Аннотация
This study presents a real-time streetlamp detection system using a Raspberry Pi and dashcam, leveraging YOLOv5 and YOLOv8 models. Tested in various conditions, YOLOv8n outperformed YOLOv5n with a mean Average Precision (mAP) of $73.7 \%$ versus $\mathbf{6 9. 4 \%}$, along with higher Precision and Recall. YOLOv8n demonstrated superior accuracy and reliability, making it better suited for IoT-based smart lighting applications in smart cities. This research underscores the potential of affordable edge-computing for adaptive urban lighting solutions.