Inspiration
In the new world of corona virus, multidisciplinary efforts have been organized to slow the spread of the pandemic. The AI community has also been a part of these endeavors. In particular, developments for monitoring social distancing or identifying face masks have made-the-headlines.
So , we decided to make a project which will be beneficial to analyze such activities in crowded places during this pandemic
What it does
- It detects people wearing face mask in public.
- It detects whether people are maintaining social distance at all times to prevent the further spread of the virus.
How we built it
1. Face Mask Detection:
The model is built using the concept of SSD Algorithm, OpenCV and Keras API
2. Social Distancing Detection:
The social distancing detection is based on the Yolov3 framework. It utilizes the concept of deep learning and computer vision.
Challenges we ran into
Initially we faced trouble installing the darknet packages. The smart move was to change the interpreter to an older version of python like 3.4. Declaring the attributes for cvBoxes was to be done with precision. Because the convoluted layer for each bounded box would be really close to each other
Accomplishments that we're proud of:
- Understanding the working and Yolo would further help us to formulate several applications like Object Detection in low light using concepts of cv
- Combining the concepts of Machine Learning and Deep Learning enabled us to bring up an overall surveillance model to aid our fight against Covid-19
What we learned
We learned how to implement various libraries and tech stack in our project. We overcame many challenges that we came across while developing our project.
What's next for COVID Warriors
Deploying the model in real time and testing it. Regular updates would be made to increase precision of the model.
Log in or sign up for Devpost to join the conversation.