Citation

Chon, Zi Kang and Connie, Tee and Goh, Michael Kah Ong (2026) An Integrated Vision-Based ADAS Framework for Robust Lane and Vehicle Detection Under Varying Weather and Lighting Conditions. In: 9th International Conference on Artificial Intelligence and Big Data, ICAIBD 2026, 29 May 2026 - 31 May 2026, Chengdu.

Text 6.pdf - Published Version Restricted to Repository staff only Download (757kB)

Abstract

Advanced Driver Assistance Systems (ADAS) rely heavily on clear visual input for accurate scene interpretation and decision-making. However, adverse weather conditions such as rain and haze can significantly degrade visibility and affect the performance of vision-based modules. This paper presents an enhanced weather-aware ADAS framework that introduces an image quality correction method as key preprocessing steps to improve overall system reliability. The framework begins by detecting environmental disturbances in the input video stream. When rain or haze is identified, corresponding removal algorithms are applied to restore scene clarity. The enhanced video is then processed for lane line detection which is further optimized using a day-night classification module to select suitable processing parameters. A vehicle distance estimation module determines whether a safe following distance is maintained and issues warnings when the following distance falls below a safe threshold. The primary contribution of this work is the integration of weather-aware correction mechanisms into the ADAS pipeline that significantly improves detection robustness in challenging environmental conditions. Experimental results demonstrate the effectiveness of the proposed in real-time applications.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	, computer vision , image processing rain removal
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Information Science and Technology (FIST)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	01 Oct 2026 04:40
Last Modified:	01 Oct 2026 04:40
URII:	http://shdl.mmu.edu.my/id/eprint/16775

Downloads

Edit (login required)