Authors :
Likhitha S. M.; Likhith N.; M. S. Chinmayee; B. Sowmya
Volume/Issue :
Volume 11 - 2026, Issue 10 - October
Google Scholar :
https://tinyurl.com/2ebxhpkz
DOI :
https://doi.org/10.38124/ijisrt/26Oct1225
Note : A published paper may take 4-5
working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and
ResearchGate.
Abstract :
Traffic jams at road intersections can cause delays for Ambulance. These delays make it hard to get emergency help to people fast. Most traffic signal systems use fixed timing. They do not react quickly when an Ambulance is coming. This paper presents an Ambulance Priority Traffic Management System. It uses computer vision, deep learning and automatic decision-making to help Ambulance move faster and to monitor traffic better at intersections. The system works at a four-way intersection with four traffic zones: North-West, North-East South-West and South-East. It uses the You Only Look Once (YOLO) object detection algorithm to analyze traffic images and video frames. A special YOLO model is trained to detect Ambulance. A general YOLO model identifies vehicles like cars, buses, trucks and motorcycles. The system draws bounding boxes and class labels around each vehicle. It also finds where each vehicle is located in the traffic scene. When Ambulance is detected the system finds the center point of Ambulance’s bounding box. It then identifies which traffic zone Ambulance is in. After that the traffic light for that zone turns green. The lights for the three zones turn red in the prototype interface. This direction-based control gives priority to Ambulance. It stops traffic from moving at the same time. Once Ambulance has passed the system could later be designed to return the signals to normal using a control strategy. In addition to giving priority to Ambulance the system counts cars, buses, trucks and motorcycles. This helps create a picture of traffic. The counts are used to label traffic density as low, medium or high. This data can help monitor traffic conditions. It also lays the groundwork for adaptive signal-control strategies. The prototype was tested using traffic images and video clips. It showed its ability to detect vehicles choose the direction count vehicles and display signal changes. Detailed testing is needed to check how accurately the system detects vehicles, how fast it responds and how well it works in real traffic. The system shows how object detection and direction-specific signal control can be combined in an emergency traffic-management prototype. Future improvements might include live CCTV feeds, vehicle tracking, Ambulance siren detection, GPS location, predictive traffic analysis and multi junction coordination, across intersections. These upgrades could help build an efficient smart traffic management system.
Keywords :
Ambulance Detection, Artificial Intelligence, Computer Vision, Emergency Vehicle Priority, Traffic Density Classification, Traffic Signal Control, Vehicle Counting.
References :
- Sarvesh Shirulkar, Rishabhdev Makode, Richa Khandelwal “Adaptive Traffic Signal Management Using Real-Time Vehicle Detection and Tracking” in 2025 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI) , doi: 10.1109/IATMSI64286.2025.10984828
- Benoygopal E B; Divya Jose; Abhilash M; Hemant Jeevan Magadum; Satheesh G “Intelligent Traffic Monitoring and Management System” 2023 International Conference on Computer, Electronics & Electrical Engineering & their Applications (IC2E3) 10.1109/IC2E357697.2023.10262689
- Rajkumar Pandiarajan; M. Mohamed Sameer; G. Logesh; N. Mohamed Najeeb; M. R. Goutham Balaji “AI and Yolo-Enabled Automated Traffic Management Framework for Emergency Vehicle Priority” 2026 Second International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS) 10.1109/ICISCOIS62701.2026.11447635
- Vandana Singh; Pragya Singh; Nidhi Phutela; Priya Grover “Road Traffic Signal Management – A Case Study” 2024 11th International Conference on Reliability, Infocom Technologies and Optimization (ICRITO)
- Jessie R. Balbin; Benjie T. Guiwo Jr.; Noel A. Salalila; Esperanza E. Chua; Kallista Coleen T. Antenor; Allana Kyle H. Deang; Sumin Yoo; Marlon Jim P. Garino “AI-Powered Urban Traffic Management: An Innovative Solution for Real-Time Traffic Optimization and Congestion Control” 2024 IEEE 16th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM) 2024 10.1109/HNICEM64917.2024.11258749
