A public surveillance camera system capable of privacy encryption and protection

Demo Video

Purpose

It mainly solves the two major challenges faced by surveillance systems in public places: privacy protection and intelligent image recognition. In terms of protecting personal privacy under these challenges, privacy encryption technology is proposed to use various encryption algorithms and steganography technology for face information encryption. Decryption can ensure that the confidentiality and concealment of face information can be maintained when presenting in the image. In terms of intelligent image recognition, the deep learning model is used to separate the human body from the image and recognize its movements, which can instantly identify whether it is in danger. In the middle, emergency incidents can be dealt with. This research aims to balance the public security needs and the protection of personal privacy and can be applied to various scenarios.

Example

fall_encrypt.mp4

Setup

1. Clone project git clone https://github.com/ytl0623/yolov7-GDPR.git
2. Create a new conda environment conda create -n yolov7 python==3.9
3. Activate conda environment conda activate yolov7
4. Install package pip install -r list.txt
5. Install Detectron2 cd detectron2 python setup.py install
6. Run any of the Python scripts you would like to try out python encrypt_image/video decrypt_image/video

References

• https://github.com/WongKinYiu/yolov7
• https://github.com/RizwanMunawar/yolov7-segmentation
• https://www.linkedin.com/posts/muhammadrizwanmunawar_computervision-objectdetection-deeplearning-activity-7082206466652184576-FGdI?utm_source=share&utm_medium=member_desktop