• 2024 (Vol.38)
  • 1990 (Vol.4)
  • 1989 (Vol.3)
  • 1988 (Vol.2)
  • 1987 (Vol.1)

Volume 31 #1

Contents

  1. Sensory properties of reward pattern affect food preferences in rats
  2. Probable role of p38 MAP-kinase in reception of infrared irradiation
  3. Investigation of Src-kinase inhibitor PP2 effects on modulation of slow sodium channels by ouabain
  4. Perimetric assessment of a blind zone margin at the extreme periphery of human temporal retina
  5. LogMAR for visual acuity is worse than horsepower for electric lamp
  6. Bright light induced freezing behavior in American cockroach, Periplaneta americana
  7. Analysis of human eye movements in the management of self-propelled chassis with video eye-tracking interface system
  8. Mechanisms of transduction of olfactory signals: the possible role of the contractive apparatus of the olfactory ciliae
  9. Architecture of a system for computer vision-based vehicle detection and classification under natural conditions
  10. Localization of a stereo camera equipped robot using poles with known location as landmarks

Architecture of a system for computer vision-based vehicle detection and classification under natural conditions

© 2017 A. Grigoryev, S. Gladilin, T. Khanipov, I. Koptelov, D. Bocharov, D. Matsnev

Institute for Information Transmission Problems RAS 127051 Moscow, Bolshoi Karetny per., 19
Moscow Institute of Physics and Technology 141701 Moscow region, Dolgoprudny, Institutskii per., 9

Received 12 Oct 2016

In this work we explore the architecture of a system for moving object detection and classi cation under outdoor observation conditions with xed scene geometry using the example of the vision-based automatic vehicle classi er (AVC). We consider the evolutionary development of the system from the prototype to a mature product achieving high classi cation quality under wide range of natural conditions. Based on the analysis of the AVC, we propose a model software architecture applicable in development of a wide range of industrial computer vision systems that allows to gradually increase the complexity and functionality of the system on the way from an early prototype to a mature product.

Key words: software architecture, computer vision, moving object classification, multicriterial classification, vehicle classification, axle counting, Viola-Jones detector, pattern recognition

Cite: Grigoryev A., Gladilin S., Khanipov T., Koptelov I., Bocharov D., Matsnev D. Arkhitektura sistemy detektsii i klassifikatsii avtomobilei sredstvami tekhnicheskogo zreniya v estestvennykh usloviyakh [Architecture of a system for computer vision-based vehicle detection and classification under natural conditions]. Sensornye sistemy [Sensory systems]. 2017. V. 31(1). P. 72-84 (in Russian).

References:

  • Gladilin S., Grigoryev A., Kotov A., Nikolaev D. Viola-Jones algorithm implementation in OpenCL // Trudy ISA RAN. 2014а. V. 64. No 4. P. 97–105 [in Russian]
  • Gladilin S.A., Kotov A.A., Nikolaev D.P., Usilin S.A. Postroenie ustoychivykh priznakov detekcii i klassifikacii objektov, ne obladajushchikh kharakternymi yarkostnymi kontrastami // Informacionnye tekhnologii i vychislitel’nye sistemy. 2014б. No 1. P. 61–72 [in Russian].
  • Kuroptev A.V., Nikolaev D.P., Postnikov V.V. Tochnaya lokalizaciya opornykh reshetok poley zapolneniya v anketakh metodami dinamicheskogo programmirovaniya I morfologicheskoy ltracii // Trudy ISA RAN. 2013. V. 63 No 3. P. 111–116 [in Russian].
  • Maljugina O., Nikolaev D. Kriterii ocenki kachestva dlja potokovoj sistemy obnaruzhen a i klassi kacii // 39th Conf. School Informat. Technol. Syst. 2015. P. 414–427 [in Russian].
  • Bocharov D., Sidorchuk D., Konovalenko I., Koptelov I. Vehicle passes detector based on multi-sensor analysis // Proc. SPIE. 7th Int. Conf. Machine Vision. 2015. V. 9445, 944510. P. 1–5.
  • Ejiri M. Machine vision in early days: Japan’s pioneering contributions // Asian Conf. Comp. Vision. 2007. P. 35–53.
  • Grigoryev A., Bocharov D., Terekhin A., Nikolaev D. Vision-based vehicle wheel detector and axle counter // Proc. 29th Europ. Conf. Model. Simulat. 2015. P. 521– 526.
  • Grigoryev A., Khanipov T., Koptelov I., Bocharov D., Postnikov V., Nikolaev D. Building a robust vehicle detection and classi cation module // Proc. SPIE. 8th Int. Conf. Machine Vision. 2015. V. 9875. 98751J. P. 1–7.
  • Khanipov T., Koptelov I., Grigoryev A., Kuznetsova E., Nikolaev D. Vision-based industrial automatic vehicle classi er // Proc. SPIE. 7th Int. Conf. Machine Vision. 2015. V. 9445, 944511. P. 1–5.
  • Kuznetsova E., Shvets E., Nikolaev D. Viola-Jones based hybrid framework for real-time object detection in multispectral images // Proc. SPIE. 8th Int. Conf. Machine Vision. 2015. V. 9875. 98750N. P. 1–6.
  • Levashov A., Yurin D. Accurate and reliable framework for fast parametric curves detection // 8th Open GermanRussian Workshop Pattern Recogn. Image Understand. 2011. P. 178–181.
  • Minkina A., Nikolaev D., Usilin S., Kozyrev V. Generalization of the Viola-Jones method as a decision tree of strong classi ers for real-time object recognition in video stream // Proc. SPIE. 7th Int. Conf. Machine Vision. 2015. V. 9445, 944517. P. 1–5.
  • Nikolaev D., Karpenko S., Nikolaev I., Nikolaev P. Hough transform: Understimated tool in the computer vision eld // Proc. 22th Europ. Conf. Model. Simulat. 2008. P. 238–246.
  • Taylor J. Smooth transition exponential smoothing // J. Forecasting. 2004. V. 23. No 6. P. 385–404.
  • Viola P., Jones M. Robust real-time face detection // Int. J. Comp. Vision. 2004. V. 57. No 2. P. 137–154.