Real-time detection of rare roadside obstacles using YOLOv8-n in autonomous vehicles

Afeera Bint-e Tanveer, Muhammad Ayoub Kamal, Muhammad Mansoor Alam, Mazliham Mohd Su’ud · 2026

Read Real-time detection of rare roadside obstacles using YOLOv8-n in autonomous vehicles by Afeera Bint-e Tanveer, Muhammad Ayoub Kamal, Muhammad Mansoor Alam, Mazliham Mohd Su’ud (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/plos-pone-0350732.txt.

Description

Self-driving cars must spot rare dangers: fallen trees, loose barrels, scattered debris. Afeera Bint-e Tanveer and colleagues trained a compact vision model, YOLOv8-n, for exactly these roadside surprises, in this 2026 PLOS One study aimed at cheaper on-board hardware.

Images from several open collections were merged and cleaned into one training set. Extra training images with changed brightness, tilts, and partial blocking taught the model to cope with bad light and clutter. On a mid-range graphics card it read sixty-eight images per second with high precision and recall. The authors say such lean models suit cars that cannot carry data-center hardware.

Catalog record

CREATORAfeera Bint-e Tanveer, Muhammad Ayoub Kamal, Muhammad Mansoor Alam, Mazliham Mohd Su’ud
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE47586
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0350732

Browse the full library · About the Tower of Babel