Analysis and Evaluation of Vehicle Traffic Counting in inner-city Automatic Number Plate Recognition by Neural Network and Random Forest Models (Case Study: Mashhad-Metropolis)

Document Type : Original Article

Authors
Mohammad Amin Ebrahimzadeh 1
Navid Nakhaie 1
Mahdiseh Dabbaqi 1
Ali Abdi kordani 2
1 Ph.D., Candidate, Majoring in Transportation Planning, Faculty of Civil Engineering, Arts and Architecture, Tehran Science and Research, Tehran, Iran.
2 Professor, Department of Civil Engineering, Faculty of Technical and Engineering, Imam Khomeini International University, Qazvin, Iran. , Iran
10.22034/road.2024.437299.2245
Abstract
Intelligent transportation systems (ITS) have provided the necessary tools for control and management by using new technologies such as electronics, communication and computer control systems and combining them with traffic engineering and planning sciences. One of the most important tools of the smart system are speed control cameras, and one of the most common cameras used in urban networks is the automatic number plate recognition (ANPR) cameras.Therefore, considering the importance of measuring the performance of Automatic Number Plate Recognition in order to investigate and correctly understand the traffic situation of cities, a research has been conducted to identify existing errors and then provide a mathematical model to reduce camera errors. In this research, traffic information recorded by two cameras number 13, at the address of Mashhad - Shahid Kalantari Highway, east gate of Ferdowsi University, south-east and camera number 14, at the address of Mashhad, Shahid Kalantari Highway, Seda & Sima Boulevard, north-west during the first week of June 2019 and included information on license plates, traffic violations, exact time, speed and number of cars, and these two cameras had the most errors compared to other cameras in Mashhad. In this research, in order to identify and reduce existing errors, two classification models (random forest, neural network) have been investigated and analyzed according to the available parameters. Speed is the most effective parameter in the total error and the accuracy of the above neural network model is 0.22% and 65% respectively. In the random forest model,
Keywords
Automatic Number Plate Recognition
Neural Network Model
Random Forest Model
Vehicles
-گودرزی، مجید، فیروزی، محمدعلی و سعیدی، امید (1398). بررسی و تحلیل موانع هوشمندسازی حمل ونقل درون شهری اهواز. جغرافیا و آمایش شهری – منطقه­ای.
- قاسمی­نژاد، حسین (1388). سیستم­های حمل و نقل هوشمند، کنفرانس ملی تصادفات و سوانح جاده ای و ریلی.
- عبداللهی، میترا و خسروی، حسین (1397). طراحی و پیاده‌سازی سامانۀ بی‌درنگ آشکارسازی و شناسایی پلاک خودرو در تصاویر ویدئویی، پردازش علائم و داده‌ها.
- تیموری، شیخ محمدی، حسین زاده کاشان و شجاعی، عباس (2019). توسعه مدل مکان‌یابی دوربین‌های پلاک خوان در جاده‌های ایران جهت پوشش مسیرهای حرکتی مبدأ–مقصد وسایل نقلیه باری. فصلنامه مهندسی حمل و نقل، 11(1)،121-97.
- میربها، بابک و حسینی، سیدمهرداد (2017). ارایه مدلی برای مکان یابی بهینه دوربین­های کنترل سرعت در راه­ها.
- جعفری، ادریس و صمدیان، منیرالسادات (2012). کاربرد داده کاوی در بررسی رفتار رانندگان متخلف در کلان شهرها.
-­Anand SS, Büchner AG. (1998). Decision support using data mining.
-­Fayyad, U. Piatetsky-Shapiro G. Smyth P. (1996). The KDD process for extracting useful knowledge from volumes of data. Communications of the ACM, 1, 39(11), 27-34.
-­Gaber T. Abdelwahab, S. Elhoseny, M. Hassanien, AE. (2018).Trust-based secure clustering in WSN-based intelligent transportation systems. Computer Networks, 9, 146, 151-158.
-­Gunay, B. Saltan, M. Ilgaz, A. Albayrak Y. (2015). Area-wide ANPR coverage with a small number of instrumented vehicles. International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS), 379-386.
-­Homayounfar, Abdollah, Anthony, TS, Ho. Naida, Zhu. George, Head, and Phil, Palmer (2011).  Multi-vehicle convoy analysis based on ANPR data.
- Khinchi, M. Agarwal, C. (2019). A review on automatic number plate recognition technology and methods. International Conference on Intelligent Sustainable Systems, 363-366.
- Patel C, Shah D, Patel A. (2013). Automatic number plate recognition system (anpr): A survey. International Journal of Computer Applications, 1, 69(9).
- Qadri, MT. Asif, M. (2009). Automatic number plate recognition system for vehicle identification using optical character recognition. International Conference on Education Technology and Computer, 17, 335-338.
- Rigatti, S.J. (2017). Random forest. Journal of Insurance Medicine, 1, 47(1), 31-39.
- Roy, A. Ghoshal DP. (2011). Number Plate Recognition for use in different countries using an improved segmentation. National Conference on Emerging Trends and Applications in Computer Science, 1-5.
- Soole D, Fleiter, J. Watson B. (2012). Point-to-point speed enforcement [Austroads Project No.SS1649]. Austroads Ltd­.
- Tan, H. Feng, G. Feng, J. Wang, W. Zhang­, YJ. Li, F. A.  (2013). tensor-based method for missing traffic data completion. Transportation Research Part C: Emerging Technologies, 1, 28, 15-27.
-­Robinson A. Venter, C. (2019). Validating traffic models using large-scale Automatic Number Plate Recognition (ANPR) data. Journal of the South African Institution of Civil Engineering, 61(3), 45-57.
-­Ebrahimzadeh, M. A., Dabbaqi, M., & Nakhaie, N. (2024). Investigating the reduction of the error caused by the counting of vehicle traffic in city license plate reader cameras by mathematical models (case study: Mashhad city). Road.
-Ebrahimzadeh, M. A., Javanshir, H., & Esfandiyari, M. (2024). Analysis and Evaluation of Smart Ramp Metering System on Urban Traffic Flow Control (Case Study: Tehran-Hakim Highway). Road, 32(121), 219-234.
-Jashnian, A. H., Ebrahimzadeh, M. A., & Yaghoobii, S. (2024). Analysis and evaluation of hourly changes in travel consumption volume and the number of severe accidents in inner-city roads (case study of Qom city). Road.
-Ebrahimzadeh, M. A., Nakhaie, N., & Dabbaqi, M. (2024). Investigating the Influential Personality and Demographic Variables of the Behavior of Public Transport and Freight Drivers in the Factors of Accidents (Case Study: Karaj City). Road, 32(120), 375-388.