In modern urban environments, traffic congestion creates significant challenges to mobility, economic productivity, and environmental sustainability. As urbanization accelerates, cities must adopt innovative technologies to manage traffic flow effectively and ensure timely access for emergency vehicles. This proposed model develops an intelligent traffic management system using advanced computer vision and machine learning techniques. The system autonomously monitors real-time traffic conditions, predicts congestion, and optimizes signal timings through adaptive algorithms. By utilizing deep learning models, including TensorFlow Object Detection and YOLO, it analyzes road images to assess traffic density and detect emergency vehicles, dynamically adjusting signal priorities to alleviate congestion and expedite emergency responses. The proposed model achieved 92% accuracy, outperforming existing algorithms like Crowding Distance and CNN-based approaches, and was effective in reducing congestion while improving emergency response times. This initiative represents a scalable, adaptable solution that enhances urban mobility, sustainability, and safety by leveraging advanced technologies for smarter, more efficient transportation infrastructures.