Analyzing Lane Visibility Distance on Urban and Suburban Roads in Slovakia Under Various Weather Conditions Using a Single Camera
Author(s) -
Marek Galinski,
Volodymyr Danylov,
Peter Lehoczky,
Rastislav Bencel,
Matej Janeba,
Ivan Kotuliak
Publication year - 2025
Publication title -
ieee access
Language(s) - English
Resource type - Magazines
SCImago Journal Rank - 0.587
H-Index - 127
eISSN - 2169-3536
DOI - 10.1109/access.2025.3611230
Subject(s) - aerospace , bioengineering , communication, networking and broadcast technologies , components, circuits, devices and systems , computing and processing , engineered materials, dielectrics and plasmas , engineering profession , fields, waves and electromagnetics , general topics for engineers , geoscience , nuclear engineering , photonics and electrooptics , power, energy and industry applications , robotics and control systems , signal processing and analysis , transportation
This article investigates lane visibility distance on urban and suburban roads in Slovakia using a single-camera system under various weather conditions. The study aims to understand how environmental factors and road quality influence lane visibility, employing a single-frame road distance estimation method that is affordable and scalable. The methodology involves rigorous data cleaning, including frame filtering and the application of empirically defined thresholds, to further improve the accuracy of lane detection. The analysis highlights variability in lane visibility influenced by weather conditions, with rain and snow typically reducing visibility; however, snow along roadsides can enhance lane detection on well-maintained highways. The type of road is also a significant factor, with highways offering the best visibility, while city roads and mountainous suburban roads pose challenges due to intersections, tight turns, and uneven terrain. Over 96 drives, we observed median lane visibility distances of 82.2 m on D2 highway and 78.7 m on D1 highway compared to just 51.6 m on urban roads, with analyzable frames representing 86.8% and 77.3% of highway data compared to 47.4% in urban environments, and down to 42.6% in rain. The results demonstrate both the feasibility and limitations of employing a single-camera setup for real-time AI-based lane visibility assessment, providing insights to improve road safety technologies and adapt them to diverse urban and suburban environments.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom