This paper presents the development of an automated intersection accident detection system via digital audio signal processing. Audio signals at busy intersections are the inputs to the system. The system is composed of three main signal processing stages: feature extraction, feature reduction, and classification. The results of the study show that the wavelet-based feature extraction in combination with the maximum likelihood classifier is the optimum design. The system is computationally inexpensive, and consistently results in accident detection accuracies of 95 % to 100 % with a very low false alarm rate in multiple stages of testing in the lab and also in a real-time real-world environment.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Development of an automated accident detection system at intersections


    Additional title:

    Die Entwicklung eines automatisierten Unfall-Erkennungs-Systems an Kreuzungen


    Contributors:


    Publication date :

    2004


    Size :

    5 Seiten, 9 Quellen


    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Development of an Automated Accident Detection System at Intersections

    Zhang, Y. / Hu, R. Q. / ASCE | British Library Conference Proceedings | 2004


    Automated Accident Detection in Intersections via Digital Audio Signal Processing

    Bruce, Lori Mann / Balraj, Navaneethakrishnan / Zhang, Yunlong et al. | Transportation Research Record | 2003



    Accident Detection at Intersections for ITS

    Stephanedes, Y. J. / Vasilakis, G. / American Society of Civil Engineers et al. | British Library Conference Proceedings | 1995