| Version 6 (modified by , 2 years ago) ( diff ) |
|---|
Cameras
Installed Cameras Information
- Mudd 1st floor, Mech E lab, towards 120th St.
- Mudd 2nd-floor balcony, towards Amsterdam Ave.
- Mudd 12th floor, Botwinick lab mudd1224, towards 120th St.
- Mudd 12th-floor balcony, towards Amsterdam Ave.
COSMOS Cameras Data-set
- 1st-floor videos (anonymized*): https://drive.google.com/drive/u/0/folders/1QXrfsLXEKfRfQyc6qzvtg37A0Z1i0io5
- 2nd-floor videos (anonymized*): https://drive.google.com/drive/u/0/folders/1LR7H4theRazz2_uYHvCFGVVewQmKbWSF
- 12th-floor videos (120th street): https://drive.google.com/drive/u/0/folders/1SEsocAAIReepdjE4XyVyT4kiqrunv7BU
- 12th-floor videos (Amsterdam Avenue): https://drive.google.com/drive/u/0/folders/1qC-62s8ohTGg-odyzo7BNw2GDv1OIeoK
Videos in this directory are outputs of the COSMOS YOLOv4 blurring pipeline.
Faces and license plates are anonymized with Gaussian blurred areas defined by bounding box detection coordinates. A high-level overview of the blurring.
Anonymization Workflow for 1st and 2nd-floor Cameras
- Frames are read individually from a video file.
- Each frame is then:
2.1 Resized to the input size of the specific YOLOv4 model (960x960 or 1440x1440)
2.2 Passed through the YOLOv4 model which outputs bounding box predictions
2.3 Blurred corresponding to the bounding box predictions
- Blurred frames are written to the output video file.
The YOLOv4 blurring model is trained in Darknet on the Mudd 1st floor video dataset annotated in Summer 2021. Models are converted from Darknet to Py Torch for integration into the current implementation of the blurring pipeline.
Reference Paper and DOI
The following paper describes the project vision and key technologies as well as the development, deployment, and outreach efforts. We would appreciate it if you cite this paper when publishing results obtained using the COSMOS testbed.
- Raychaudhuri, I. Seskar, G. Zussman, T. Korakis, D. Kilper, T. Chen, J. Kolodziejski, M. Sherman, Z. Kostic, X. Gu, H. Krishnaswamy, S. Maheshwari, P. Skrimponis, and C. Gutterman, “Challenge: COSMOS: A city-scale programmable testbed for experimentation with advanced wireless,” in Proc. ACM MOBICOM’20, 2020." (Download) https://doi.org/10.1145/3372224.3380891
