AI Enabled Next-Generation Traffic Control System
Article Sidebar
Main Article Content
Abstract
Traffic is one of the superior problems in modern metropolis. Fresh and advanced technology related infusions are required to supervise themselves and direct traffic signals in order to decrease the snarl-upping of traffic. Major problem is when it comes to a predicament or an emergency circumstance which affects the servicing facilities like ambulances, fire trucks, police vans etc. In this paper, we capture data from the surveillance camera and using it we will train the machine using Machine Learning and Deep Learning. So, the process goes where we use a collective number of images which can be enormous in numbers which can be used to train the model. Subsequently, the vehicles are identified, and are categorized into various classes and this classification is done by itself, as it is edified to precision. We procured 88% accuracy using YOLOv5 for vehicle recognition. Further it contributes to the future, so that road design and scrutiny can be developed and secondly the fuel usage can be controlled, and the standby time is also saved effectively. Within some period, we will be able to harmonize most of the signals, by imparting a flexible traffic management system, thus resulting in declination of traffic congestion.
Article Details
References
Sabeen Javaid, Ali Sufian, Saima Pervaiz, and Mehak Tanveer , “Smart Traffic Management System Using Internet of Things” , International Conference on Advanced Communications Technology(ICACT), 2018
Ninad Lanke and Sheetal Koul, “Smart Traffic Management System”, International Journal of Computer Applications , 2013
Sheena Mariam Jacob, Shobha Rekh, Manoj G and J John Paul, “Smart Traffic Management System with Real Time Analysis”, 2018
Fahimul Hoque Shubho, Fahim Iftekhar, Ekhfa Hossain and Shahnewaz Siddique, “Real-time traffic monitoring and traffic offense detection using YOLOv4 and OpenCV DNN”, 2021 IEEE Region 10 Conference (TENCON).
Jiachen Yang, Jipeng Zhang and Huihui Wang , “Urban Traffic Control in Software Defined Internet of Things via a Multi-Agent Deep Reinforcement Learning Approach” , IEEE Transactions on Intelligent Transportation Systems
Jayadurga, R. ., Veeramakali, T. ., Ali Sohail, M. ., Alangudi Balaji, N. ., Kumar C., K. ., & L. P., S. (2023). Deep Learning Based Detection and Classification of Anomaly Texts in Social Media. International Journal of Intelligent Systems and Applications in Engineering, 11(4s), 78–89. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/2574
Junchen Jin, Haifeng Guo, Jia Xu, Xiao Wang and Fei-Yue Wang ,”An End-to-End Recommendation System for Urban Traffic Controls and Management Under a Parallel Learning Framework”,IEEE Transactions on Intelligent Transportation Systems
T. V. Janardhana Rao, R. Arun Sekar, B. Drakshyani, P Kalyan Chakravarthi, N. Kumareshan and S. P. Karthi , “IOT based Smart solution for Traffic congestion at Metro Cities” , 2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems.
Faris, W. F. . (2020). Cataract Eye Detection Using Deep Learning Based Feature Extraction with Classification. Research Journal of Computer Systems and Engineering, 1(2), 20:25. Retrieved from https://technicaljournals.org/RJCSE/index.php/journal/article/view/7
Dr. Vikram Bali, Ms. Sonali Mathur, Dr. Vishnu Sharma and Dev Gaur ,”Smart Traffic Management System using IoT Enabled Technology”, 2020 2nd International Conference on Advances in Computing, Communication Control and Networking (ICACCCN).