Detection of vehicles moving in wrong direction

• Autorzy: Bazan M. , Ciskowski P. , Halawa K. , Janiczek T. , Rusiecki A. , Śmigowski M.
• Języki publikacji: EN

Abstrakty

EN

In this paper we describe a method for detecting situations where a vehicle moves along a highway in the wrong direction. The first step of the algorithm is to build a pattern using Gaussian mixture model based on the optical flow calculated with the Lucas-Kanade method. The second stage concerns the detection of objects as a potential road hazard. The optical flow calculated on-line during the second stage is compared with the traffic pattern used in the first stage. Then the difference in movement direction is detected using predefined thresholds.

Słowa kluczowe

EN

optical flow; wrong direction driving incidents detection; Lucas-Kanade method

PL

przepływ optyczny; wykrywanie jazdy pod prąd; metoda Lucasa-Kanade

• Wydawca: Polskie Stowarzyszenie Telematyki Transportu
• Czasopismo: Archives of Transport System Telematics
• Rocznik: 2016
• Tom: Vol. 9, iss. 1
• Strony: 3--9
• Opis fizyczny: Bibliogr. 9 poz.

Twórcy

autor

Bazan M.

• Wrocław University Of Technology, Faculty of Electronics, Department of Computer Engineering, ul. Janiczewskiego 11/17, 50-372 Wrocław, Poland

autor

Ciskowski P.

• Wrocław University Of Technology, Faculty of Electronics, Department of Computer Engineering, ul. Janiczewskiego 11/17, 50-372 Wrocław, Poland

autor

Halawa K.

• Wrocław University Of Technology, Faculty of Electronics, Department of Computer Engineering, ul. Janiczewskiego 11/17, 50-372 Wrocław, Poland

autor

Janiczek T.

• Wrocław University Of Technology, Faculty of Electronics, Department of Computer Engineering, ul. Janiczewskiego 11/17, 50-372 Wrocław, Poland

autor

Rusiecki A.

• Wrocław University Of Technology, Faculty of Electronics, Department of Computer Engineering, ul. Janiczewskiego 11/17, 50-372 Wrocław, Poland

autor

Śmigowski M.

• Wrocław University Of Technology, Faculty of Electronics, Department of Computer Engineering, ul. Janiczewskiego 11/17, 50-372 Wrocław, Poland

Bibliografia

• [1] SAETERN T. L.: Wrong-Way Driving Prevention Methods, Sacramento: Caltrans, 2015.
• [2] BRADSKI G., KAEHLER A.: Learning OpenCV, p. 322-337, Sebastopol: O’Reilly, 2008.
• [3] BARRON J.L., FLEET D.J., BEAUCHEMIN S.S.: Performance of optical flow techniques, International Journal of Computer Vision, Volume 12, p. 43-77, 1994).
• [4] LUCAS B., KANADE T.,: An iterative image registration technique with an application to stereo vision, DARPA Image Understanding Workshop, p. 121-130, 1981).
• [5] FORESTI G.: Object detection and tracking in time-varying and badly illuminated outdoor environments, SPIE Journal on Optical Engineering, Volume 37, p. 2550-2564, 1998.
• [6] PAŁCZYNSKI K.: Segmentacja na podstawie analizy pola ruchu sekwencji obrazów cyfrowych, Praca Dyplomowa, Krąków: Akademia Górniczo-Hutnicza im. Stanisława Staszica, 2002.
• [7] FLEET D.J., WEISS T.: Optical flow estimation, Mathematical models for Computer Vision: The Handbook, s. 239-257, 2005.
• [8] MONTEIRO G., et al.: Wrong way drivers detection based on optical flow, Image Processing, San Antonio, Volume V, s. 141-144, 2007.
• [9] HUPTAS R.: Zastosowanie algorytmu EM do estymacji parametrów rozkładu na podstawie danych pogrupowanych, Zeszyty Naukowe Akademii Ekonomicznej w Krakowie 2007 .