Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Motorbike Helmet Usage Detection in Foggy Weather Conditions with Dark Channel Prior and YOLOv8

Rektorat UDINUS 2024 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2024
Goals
Record
fb58c8a4-897c-4617-927c-1bffd1a355d5
Published
2026-10-30

Universitas Dian Nuswantoro, with activity participants Ridho, Ihda Innar; Andono, Pulung Nurtantio; Purwanto; Soeleman, Moch Arief; and Noersasongko, Edi, addresses automatic detection of helmetless motorcyclists in foggy weather conditions. The activity concerns driving safety, road safety, and helmet use as an important measure for reducing serious head injuries during accidents. It also identifies continuing challenges in compliance with helmet use, especially in developing countries.

The activity focuses on traffic surveillance and law enforcement. Fog is identified as a significant challenge because it reduces visibility and hinders visual detection. The described approach combines the Dark Channel Prior technique and YOLOv8. Dark Channel Prior enhances visibility in foggy conditions by using the characteristic of foggy images in which at least one color channel, red, green, or blue, has very low intensity at each pixel. This dehazing process removes fog effects and improves image contrast.

YOLOv8 is described as an advanced object detection algorithm that uses an optimized convolutional neural network for real-time, high-accuracy detection of objects including motorcyclists and helmets. Combining Dark Channel Prior and YOLOv8 is presented as a system for detecting helmetless motorcyclists in various weather conditions. The system can be applied to traffic Closed-Circuit Television for Electronic Traffic Law Enforcement to facilitate enforcement of applicable traffic laws. The activity therefore relates to the stated goals through its attention to helmet use, serious head-injury prevention, road safety, traffic surveillance, and enforcement technology. The source does not provide study results, evaluation metrics, dataset details, or documented implementation outcomes.

Reference https://www.scopus.com/pages/publications/85213361968?origin=resultslist