- Joesam Dinesh C; Dr. Sibi Amaran; Shrinidhi S; Dr. Sree Kumar K; Dr. Karthikeyan U “YOLO-based Traffic Signal Optimization for Intelligent Traffic Flow Management” 2024 8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC) 10.1109/I-SMAC61858.2024.10714806
- Saurabh Pratap Singh Rathore; Yousef Farhaoui; Tapsi Nagpal; Thanuja M; Ebuka Emmanuel Aniebonam; Priyanka Kaushik “AI-Driven Traffic Congestion Management: A Predictive Analytics Approach for Smart Cities” 2025 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation (IATMSI)2025 10.1109/IATMSI64286.2025.10985513
- R. Geetha; P. Kalyanasundaram; S. S. Rakshana; E. Nithyakala; K. Jeevitha; P. Anitha “AI Enabled Emergency Vehicle Recognition and Adaptive Traffic Signal System” Proceedings of the 8th International Conference on Inventive Material Science and Applications (ICIMA-2026) 10.1109/ICIMA68728.2026.11564613
- V. Devi; Satheesh Kumar D; Ganapathi M; Rishidharan G; Thirumalaivasan R; Thulasi Srirami K “A Real-Time Adaptive AI Based Traffic Management Framework for Ambulance Priority” Proceedings of the 6th International Conference on Pervasive Computing and Social Networking (ICPCSN-2026) 10.1109/ICPCSN68523.2026.11543612
- K. V. V. SubbaRao, N. Jayakrishna, M. V. S. G. Prakash, P. L. Prasanna, and K. Ramesh, “Intelligent Traffic Signal Optimization Using Image Processing and Canny Edge Detection for Density-Based Traffic Management,” International Journal of Scientific Research & Engineering Trends (IJSRET), vol. 12, no. 2, Mar.–Apr. 2026.
Traffic jams at road intersections can cause delays for Ambulance. These delays make it hard to get emergency help to people fast. Most traffic signal systems use fixed timing. They do not react quickly when an Ambulance is coming. This paper presents an Ambulance Priority Traffic Management System. It uses computer vision, deep learning and automatic decision-making to help Ambulance move faster and to monitor traffic better at intersections. The system works at a four-way intersection with four traffic zones: North-West, North-East South-West and South-East. It uses the You Only Look Once (YOLO) object detection algorithm to analyze traffic images and video frames. A special YOLO model is trained to detect Ambulance. A general YOLO model identifies vehicles like cars, buses, trucks and motorcycles. The system draws bounding boxes and class labels around each vehicle. It also finds where each vehicle is located in the traffic scene. When Ambulance is detected the system finds the center point of Ambulance’s bounding box. It then identifies which traffic zone Ambulance is in. After that the traffic light for that zone turns green. The lights for the three zones turn red in the prototype interface. This direction-based control gives priority to Ambulance. It stops traffic from moving at the same time. Once Ambulance has passed the system could later be designed to return the signals to normal using a control strategy. In addition to giving priority to Ambulance the system counts cars, buses, trucks and motorcycles. This helps create a picture of traffic. The counts are used to label traffic density as low, medium or high. This data can help monitor traffic conditions. It also lays the groundwork for adaptive signal-control strategies. The prototype was tested using traffic images and video clips. It showed its ability to detect vehicles choose the direction count vehicles and display signal changes. Detailed testing is needed to check how accurately the system detects vehicles, how fast it responds and how well it works in real traffic. The system shows how object detection and direction-specific signal control can be combined in an emergency traffic-management prototype. Future improvements might include live CCTV feeds, vehicle tracking, Ambulance siren detection, GPS location, predictive traffic analysis and multi junction coordination, across intersections. These upgrades could help build an efficient smart traffic management system.
Keywords :
Ambulance Detection, Artificial Intelligence, Computer Vision, Emergency Vehicle Priority, Traffic Density Classification, Traffic Signal Control, Vehicle Counting.
