Control Systems and Computers, N3, 2020, Article 5

Control Systems and Computers, 2019, Issue 3 (287), pp. 50-59.

UDC 004.932

O.P. STELMAKH, PhD student of the Department of Computer-Aided Management and Data Processing Systems, National Technical University of Ukraine “Igor Sikorsky Kyiv Politechnic Institute”, 03056, Kyiv, Peremohy Ave 37, Ukraine,

I.V. STETSENKO, Doctor of Science, professor of the Department of Computer-Aided Management and Data Processing Systems, National Technical University of Ukraine “Igor Sikorsky Kyiv Politechnic Institute”, 03056, Kyiv, Peremohy Ave 37, Ukraine,

D.V. VELYHOTSKYI, Junior Researcher, Institute of Applied Problems of Physics & Biophysics, NAS of Ukraine, 03680, Kyiv, 3 V.Stepanchenko str., Ukraine,


Traffic jams are a huge problem for all road users and are caused by increasing traffic intensity and poor quality of traffic management systems. Systems that control traffic flows and decide to change control parameters must receive reliable and up-to-date data on traffic intensity. In order to accurately determine the traffic intensity, a system of automated video data processing from video surveillance cameras of the traffic lane is developed. The traffic intensity is determined by the developed method of obtaining the traffic congestion coefficient (TLCR) according to the data, obtained by processing the video frame using the U-Net neural network, and the following transformation of TLCR time series into traffic intensity time series. The newinformation technology implements an image processing algorithm to detect the presence of vehicles in a certain section of road, a method of determining the congestion of the lane (TLCR) and a method of determining the intensity of successive values of congestion of the lane.The experimental results show that the proposed information technology is able to identify traffic intensity with an accuracy of 99.35 percent.

Download full text! (In  English)

Keywords: Image Analysis, Traffic Intensity, Traffic Congestion Index, TLCR, Neural Network.

  1. Gani, M.H.H., Khalifa, O., Gunawan, T.S., Shamsan, E.,2017. Traffic Intensity Monitoring using Multiple Object Detection with Traffic Surveillance Cameras.2017 Ieee 4th International Conference on Smart Instrumentation, Measurement and Application (ICSIMA 2017), p. 5.
  2. Hoque, D.M.S., Ullah, M.A. and Nikraz, D.H., 2013. Investigation of Traffic Flow Characteristics of Dhaka-Sylhet Highway (N-2) of Bangladesh.International Journal of Civil Engineering and Technology, 4, no. 4, pp. 55-65.
  3. ISO 8824:2019. Avtomobilnidorogy. Vyznachennya intensyvnosti ruhu ta skladu transportnogo potoku [Highways. Determination of traffic intensity and composition of trafficflow].
  4. Agafonov, A. and Myasnikov, V., 2015. Traffic Flow Forecasting Algorithm Based on Combination ofAdaptive Elementary Predictors. Analysis of Images, Social Networks and Texts, 542, pp. 163-74.
  5. Logynova, O.A., Gatiyatov, R.R., 2019. “Obzor suschest vuyuschih metodov i tehnicheskih sredstv uchota intensivnosti dvizheniy atransportnogo potoka” [Review of existing methods and technical means for measuring trafficf low]. Tehnika i tehnologii transporta – Technique and technology of transport, no. 11, pp. 1-5. [inRussian]
  6. Pechatnova, Y. V., Matematicheskoye modelirovaniye kolebaniy sutochnoy intensivnosti dvizheniya. VestnikSibirskogoavtomobilno-dorozhnogounoversiteta- The Russian Automobileand Highway Industry Journal, Vol. 56-57, no. 4-5, pp. 145-151. [inRussian]
  7. Zhang, B., Wang, C., Zhang, H., Wu, F. and Tang, Y.X., 2017. Detectability Analysis of Road Vehicles in Radarsat-2 Fully Polarimetric SAR Images for Traffic Monitoring.Sensors, 17, no. 2, p. 23-36.
  8. Robinson E. M., CrimeScenePhotography. Academic Press: Elsevier.
  9. Fernandez-Caballero, A., Gomez, F.J. and Lopez-Lopez, J., 2008. Road-traffic monitoring by knowledge-driven static and dynamic image analysis.Expert Systems with Applications, 35, no. 3, pp. 701-719.
  10. Fernandez-Caballero, A., Mira, J., Fernandez, M.A. and Lopez, M.T., 2001. Segmentation from motion of non-rigid objects by neuronal lateral interaction.Pattern Recognition Letters, 22, no. 14, pp. 1517-24.
  11. Videodetektirovaniye.Available at:<> [Accessed 28 June 2020].
  12. Stetsenko, I. and Stelmakh, O., 2020. Traffic Lane Congestion Ratio Evaluation by Video Data. Advances in Intelligent Systems and Computing, 1019, pp. 172-181.
  13. Ronneberger, O., Fischer, P. and Brox, T., 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation.Medical Image Computing and Computer-Assisted Intervention, 9351, pp. 234-241.
  14. OpenCV Documentation. StructuralAnalysisandShapeDescriptors. Available at:<>[Accessed 28 June 2020].
  15. Stetsenko, I.V. 2010. Modelyuvannyasystem [Systemssimulation] Cherkassy: CDTU.
  16. Chen, Y. and Hu, W., Robust Vehicle Detection and Counting Algorithm Adapted to Complex Traffic Environments with Sudden Illumination Changes and Shadows. Sensors, 20 (9), pp. 21-42.

Received 25.05.2020