Publication Details
Brno University of Technology at TRECVid 2013: Interactive Surveillance Event Detection
Mlích Jozef, Ing. (FIT)
Pešek Martin, Ing.
Volf Tomáš, Ing. (DIFS)
Zemčík Pavel, prof. Dr. Ing., dr. h. c. (DCGM)
Zendulka Jaroslav, doc. Ing., CSc. (UIFS)
In the paper, we describe ourexperiments in the interactive surveillance event detection pilot(SED) of the 2009 TRECVid evaluation. Our approach inheritsfunctionality of the Surveillance Network Augmented by Retrieval(SUNAR) system, which is an information retrieval based wide area(video) surveillance system being developed at Faculty of IT, BrnoUniversity of Technology. It contains both standard and experimentaltechniques evaluated at the AVSS 2009/10 Multi-Camera TrackingChallenge. We have deployed active learning functionality (Bayesian,SVM and HMM) based on moving objects' trajectory statistics and shapeclassification using Video Terror Application Programming Interface(VTApi), which was created to unify and accelerate the intelligentvision applications development.
@inproceedings{BUT192931,
author="Petr {Chmelař} and Jozef {Mlích} and Martin {Pešek} and Tomáš {Volf} and Pavel {Zemčík} and Jaroslav {Zendulka}",
title="Brno University of Technology at TRECVid 2013: Interactive Surveillance Event Detection",
booktitle="2013 TREC Video Retrieval Evaluation Notebook Papers and Slides",
year="2013",
pages="1--9",
address="Gaithersburg",
url="https://www.fit.vut.cz/research/publication/10485/"
}