yolov8-blur
Science Score: 31.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (13.0%) to scientific vocabulary
Keywords
privacy
virtualcamera
yolov8
Last synced: 10 months ago
·
JSON representation
·
Repository
Basic Info
Statistics
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 15
- Releases: 0
Topics
privacy
virtualcamera
yolov8
Created about 2 years ago
· Last pushed almost 2 years ago
Metadata Files
Readme
Citation
readme.md
YOLOv8 Blur
Introduction
This is a simple implementation of YOLOv8 with blur augmentation for privacy protection.
Features
- [x] Real-time object detection with YOLOv8.
- [x] Blur augmentation for privacy protection.
- [x] Virtual camera output for use in applications like Zoom, Skype, and Discord. ## Planned Features
- [ ] Fine-tuning the model for better performance.
- [ ] Face identification for selective blurring.
- [ ] Inpainting to fill the black screen with the background.
- [ ] GUI for easy configuration.
- [ ] 3D Avatar overlay for people in the frame. (Depends on Face identification feature.)
Requirements
- Python 3.10
- CUDA 12.1
- OBS Studio (With Virtual Camera) or Unity Capture
Usage
- Install the requirements.
- Run the following command to start the virtual camera:
bash python main.py - Open the application you want to use the virtual camera with.
- Select the virtual camera as the video input.
Your application should now use the virtual camera with YOLOv8 blur augmentation. TV screens will be black, and people will be blurred.
Installation
bash
pip install -r requirements.txt
Note: Ensure you install the correct PyTorch and torchvision versions for your CUDA version. You can find the correct version here.
Notes
- Achieves 11-15 FPS on an RTX 3080 10GB depending on the resolution and number of objects detected.
- The model is trained on the COCO dataset.
- The model may not work perfectly in all scenarios.
- Not optimized for speed.
Citation
- Ultralytics YOLOv8: Glenn Jocher, Ayush Chaurasia, Jing Qiu. (2023). Ultralytics YOLOv8 (v8.0.0). Available at: https://github.com/ultralytics/ultralytics. License: AGPL-3.0.
- OpenCV: Intel Corporation, Willow Garage, Itseez. (2023). OpenCV (v4.9.0.80). Available at: https://opencv.org. License: 3-clause BSD.
- PyTorch: Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan. (2024). PyTorch (v2.2.2). Available at: https://pytorch.org. License: BSD-3-Clause.
- TensorFlow: Martín Abadi, et al. (2015). TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Available at: https://www.tensorflow.org.
Owner
- Name: Ultr4_dev
- Login: Ultr4Dev
- Kind: user
- Repositories: 1
- Profile: https://github.com/Ultr4Dev
Citation (CITATION.bib)
@software{yolov8_ultralytics,
author = {Glenn Jocher and Ayush Chaurasia and Jing Qiu},
title = {Ultralytics YOLOv8},
version = {8.0.0},
year = {2023},
url = {https://github.com/ultralytics/ultralytics},
orcid = {0000-0001-5950-6979, 0000-0002-7603-6750, 0000-0003-3783-7069},
license = {AGPL-3.0}
}
@software{opencv,
author = {Intel Corporation and Willow Garage and Itseez},
title = {OpenCV},
version = {4.9.0.80},
year = {2023},
url = {https://opencv.org},
license = {3-clause BSD}
}
@software{opencv,
author = {Intel Corporation and Willow Garage and Itseez},
title = {OpenCV},
version = {4.9.0.80},
year = {2024},
url = {https://opencv.org},
license = {3-clause BSD}
}
@software{pyvirtualcam,
author = {Maik Riechert},
title = {Pyvirtualcam},
version = {0.11.1},
year = {2024},
url = { https://github.com/letmaik/pyvirtualcam}
}
@software{pytorch,
author = {Adam Paszke and Sam Gross and Soumith Chintala and Gregory Chanan},
title = {PyTorch},
version = {2.2.2},
year = {2024},
url = {https://pytorch.org},
license = {BSD-3-Clause}
}
@misc{tensorflow2015-whitepaper,
title={ {TensorFlow}: Large-Scale Machine Learning on Heterogeneous Systems},
