2nd International ICST Conference on Mobile Multimedia Communications

Research Article

Human expert modelling using semantics-oriented video retrieval for surveillance in hard industry

  • @INPROCEEDINGS{10.1145/1374296.1374322,
        author={Pavel Praks  and Jindřich Černohorsk\"{y} and Vojtěch Sv\^{a}tek},
        title={Human expert modelling using semantics-oriented video retrieval for surveillance in hard industry},
        proceedings={2nd International ICST Conference on Mobile Multimedia Communications},
        publisher={ACM},
        proceedings_a={MOBIMEDIA},
        year={2006},
        month={9},
        keywords={surveillance application industrial automation information retrieval multidimensional data dimension reduction numerical linear algebra Singular Value Decomposition (SVD) ∗ Also Dept. of Mathematics and Descriptive Geometry Dept. of Applied Mathematics Center of Quality and Reliability of Production VˇSB - Technical University of Ostrava 17. listopadu 15 708 33 Ostrava Czech Republic † Also Centre of Applied Cybernetics partial symmetric eigenproblem very large systems of linear equations iterative solvers},
        doi={10.1145/1374296.1374322}
    }
    
  • Pavel Praks
    Jindřich Černohorský
    Vojtěch Svátek
    Year: 2006
    Human expert modelling using semantics-oriented video retrieval for surveillance in hard industry
    MOBIMEDIA
    ACM
    DOI: 10.1145/1374296.1374322
Pavel Praks 1,*, Jindřich Černohorský2,*, Vojtěch Svátek1,*
  • 1: University of Economics, Prague, Czech Republic
  • 2: Technical University of Ostrava, Ostrava, Czech Republic
*Contact email: pavel.praks@vsb.cz, jindrich.cernohorsky@vsb.cz, svatek@vse.cz

Abstract

The surveillance application aims at improving the quality of technology via modelling human expert behaviour in the coking plant Mittal Steel Ostrava, the Czech Republic. Video data on several industrial processes are captured by means of a CCD camera and classified by using Latent Semantic Indexing (LSI) with the respect to etalons classified by an expert. We also investigate the possibility to combine LSI with color histogram analysis, using experience from our prior research on web image classification.