag | 2016


    Robust GPS-Vision Localization via Integrity-Driven Landmark Attention

    Sriramya Bhamidipati / Grace Gao | DOAJ | 2022

    Free access

    WINDSHIELD AND WINDSHIELD ASSEMBLY

    TSO FAI / ZHANG JIELIN / ZHANG XIAORONG et al. | European Patent Office | 2023

    Free access

    Windshield and windshield assembly

    CAO HUI / ZHANG JIELIN / ZHANG XIAORONG et al. | European Patent Office | 2024

    Free access