Six months ago, we were not even familiar with the expression ‘social distancing’. But then the coronavirus pandemic began to spread across the world infecting hundreds of thousands of people. With the rising cases in India, we too have been urged to stay home and practise social distancing.
Social distancing means keeping a minimum distance of 5-6 feet between you and other people outside your home. This means no group gatherings and staying away from crowded places. It limits your exposure to the virus and keeps your family safe.
The Real-time Social Distancing Detector will help governments and individuals monitor if Social Distancing is maintained at a particular place in real-time and hence spread awareness and efficiently disperse the crowd to save people from coronavirus.
Required skills: Python, OpenCV, Deep Learning, Computer Vision
Bonus skills: Cloud computing, Docker
Possible mentors: Sayak Paul (GDE in ML), Rishiraj Acharya
References and open-source building blocks:
- Models: Tensorflow, Keras, Scikit-learn, TensorflowJS
- Virtualization: Docker
- Examples:
Points to consider in the proposal:
Design of the system:
- What are the inputs, what are the outputs?
- What are the package requirements?
Performance:
- How long does it take? What are the time limitations?
- What resources can be used to speed it up?
- Is there associated cost?