MRSC-V: Moroccan Road-Sign Crops from driving Videos (labels and boxes)
Authors/Creators
- 1. LSATI Laboratory, Sidi Mohamed Ben Abdellah University, Fez, Morocco
Description
Labels, bounding boxes and statistics for 2,081 crops of traffic signs cut from public YouTube driving videos filmed on 9 Moroccan drives (Casablanca, Rabat, Fes, Marrakech, Midelt–Fes, Fes–Ifrane and motorways). The crops are labelled with 70 Morocco-relevant TS-1M classes, plus “other sign” for signs outside them. There are three splits from different drives: training (868 crops, 3 drives), development (696 known + 70 unknown, 4 drives) and final test (423 known + 24 unknown, 2 drives, labelled blind and evaluated once). This package contains no images. The images are available on request for research use in the restricted record https://doi.org/10.5281/zenodo.23922536. Made for: B. Ait Messaad, S. Motahhir, “TinyML traffic-sign classification for Moroccan roads under cross-country domain shift”, Digital Engineering (submitted), 2026.
Files
MRSC-V_v1.0_public.zip
Additional details
Software
- Repository URL
- https://github.com/badraitmessaad-ing/tinyml-moroccan-signs
- Programming language
- Python