Automatic construction of a recurrent neural network based classifier for vehicle passage detection

Evgeny Burnaev, Ivan Koptelov, German Novikov, Timur Khanipov

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    7 Citations (Scopus)

    Abstract

    Recurrent Neural Networks (RNNs) are extensively used for time-series modeling and prediction. We propose an approach for automatic construction of a binary classifier based on Long Short-Term Memory RNNs (LSTM-RNNs) for detection of a vehicle passage through a checkpoint. As an input to the classifier we use multidimensional signals of various sensors that are installed on the checkpoint. Obtained results demonstrate that the previous approach to handcrafting a classifier, consisting of a set of deterministic rules, can be successfully replaced by an automatic RNN training on an appropriately labelled data.

    Original languageEnglish
    Title of host publicationNinth International Conference on Machine Vision, ICMV 2016
    EditorsDmitry P. Nikolaev, Antanas Verikas, Jianhong Zhou, Petia Radeva, Wei Zhang
    PublisherSPIE
    Volume10341
    ISBN (Electronic)9781510611313
    DOIs
    Publication statusPublished - 2017
    Event9th International Conference on Machine Vision, ICMV 2016 - Nice, France
    Duration: 18 Nov 201620 Nov 2016

    Publication series

    NameProceedings of SPIE - The International Society for Optical Engineering
    Volume10341
    ISSN (Print)0277-786X
    ISSN (Electronic)1996-756X

    Conference

    Conference9th International Conference on Machine Vision, ICMV 2016
    Country/TerritoryFrance
    CityNice
    Period18/11/1620/11/16

    Keywords

    • Classification
    • Recurrent Neural Networks
    • Time-Series

    Fingerprint

    Dive into the research topics of 'Automatic construction of a recurrent neural network based classifier for vehicle passage detection'. Together they form a unique fingerprint.

    Cite this