Intelligent Transportation System is a worldwide research hotspot and the extraction of traffic parameters is a crucial part of it for subsequent identification of traffic states. This paper proposes a novel approach of extracting traffic parameters such as time occupancy, volume and vehicle velocity based on video images. Visual features obtained from spatio-temporal images are more immune to environmental variations which including illuminations and background. Also binaryzation with Self-adaptive Threshold based on clustering can segment vehicle areas more accurately. With combination of parameters modification, PVI and EPI analysis serve to extract final parameters even when congestion happens. To testify the efficacy of measurement, extracted parameters are input to classifier of Support Vector Machine (SVM) to identify four levels of traffic states, which are fluent, non-congestion, congestion and terrible congestion respectively. Experimental results show that performance can sustain various environmental conditions and the accuracy is robust in heavy traffic states.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Novel Approach of Extracting Traffic Parameters by Using Video Features


    Contributors:
    Zhang, Yuan (author) / Jia, Kebin (author)


    Publication date :

    2013-10-01


    Size :

    276269 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    A New Video-Based Approach to Extract Traffic State Parameters for Traffic Surveillance

    Wang, G. / Xiao, D. / China Communications and Transportation Association; Transportation & Development Institute (American Society of Civil Engineers) | British Library Conference Proceedings | 2007


    Extracting road features from color images using a cognitive approach

    Rotaru, C. / Graf, T. / Jianwei Zhang, | IEEE | 2004


    A Machine Learning Pipeline for Extracting Decision-Support Features from Traffic Scenes

    Fraga, Vitor / Schreiber, Lincoln / Kunst, Rafael et al. | TIBKAT | 2022

    Free access

    MPP1.04 Extracting Road Features from Color Images using a Cognitive Approach

    Rotaru, C. / Graf, T. / Zhang, J. et al. | British Library Conference Proceedings | 2004