Motorbike Helmet Usage Detection in Foggy Weather Conditions with Dark Channel Prior and YOLOV8

Driving safety is crucial for maintaining road safety, and helmet use by motorcyclists is essential for reducing serious head injuries during accidents. However, compliance with helmet use remains challenging, especially in developing countries. Automatic detection of helmetless motorcyclists is, therefore, a highly relevant topic for traffic surveillance and law enforcement. One significant challenge is detecting helmetless motorcyclists in non-ideal weather conditions, such as fog, which reduces visibility and hinders visual detection. The Dark Channel Prior (DCP) technique enhances visibility in foggy conditions by exploiting the nature of foggy images, where at least one color channel (red, green, or blue) at each pixel has very low intensity. This dehazing process removes fog effects and improves image contrast. YOLOv8, an advanced object detection algorithm, utilizes an optimized convolutional neural network for real-time, high-accuracy detection of various objects, including motorcyclists and helmets. Combining DCP and YOLOv8 can create a robust system for detecting helmetless motorcyclists in various weather conditions, providing a reliable solution for law enforcement and traffic safety. This motorcycle helmet use detection system can be applied to traffic Closed-Circuit Television (CCTV) for Electronic Traffic Law Enforcement (ETLE), to facilitate authorities in enforcing applicable traffic laws.