This paper presents a simple Forward Scattering Radar (FSR) and describes its application for automatic road vehicle classification. It introduces the radar itself and the targets classification system. For classification, the authors propose a system which extracts features from radar measurements, uses Fourier Transform and Principle Component Analysis (PCA) to transform these features prior to using the k-nearest neighbour classifier. By analysing 850 experimentally obtained car signatures, the effectiveness of the system is confirmed. This paper is a continuation of the work dedicated to the vehicles classification using FSR first introduced at the VehCom conference.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Progress on using principle component analysis in FSR for vehicle classification


    Additional title:

    Fortschritte bei der Anwendung der grundlegenden Komponenten-Analyse im System des vorwärts gerichteten Radars zur Fahrzeugklassifizierung


    Contributors:


    Publication date :

    2005


    Size :

    5 Seiten, 6 Bilder, 3 Tabellen, 5 Quellen


    Type of media :

    Conference paper


    Type of material :

    Print


    Language :

    English




    Progress on Using Principle Component Analysis in FSR for Vehicle Classification

    Abdullah, R. S. A. R. / Cherniakov, M. / Jancovic, P. et al. | British Library Conference Proceedings | 2005



    Texture resynthesis using principle component analysis [4662-53]

    Haenselmann, T. / Effelsberg, W. / SPIE- the International Society for Optical Engineering et al. | British Library Conference Proceedings | 2002


    Face Recognition using Principle Component Analysis, Eigenface and Neural Network

    Agarwal, M. / Jain, N. / Kumar, M. et al. | British Library Conference Proceedings | 2009


    Principal component analysis-based learning for preceding vehicle classification

    Mangai, Muthulingam Alarmel / Gounden, Nanjappagounder Ammasai | IET | 2014

    Free access