University of Twente Student Theses
Driver behavior recognition using ST-Gait++
Rosca, Maxim (2024) Driver behavior recognition using ST-Gait++.
|
PDF
11MB |
| Abstract: | Detecting driver behavior is crucial for enhancing road safety and developing intelligent transportation systems. Over 70% of accidents are attributed to human behavior, underscoring its significance in this field. This results in the need to understand human driving behavior to reduce this percentage. Computer vision is used to understand This research assesses the performance of ST-Gait++ model, originally designed to predict human emotion based on body position, for detecting driver behavior. The AIDE dataset is used and multiple models are trained, with various training inputs and configurations. Most of the trained models always predicted the same label, except for one that had greater accuracy and predicted two labels out of 3, instead of one. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Link to this item: | https://purl.utwente.nl/essays/100786 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page