• Bavith
• Fathimath Safreena
• Fathimathul Haifa
• Karthik Vishwajeeth S
• Nivin K S,Daya Naik

Emergency vehicle detection is vital for ensuring timely responses and minimizing delays in critical situations within urban environments. Traditional detection methods often fall short under challenging conditions, such as poor visibility or high traffic density. This research develops an AI-driven real- time emergency vehicle detection system utilizing advanced deep learning techniques. Specifically, we implemented a Multi-Level Spatial Fusion YOLO (MLSF-YOLO) architecture to accurately detect emergency vehicles, such as ambulances and fire engines, in video streams. The system dynamically controls traffic signals to prioritize emergency vehicle movement, halting other lanes to ensure a clear pathway. Experimental evaluations demonstrate the robustness of the proposed approach, achieving an accuracy of 96.2.

YOLO, emergency vehicle detection, real-time system, traffic management, road safety.

"AI-Driven Real-Time Detection of Emergency Vehicles", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.773-775, July-2025, Available :http://www.jetir.org/papers/JETIRGX06143.pdf

"AI-Driven Real-Time Detection of Emergency Vehicles", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp773-775, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06143.pdf