Authors - Anusha.S.Pujar, Gourishankari.S.P, Saniya.G, Pooja.B.L, Sanchit.H, Amit.N, Suneetha.V.B Abstract - For the purpose of controlling traffic flow, identifying congestion, and averting accidents, contemporary urban traffic monitoring is essential. An enhanced YOLOv5 model is presented in this study for precise vehicle tracking and identification under a variety of circumstances, including day and night. A multi-scale feature detection layer for seeing cars of all sizes in congested regions and an improved pixel-to-real-world distance calibration for accurate speed and distance estimation are two important improvements. Real-time traffic management is improved by integrated collision warning and congestion identification algorithms. Experimental results demonstrate improved detection reliability and mean Average Precision (mAP), making this approach suitable for scalable urban traffic control systems.
