• DocumentCode
    2603921
  • Title

    Vehicle speeding early warning model using frame feature detection and HMM

  • Author

    Lin, Chien-Chuan ; Wang, Ming-Shi

  • Author_Institution
    Dept. of Eng. Sci., Nat. Cheng Kung Univ., Tainan, Taiwan
  • fYear
    2011
  • fDate
    14-17 June 2011
  • Firstpage
    241
  • Lastpage
    244
  • Abstract
    The techniques of digital image analysis, features detection, and Hidden Markov Model are employed to develop a vehicle speed prediction system, which used to find the trend of the speed changed. The proposed vehicle speed prediction model is used to set up a vehicle speeding early warning model. The proposed vehicle speed early warning system includes the vehicle speed computation and prediction model. All the data source of this study is obtained by the special design vehicular digital video recorder device that includes well defined driving data format. The data of digital video recorder, which represented the driving state data of the vehicle the speed is included, are analyzed to set up the speed computation and prediction model. The proposed approaches can closely match the vehicle speed and its concurrent video frame. The results of this study can also provide other vehicular computer vision techniques to reduce the processing time along with vehicle´s speed.
  • Keywords
    computer vision; feature extraction; hidden Markov models; traffic engineering computing; video recording; digital image analysis; driving state data; frame feature detection; hidden Markov model; vehicle speeding early warning model; vehicular computer vision techniques; vehicular digital video recorder device; Computational modeling; Computer vision; Feature extraction; Hidden Markov models; Markov processes; Predictive models; Vehicles;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Consumer Electronics (ISCE), 2011 IEEE 15th International Symposium on
  • Conference_Location
    Singapore
  • ISSN
    0747-668X
  • Print_ISBN
    978-1-61284-843-3
  • Type

    conf

  • DOI
    10.1109/ISCE.2011.5973824
  • Filename
    5973824