FDMB-YOLOv11: Traffic police command gesture recognition method under different lighting conditions

Xiaoyu Zhang, Baohua Guo, Sigama Anthony, David Bassir, Yuandi Zhang · 2026

Read FDMB-YOLOv11: Traffic police command gesture recognition method under different lighting conditions by Xiaoyu Zhang, Baohua Guo, Sigama Anthony, David Bassir, Yuandi Zhang (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-0357212.txt.

Description

Xiaoyu Zhang and colleagues redesigned a real-time vision model so traffic cameras can read a police officer's hand signals reliably in bright sun, shade, and glare. Their 2026 study rebuilt the lightweight YOLOv11 detector with a mobile phone-grade backbone, attention modules that pick out the officer, and flexible filters that adapt to bent arms and odd angles.

On their test images the rebuilt model named gestures far more accurately than the standard version while using fewer parameters, and it stopped confusing left-turn with right-turn signals. It still runs fast enough for live video. Systems like this could feed officer gestures into smart traffic lights and driver-assistance tools, so automated systems respect the human directing traffic when signals fail.

Catalog record

CREATORXiaoyu Zhang, Baohua Guo, Sigama Anthony, David Bassir, Yuandi Zhang
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE59660
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0357212

Browse the full library · About the Tower of Babel