Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{208845,
        author = {Adithya S Kundar and Ambika S Kundar and Ankith G Kodiya and B G rohith and Prof. Shruthi D},
        title = {SmartFlow: Intelligent Traffic Signal Management with YOLO and ViT},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {4},
        pages = {3069-3077},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=208845},
        abstract = {Increased traffic, congestion, and traffic signal problems affects fuel consumption and raise emission rates. There are also constraints like emergency vehicle priority, accident management, and red-light violations. This study proposed Automated Traffic System (ATS) using YOLOv8 and computer vision to manage a four-way road traffic system and developed the prototype and web dashboard. The system aims to automatically adjust signal light changes based on the number of vehicles waiting at an intersection. The framework utilizes YOLOv8 to detect and count vehicles and recognize emergency vehicles such as ambulances and police cars and employs a Vision Transformer (ViT) model to classify accidents. Moreover, the OpenCV library was used to extract key frames from the uploaded videos. The framework counts the number of cars in each frame, and the traffic controller decides which junction will get the green light based on this information within a specified range. The system prioritizes pedestrians, emergency vehicles, and accident scenes over regular traffic. The model also provides a 30 seconds green corridor for emergency vehicles, and when an accident is identified, it initiates an accident management state. This framework provides a REST API backend built using the Flask framework and a web dashboard built using HTML, CSS, and JavaScript to view signals status, vehicle counting, alerts, timers, and statistics. Therefore, the proposed ATS framework can be considered as a prototype for managing a four-way traffic system by using an artificial intelligence approach.},
        keywords = {Automated Traffic System, Intelligent Transportation System, YOLOv8, Computer Vision, Vision Transformer, Accident Detection, Emergency Vehicle Detection, Adaptive Traffic Signal Control, Green Corridor, Traffic Management, Flask, Real-Time Traffic Monitoring.},
        month = {September},
        }