Impact of Environmental Conditions on YOLOv8-Based Traffic Sign Detection: A Controlled Comparison of Simulated and Real Weather Cases

Ziyad N. Aldoski, Csaba Koren, Daniel Miletics · 2026

Read Impact of Environmental Conditions on YOLOv8-Based Traffic Sign Detection: A Controlled Comparison of Simulated and Real Weather Cases by Ziyad N. Aldoski, Csaba Koren, Daniel Miletics (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13611514.txt.

Description

Ziyad Aldoski, Csaba Koren, and Daniel Miletics test whether fake weather in simulation fools a traffic sign detector the way real weather does, in a 2026 study. One road segment, one camera setup, and the same 55 signs were filmed in four conditions: clear sun, simulated rain, real rain, and simulated snow. A YOLOv8 detector's confidence was scored sign by sign, alongside image quality measures.

Clear weather scored highest, then simulated snow. Real and simulated rain trailed and did not differ significantly from each other in confidence. Yet the images told another story: sharpness and color saturation diverged sharply between the two rains. The authors conclude simulated weather mimics detector behavior fairly well, but not the look of real rain, so validation needs both.

Catalog record

CREATORZiyad N. Aldoski, Csaba Koren, Daniel Miletics
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE117 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13611514

Browse the full library · About the Tower of Babel