In this project, you will develop a vision-based human safety and assistance detection system for a public train station in the context of Automatic Train Operation (ATO). While there are many specialized algorithms concerned with fall detection, few approaches provide a comprehensive detection of safety critical events in public spaces that extend to the general detection of injuries, assistive needs and social violence. To develop such a system, you are working hands-on with an experimental setup with stereocameras and LiDARs here in CITEC.
Your tasks will be to:
- Farmiliarize yourself with the sensor setup and play around with existing models for human safety
- Train a model to detect a broad range of safety critical events
- Optionally perform camera-LiDAR fusion to enhance detection performance
| Frequency | Weekday | Time | Format / Place | Period | |
|---|---|---|---|---|---|
| by appointment | n.V. | 07.04.-18.07.2025 |
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.