url={https://www.tensorflow.org/},
note={Software available from tensorflow.org},
author={
Mart\'{i}n~Abadi and
Ashish~Agarwal and
Paul~Barham and
Eugene~Brevdo and
Zhifeng~Chen and
Craig~Citro and
Greg~S.~Corrado and
Andy~Davis and
Jeffrey~Dean and
Matthieu~Devin and
Sanjay~Ghemawat and
Ian~Goodfellow and
Andrew~Harp and
Geoffrey~Irving and
Michael~Isard and
Yangqing Jia and
Rafal~Jozefowicz and
Lukasz~Kaiser and
Manjunath~Kudlur and
Josh~Levenberg and
Dandelion~Man\'{e} and
Rajat~Monga and
Sherry~Moore and
Derek~Murray and
Chris~Olah and
Mike~Schuster and
Jonathon~Shlens and
Benoit~Steiner and
Ilya~Sutskever and
Kunal~Talwar and
Paul~Tucker and
Vincent~Vanhoucke and
Vijay~Vasudevan and
Fernanda~Vi\'{e}gas and
Oriol~Vinyals and
Pete~Warden and
Martin~Wattenberg and
Martin~Wicke and
Yuan~Yu and
Xiaoqiang~Zheng},
year={2015},
}
GitHub Events
Total
- Delete event: 2
- Issue comment event: 3
- Pull request event: 4
- Create event: 1
Last Year
- Delete event: 2
- Issue comment event: 3
- Pull request event: 4
- Create event: 1
Dependencies
.github/workflows/action.yml
actions
.github/workflows/build.yml
actions
- Nuitka/Nuitka-Action main composite
- actions/checkout v3 composite
- actions/setup-python v4 composite
- actions/upload-artifact v3 composite
pyproject.toml
pypi
requirements.txt
pypi
- Jinja2 ==3.1.3
- MarkupSafe ==2.1.3
- PyYAML ==6.0.1
- certifi ==2024.2.2
- charset-normalizer ==3.3.2
- colorama ==0.4.6
- contourpy ==1.2.0
- cycler ==0.12.1
- filelock ==3.13.3
- fonttools ==4.50.0
- fsspec ==2024.3.1
- idna ==3.6
- kiwisolver ==1.4.5
- matplotlib ==3.8.3
- mpmath ==1.3.0
- networkx ==3.2.1
- numpy ==1.26.4
- opencv-python ==4.9.0.80
- packaging ==24.0
- pandas ==2.2.1
- pillow ==10.3.0
- psutil ==5.9.8
- py-cpuinfo ==9.0.0
- pyarrow ==15.0.2
- pyparsing ==3.1.2
- python-dateutil ==2.9.0.post0
- pytz ==2024.1
- pyvirtualcam ==0.11.1
- requests ==2.31.0
- scipy ==1.12.0
- seaborn ==0.13.2
- six ==1.16.0
- sympy ==1.12
- thop ==0.1.1.post2209072238
- torch ==2.2.2
- torchaudio ==2.2.2
- torchvision ==0.17.2
- tqdm ==4.66.2
- typing_extensions ==4.10.0
- tzdata ==2024.1
- urllib3 ==2.2.1
requirements-amd.txt
pypi
- Jinja2 ==3.1.3
- MarkupSafe ==2.1.5
- PyYAML ==6.0.1
- certifi ==2024.2.2
- charset-normalizer ==3.3.2
- colorama ==0.4.6
- contourpy ==1.2.1
- cycler ==0.12.1
- dill ==0.3.8
- filelock ==3.13.3
- fonttools ==4.51.0
- fsspec ==2024.3.1
- idna ==3.7
- kiwisolver ==1.4.5
- matplotlib ==3.8.3
- mpmath ==1.3.0
- networkx ==3.3
- numpy ==1.26.4
- opencv-python ==4.9.0.80
- packaging ==24.0
- pandas ==2.2.1
- pillow ==10.3.0
- psutil ==5.9.8
- py-cpuinfo ==9.0.0
- pyarrow ==15.0.2
- pyparsing ==3.1.2
- python-dateutil ==2.9.0.post0
- pytz ==2024.1
- pyvirtualcam ==0.11.1
- requests ==2.31.0
- scipy ==1.13.0
- seaborn ==0.13.2
- six ==1.16.0
- sympy ==1.12
- thop ==0.1.1.post2209072238
- torch ==2.2.2
- torchaudio ==2.2.2
- torchvision ==0.17.2
- tqdm ==4.66.2
- typing_extensions ==4.10.0
- tzdata ==2024.1
- urllib3 ==2.2.1
requirements-cuda.txt
pypi
- Jinja2 ==3.1.3
- MarkupSafe ==2.1.5
- PyYAML ==6.0.1
- certifi ==2024.2.2
- charset-normalizer ==3.3.2
- colorama ==0.4.6
- contourpy ==1.2.1
- cycler ==0.12.1
- dill ==0.3.8
- filelock ==3.13.3
- fonttools ==4.51.0
- fsspec ==2024.3.1
- idna ==3.7
- kiwisolver ==1.4.5
- matplotlib ==3.8.3
- mpmath ==1.3.0
- networkx ==3.3
- numpy ==1.26.4
- opencv-python ==4.9.0.80
- packaging ==24.0
- pandas ==2.2.1
- pillow ==10.3.0
- psutil ==5.9.8
- py-cpuinfo ==9.0.0
- pyarrow ==15.0.2
- pyparsing ==3.1.2
- python-dateutil ==2.9.0.post0
- pytz ==2024.1
- pyvirtualcam ==0.11.1
- requests ==2.31.0
- scipy ==1.13.0
- seaborn ==0.13.2
- six ==1.16.0
- sympy ==1.12
- thop ==0.1.1.post2209072238
- torch ==2.2.2
- torchaudio ==2.2.2
- torchvision ==0.17.2
- tqdm ==4.66.2
- typing_extensions ==4.10.0
- tzdata ==2024.1
- urllib3 ==2.2.1