Advanced driver assistance systems (ADAS) become an integral part of almost all modern automotive systems. ADAS have been evolving over a decade and the expansion of vision‐based ADAS is quite rapid mainly due to the recent advancements in camera technologies. Most of the vision‐based ADAS applications have been developed focusing on structured environment parameters and being tested adequately for those environments whereas they cannot be applied with their current framework as such for non‐structured environments due to various limitations. This study presents a comprehensive overview of challenges in expanding the vision‐based ADAS for non‐structured environments. The authors have proposed a segmentation detection method for pedestrians and cyclists in a non‐structured road environment to improve the accuracy of the popular deep learning networks. This method uses upper body detection and a pairing technique that improves the average precision significantly without consuming much computational resources. This approach would help to transform the structured environment ADAS to non‐structured environments with minimal modifications. With the proposed approach, they are able to increase the accuracy of certain object classes up to 49% for various popular deep learning networks.


    Access

    Download


    Export, share and cite



    Camera Modeling for Vision-Based ADAS

    Zhang, Sumin / Deng, Weiwen / Wang, Ye et al. | SAE Technical Papers | 2015


    Camera modeling for vision-based ADAS

    Wang,Y. / Qu,Y. / Zhang,S. et al. | Automotive engineering | 2015


    Safety and ADAS - realising the vision

    Sampson,B. / Volvo,SE | Automotive engineering | 2015


    ADAS horizon and vision supplemental V2X

    SCHILLING ROBERT / NIST SCOTT A | European Patent Office | 2021

    Free access

    ADAS HORIZON AND VISION SUPPLEMENTAL V2X

    SCHILLING ROBERT / NIST SCOTT A | European Patent Office | 2019

    Free access