A Vehicle Density Estimation Traffic Light Control System Using a Two-Dimensional Convolution Neural Network
Author:
Mathiane Malose John1, Tu Chunling1, Adewale Pius1ORCID, Nawej Mukatshung1
Affiliation:
1. Department of Computers System Engineering, Faculty of Information and Communication Technology, Tshwane University of Technology, Soshanguve, Pretoria 0001, South Africa
Abstract
One of the world’s challenges is the amount of traffic on the roads. Waiting for the green light is a major cause of traffic congestion. Low throughput rates and eventual congestion come from many traffic signals that are hard coded, irrespective of the volume of the amount of traffic. Instead of depending on predefined time intervals, it is essential to build a traffic signal control system that can react to changing vehicle densities. Emergency vehicles, like ambulances, must be given priority at the intersection so as not to spend more time at the traffic light. Computer vision techniques can be used to improve road traffic signal control and reduce real-time traffic delays at intersections without the requirement for substantial infrastructure analysis. Long wait times and significant energy consumption are just two of the problems of the current traffic signal control system. To optimal efficiency, the traffic signal’s duration must be dynamically changed to account for current traffic volume. To lessen congestion, the approach taken in this research focuses on modifying traffic signal time determined by the density of vehicles at the crossroads. The main purpose of this article is to demonstrate heavy traffic and emergency vehicle prioritization from all directions at the traffic intersection for a speedy passage. Using the Pygame tool, the proposed method in this study, which includes a mechanism for estimating traffic density and prioritization by counting vehicles at a traffic junction, is demonstrated. The vehicle throughput for the adaptive traffic light built using Pygame is compared with the vehicle pass rate for the adaptive traffic light built using Simulation of Urban Mobility (SUMO). The simulation results show that the adaptive traffic light built using Pygame achieves 90% throughput compared to the adaptive traffic light built using SUMO. A Two-Dimensional Convolutional Neural Network (2D-CNN) is implemented using Tensorflow for vehicle classification. The 2D-CNN model demonstrated 96% accuracy in classifying vehicles using the test dataset. Additionally, emergency vehicles, such as ambulances, are given priority for quick passing.
Funder
The Tshwane University of Technology
Subject
Electrical and Electronic Engineering,Automotive Engineering
Reference30 articles.
1. Deepajothi, S., Rajan, D.P., Karthikeyan, P., and Velliangiri, S. (2021, January 19–20). Intelligent traffic management for emergency vehicles using convolutional neural network. Proceedings of the 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India. 2. Atrip: Architecture for traffic classification based on image processing;Cristiani;Vehicles,2020 3. Mall, P.K., Narayan, V., Pramanik, S., Srivastava, S., Faiz, M., Sriramulu, S., and Kumar, M.N. (2023). Handbook of Research on Data-Driven Mathematical Modeling in Smart Cities, IGI Global. 4. Zhou, B., Cao, J., Zeng, X., and Wu, H. (2010, January 6–9). Adaptive traffic light control in wireless sensor network-based intelligent transportation system. Proceedings of the 2010 IEEE 72nd Vehicular Technology Conference-Fall, Ottawa, ON, Canada. 5. Cano, M.-D., Sanchez-Iborra, R., Freire-Viteri, B., Garcia-Sanchez, A.-J., Garcia-Sanchez, F., and Garcia-Haro, J. (2017, January 2–6). A self-adaptive approach for traffic lights control in an urban network. Proceedings of the 2017 19th International Conference on Transparent Optical Networks (ICTON), Girona, Spain.
|
|