IG03 - Research Group for Computer Science and Human-Computer Interaction

This research focuses on developing advanced computer vision systems for the real-time detection of pedestrian crossings and traffic signaling. The core of our approach lies in deep learning algorithms, whose robustness is enhanced through the use of synthetically generated data. By utilizing this method, we simulate diverse traffic scenarios and various atmospheric conditions, ensuring high detection reliability. The final system aims to provide users with safer navigation through dynamic urban environments by delivering precise information about traffic infrastructure on the move.