| dc.contributor.author | Tendai, P. N. | ru |
| dc.contributor.author | Kudzai, B. C. | ru |
| dc.coverage.spatial | Минск | ru |
| dc.date.accessioned | 2026-01-14T07:23:17Z | |
| dc.date.available | 2026-01-14T07:23:17Z | |
| dc.date.issued | 2025 | |
| dc.identifier.citation | Tendai, P. N. Driver distraction detection system using visual sensors based on deep learning = / P. N. Tendai, B. C. Kudzai // Приборостроение-2025 : материалы 18-й Международной научно-технической конференции, 13–15 ноября 2025 года Минск, Республика Беларусь / редкол.: А. И. Свистун (пред.), О. К. Гусев, Р. И. Воробей [и др.]. – Минск : БНТУ, 2025. – С. 443-445. | ru |
| dc.identifier.uri | https://rep.bntu.by/handle/data/162716 | |
| dc.description.abstract | Drivers often engage in secondary activities that divert attention from driving, increasing accident risks. This study uses deep learning, specifically Squeeze Net 1.1, to detect visual and cognitive distractions through camera-based monitoring of the driver’s face, hands, and body. Comparative analysis of algorithms shows ResNet offers the best accuracy. The system effectively identifies distracted driving, contributing to safer roads and advancing intelligent driver assistance technologies. | ru |
| dc.language.iso | en | ru |
| dc.publisher | БНТУ | ru |
| dc.title | Driver distraction detection system using visual sensors based on deep learning | ru |
| dc.type | Working Paper | ru |
