A Smart Traffic Volume Measurement Based on Deep Learning

International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 1, pp. 318-324, January 2026.

https://doi.org/10.58482/ijersem.v2i1.43

This work is licensed under a Creative Commons Attribution 4.0 International License.

A Smart Traffic Volume Measurement Based on Deep Learning

Full Text PDF

B Hima Bindhu

M Nandini

T Navaneetha

B Kedharinath Reddy

VS Zuberuddin Ali

S Dhanush

1-5Department of CSE, Siddartha Institute of Science and Technology, Puttur, India.

6Professor & Head, Department of Mechanical Engineering, Siddartha Institute of Science and Technology, Puttur, India.

Abstract: The detection and monitoring of autonomous vehicles are essential components of intelligent transportation management and control systems. By using the latest advancements in machine learning and deep learning, computers can detect, classify, and track multiple objects from captured images or videos. This paper uses the AdaBoost algorithm to create an intelligent, reliable, and efficient vehicle detection and tracking system based on aerial images. Also, the segmentation techniques can be used to separate the targeted objects from other background elements. Finally, the paper is useful for detecting the traffic density, identifying the vehicles in traffic, and evaluating the traffic flow conditions on the road. The AdaBoost algorithm for traffic volume measurement presents a promising approach towards efficient and accurate traffic analysis. Its adaptability to various environmental conditions and scalability makes it well-suited for real-world applications in traffic management and urban planning. Based on experimental analysis, the proposed Ada Boost algorithm achieved a 95% accuracy in estimating the traffic density on the road.

Keywords: Convolutional Neural Network, Computer Vision, Deep Learning, Vehicle Counting, Traffic Volume.

References: 

  1. E. I. Vlahogianni, M. G. Karlaftis, and J. C. Golias, “Statistical methods for detecting nonlinearity and non-stationarity in univariate short-term time-series of traffic volume,” Transportation Research Part C Emerging Technologies, vol. 14, no. 5, pp. 351–367, Oct. 2006, doi: 10.1016/j.trc.2006.09.002.
  2. E. I. Vlahogianni, “Some Empirical Relations Between Travel Speed, Traffic Volume and Traffic Composition in Urban Arterials,” IATSS Research, vol. 31, no. 1, pp. 110–119, Jan. 2007, doi: 10.1016/s0386-1112(14)60189-8.
  3. L. K. Sturm, M. G. Duck, A. L. Bitar, Y. L. Polyachenko, and D. A. Campbell, “Measurement and analysis of foot traffic in a university hospital operating room,” American Journal of Infection Control, vol. 35, no. 5, pp. E155–E156, Jun. 2007, doi: 10.1016/j.ajic.2007.04.182.
  4. T. A. Schlacher and J. M. Morrison, “Beach disturbance caused by off-road vehicles (ORVs) on sandy shores: Relationship with traffic volumes and a new method to quantify impacts using image-based data acquisition and analysis,” Marine Pollution Bulletin, vol. 56, no. 9, pp. 1646–1649, Jul. 2008, doi: 10.1016/j.marpolbul.2008.06.008.
  5. M. Burger, A. Hegyi, and B. De Schutter, “Model-based speed limit control with different traffic state measurements,” IFAC Proceedings Volumes, vol. 41, no. 2, pp. 14072–14077, Jan. 2008, doi: 10.3182/20080706-5-kr-1001.02382.
  6. S. Weimer et al., “Mobile measurements of aerosol number and volume size distributions in an Alpine valley: Influence of traffic versus wood burning,” Atmospheric Environment, vol. 43, no. 3, pp. 624–630, Oct. 2008, doi: 10.1016/j.atmosenv.2008.10.034.
  7. M. Papageorgiou and P. Varaiya, “Link Vehicle-Count—the missing measurement for traffic control,” IFAC Proceedings Volumes, vol. 42, no. 15, pp. 224–229, Jan. 2009, doi: 10.3182/20090902-3-us-2007.0054.
  8. K. El-Basyouny and T. Sayed, “Safety performance functions with measurement errors in traffic volume,” Safety Science, vol. 48, no. 10, pp. 1339–1344, Jun. 2010, doi: 10.1016/j.ssci.2010.05.005.
  9. Y. -H. Cheng and Y.-S. Li, “Influences of traffic volumes and wind speeds on ambient ultrafine particle levels—Observations at a highway electronic toll collection (ETC) lane,” Atmospheric Environment, vol. 45, no. 1, pp. 117–122, Sep. 2010, doi: 10.1016/j.atmosenv.2010.09.038.
  10. F. Dobruszkes, M. Lennert, and G. Van Hamme, “An analysis of the determinants of air traffic volume for European metropolitan areas,” Journal of Transport Geography, vol. 19, no. 4, pp. 755–762, Dec. 2010, doi: 10.1016/j.jtrangeo.2010.09.003.
  11. F. Raspall, “Efficient packet sampling for accurate traffic measurements,” Computer Networks, vol. 56, no. 6, pp. 1667–1684, Dec. 2011, doi: 10.1016/j.comnet.2011.11.017.
  12. E. Nathanail, P. Kouros, and P. Kopelias, “Traffic volume responsive incident detection,” Transportation Research Procedia, vol. 25, pp. 1755–1768, Jan. 2017, doi: 10.1016/j.trpro.2017.05.136.
  13. P. Sekuła, N. Marković, Z. V. Laan, and K. F. Sadabadi, “Estimating historical hourly traffic volumes via machine learning and vehicle probe data: A Maryland case study,” Transportation Research Part C Emerging Technologies, vol. 97, pp. 147–158, Oct. 2018, doi: 10.1016/j.trc.2018.10.012.
  14. J. Xiao, Z. Xiao, D. Wang, J. Bai, V. Havyarimana, and F. Zeng, “Short-term traffic volume prediction by ensemble learning in concept drifting environments,” Knowledge-Based Systems, vol. 164, pp. 213–225, Nov. 2018, doi: 10.1016/j.knosys.2018.10.037.
  15. J. M. F. Barroso, J. L. Albuquerque-Oliveira, and F. M. Oliveira-Neto, “Correlation analysis of day-to-day origin-destination flows and traffic volumes in urban networks,” Journal of Transport Geography, vol. 89, p. 102899, Nov. 2020, doi: 10.1016/j.jtrangeo.2020.102899.
Download PDF

This article is part of Volume 2, Issue 1 (January 2026)