In the USA from 2014 the implementation of fisheye rear cameras will begin to become more widespread due to upcoming federal legislation. By adding Intelligence to such cameras, IAV GmbH has developed and performed a variety of reversing functions such as Pedestrian Detection and General Object detection. Such implementations will permit the OEM to introduce systems to help reduce the 6,000 or so reversing accidents involving children that currently take place each year in the USA alone. Pedestrian detection is a key problem in computer vision, with several applications including surveillance and automotive safety. Much of the progress of the past few years has been driven by the availability of challenging public datasets. Advanced vehicles equipped with camera vision based advanced driver assistance systems (ADAS) increase rapidly. IAV GmbH is now in Advanced Development for adding intelligent Driver Assistant Functions for fisheye rear mounted cameras. A real time vision-based system for driver assistance on-board vehicles is developed. Safety and ease-of-use of vehicles are the two central themes in this line of work. This paper focuses on the safety aspect and presents a prototype system for the detection of the most vulnerable traffic participants: pedestrian using a fisheye mounted camera. This paper proposes a robust rear-view camera based moving object detection algorithm for backup aid and parking assist applications. A single fish-eye camera is used in order to get much larger FOV (field of view) for object detection. The dataset contains richly annotated video, recorded directly from a vehicle, with challenging images of fisheye camera. IAV GmbH also benchmark several promising detection systems, providing an overview of state-of-the art performance and a direct, unbiased comparison of existing methods. Finally, by analysing common failure cases, IAV GmbH helps identify future research directions for the field.


    Zugriff

    Zugriff über TIB

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Object Detection and Classification Using a Rear In-Vehicle Fisheye Camera


    Beteiligte:
    Tadjine, HadjHamma (Autor:in) / Hess, Markus (Autor:in) / Karsten, Schulze (Autor:in)


    Erscheinungsdatum :

    2012


    Format / Umfang :

    10 Seiten





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch




    Object detection and classification using a rear in-vehicle fisheye camera

    Tadjine,H.H. / Hess,M. / Karsten,S. et al. | Kraftfahrwesen | 2012


    Object Detection and Classification Using a Rear In-Vehicle Fisheye Camera

    Tadjine, HadjHamma / Hess, Markus / Karsten, Schulze | Springer Verlag | 2012


    Object Detection and Classification Using a Rear In-Vehicle Fisheye Camera F2012-F07-009

    Tadjine, H. / Hess, M. / Karsten, S. et al. | British Library Conference Proceedings | 2013


    Rear obstacle detection system with fisheye stereo camera using HCT

    Kim, Deukhyeon / Choi, Jinwook / Yoo, Hunjae et al. | Tema Archiv | 2015


    Wide rear vehicle recognition using a fisheye lens camera image

    Jeong, Jin-Seong / Kim, Hyun-Tae / Kim, Bruce et al. | IEEE | 2016