536
edits
Theses and Projects: Difference between revisions
→Privacy-preserved Video Analytics
| Line 69: | Line 69: | ||
Please contact Dr. Tingting Yuan [tingting.yuan@cs.uni-goettingen.de]] (B/M/P) | Please contact Dr. Tingting Yuan [tingting.yuan@cs.uni-goettingen.de]] (B/M/P) | ||
=== '' Privacy-preserved Video Analytics=== | === '''' Privacy-preserved Video Analytics=== | ||
This project/thesis topic focuses on the protection of privacy in | This project/thesis topic focuses on the protection of privacy in video analytics. | ||
The project involves three key tasks: | The project involves three key tasks: | ||
1) Implementation of a system utilizing YOLO and CycleGANs/DataGen for video analysis and processing. | 1) Implementation of a system utilizing YOLO and CycleGANs/DataGen for video analysis and processing. The code for this is already available for use. | ||
2) Development of a privacy protection mechanism by adjusting the level of blur applied to the video, taking into account a trade-off between inference accuracy (e.g. detection by YOLO) and the level of privacy protection. | 2) Development of a privacy protection mechanism by adjusting the level of blur applied to the video, taking into account a trade-off between inference accuracy (e.g., detection by YOLO) and the level of privacy protection. | ||
3) | 3) Optimize the blur level for Pan-tilt-zoom cameras to ensure that the system effectively captures key visual information while still preserving privacy. | ||
Please contact Dr. Tingting Yuan [tingting.yuan@cs.uni-goettingen.de] (B/M/P) | Please contact Dr. Tingting Yuan [tingting.yuan@cs.uni-goettingen.de] (B/M/P) | ||