Nightwatch with YOLOv8: Real-Time Vehicle Detection and Speed Analysis for Safer Roads

Abstract

The heavy electric energy consumption of street-lights has prompted the scientific community to develop various control methods. Among these, zoning control, where light follows road users, has emerged as a promising approach due to its significant energy-saving potential. However, existing research often relies on fixed illumination zones based on speed limits or imprecise methods to locate road users. In this paper, we propose a zoning control method based on computer vision and speed measurement to address these issues. We first calibrate the camera using a semi-automatic PnP method to accurately measure distances. Next, we employ a YOLOv8 model trained on a nighttime dataset to detect vehicles in real time and measure their speeds. The results demonstrate significant energy reduction while ensuring road safety.