Vestnik Yuzhno-Ural'skogo Universiteta. Seriya Matematicheskoe Modelirovanie i Programmirovanie
RUS  ENG    JOURNALS   PEOPLE   ORGANISATIONS   CONFERENCES   SEMINARS   VIDEO LIBRARY   PACKAGE AMSBIB  
General information
Latest issue
Archive
Submit a manuscript

Search papers
Search references

RSS
Latest issue
Current issues
Archive issues
What is RSS



Vestnik YuUrGU. Ser. Mat. Model. Progr.:
Year:
Volume:
Issue:
Page:
Find






Personal entry:
Login:
Password:
Save password
Enter
Forgotten password?
Register


Vestnik YuUrGU. Ser. Mat. Model. Progr., 2020, Volume 13, Issue 4, Pages 94–106 (Mi vyuru574)  

Programming & Computer Software

Training Viola–Jones detectors for 3D objects based on fully synthetic data for use in rescue missions with UAV

S. A. Usilinabc, V. V. Arlazarovcdba, N. S. Rokhline, S. A. Rudykae, S. A. Matveeve, A. A. Zatsarinnyya

a Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences, Moscow, Russian Federation
b Moscow Institute of Physics and Technology, Moscow, Russian Federation
c Smart Engines Service LLC, Moscow, Russian Federation
d Institute for Information Transmission Problems (Kharkevich Institute) of the Russian Academy of Sciences, Moscow, Russian Federation
e Baltic State Technical University “VOENMEH” named after D.F. Ustinov, St. Petersburg, Russian Federation

Abstract: In this paper, the problem of training the Viola–Jones detector for 3D objects is considered on the example of an inflatable life raft PSN-10. The detector is trained on a fully synthetic training dataset. The paper discusses in detail the methods of modelling an inflatable life raft, water surface, various weather conditions. As a feature space, we use edge Haar-like features, which allow training the detector that is resistant to various lighting conditions. To increase the computational efficiency, the L1 norm is used to calculate the magnitude of the image gradient. The performance of the trained detector is estimated on real data obtained during the rescue operation of the trawler “Dalniy Vostok”. The proposed method for training the Viola–Jones detectors can be successfully used as a component of hardware and software “assistants” of the UAV.

Keywords: machine learning, object detection, Viola–Jones, classification, 3D object, UAV, rescue mission.

Funding Agency Grant Number
Ministry of Science and Higher Education of the Russian Federation 074-11-2018-025


DOI: https://doi.org/10.14529/mmp200408

Full text: PDF file (427 kB)
References: PDF file   HTML file

MSC: 68T10
Received: 11.09.2020
Language:

Citation: S. A. Usilin, V. V. Arlazarov, N. S. Rokhlin, S. A. Rudyka, S. A. Matveev, A. A. Zatsarinnyy, “Training Viola–Jones detectors for 3D objects based on fully synthetic data for use in rescue missions with UAV”, Vestnik YuUrGU. Ser. Mat. Model. Progr., 13:4 (2020), 94–106

Citation in format AMSBIB
\Bibitem{UsiArlRok20}
\by S.~A.~Usilin, V.~V.~Arlazarov, N.~S.~Rokhlin, S.~A.~Rudyka, S.~A.~Matveev, A.~A.~Zatsarinnyy
\paper Training Viola--Jones detectors for 3D objects based on fully synthetic data for use in rescue missions with UAV
\jour Vestnik YuUrGU. Ser. Mat. Model. Progr.
\yr 2020
\vol 13
\issue 4
\pages 94--106
\mathnet{http://mi.mathnet.ru/vyuru574}
\crossref{https://doi.org/10.14529/mmp200408}
\elib{https://elibrary.ru/item.asp?id=44541965}


Linking options:
  • http://mi.mathnet.ru/eng/vyuru574
  • http://mi.mathnet.ru/eng/vyuru/v13/i4/p94

    SHARE: VKontakte.ru FaceBook Twitter Mail.ru Livejournal Memori.ru


    Citing articles on Google Scholar: Russian citations, English citations
    Related articles on Google Scholar: Russian articles, English articles
  • Number of views:
    This page:28
    Full text:22
    References:1

     
    Contact us:
     Terms of Use  Registration to the website  Logotypes © Steklov Mathematical Institute RAS, 2021