Sani SaminuOlaosebikan Samuel TunmiseSuleiman Abimbola YahayaIdris Oladele MuniruSalaudeen K. OlawaleMuhammad kabir AbdulkadirSanusi AbdulrazaqHauwa Mohammed Hambali2026-09-042026-09-042026Saminu, S. Tunmise, O.S. Yahaya, S. A. Muniru, I. O. Salaudeen A.H. Salaudeen, K.O. Kabir, M.A. Sanusi, A. Hauwa, M.H. (2026): Development of an AI-enabled smart ambulance system for real-time emergency response and traffic navigation. KIU Journal of Science, Engineering and Technology, 5(1), 14-23. published by Kampala International University (KIU)https://uilspace.unilorin.edu.ng/handle/123456789/18523Delay in ambulance arrival during an emergency remains a major cause of avoidable damage, especially in congested areas and under-resourced regions. This project presents the design and development of an artificial intelligence ambulance detection and alert system using public space CCTV cameras. The system uses a Raspberry Pi as the central processing unit, running a deep learning model built on TensorFlow and trained with MobileNetV2 to identify an ambulance. Upon successful detection, an integrated buzzer is triggered for immediate local alert, while a GSM module sends SMS notifications to the nearby hospital or emergency response unit. The system was mechanically designed using TinkerCAD, with a 3D model that optimally arranges the camera, Raspberry Pi, and peripheral components. Circuit design and simulation were conducted using Cirkit Designer to ensure electrical stability and compatibility. This AI-enabled system demonstrated 96% detection accuracy and high precision, providing a reliable, cost-effective, and scalable alternative to GPS or a manual tracking approach. It offers a vital improvement to emergency medical response workflow, particularly in developing environments where smart healthcare infrastructure is still emerging.enAmbulance DetectionPublic Space CameraRaspberry PiDeep LearningTinkerCADArticle