Description: Physical distancing is crucial for preventing the spread of contagious illnesses such as COVID-19 (coronavirus). COVID-19 can spread through coughing, sneezing and close contact. By minimizing the amount of close contact with others, we reduce our chances of catching the virus and spreading it to our loved ones and within our community. Physical distancing is the practice of purposefully reducing close contact between people by avoiding the crowded scene. This can be practice by maintaining a distance of about at least 6 feet from others when possible. Motivated by this notion, this research will propose a vision-based deep learning framework for automating the task of monitoring physical distancing using surveillance video. The proposed framework will perform the human detection model to segregate humans from the background and track the identified people with the help of bounding boxes and assigned IDs. The violation index term will be proposed based on the crowd density measure to quantify the non adoption of social distancing protocol.
Should use MATLAB to explore the knowledge of computer vision and machine learning. The final outcome of this project is expected to be a software-based implementation with a graphical user interface to connect with an RGB camera.
Matlab Version I am using R2020b
Tell me what Yolo version you are using
For the detection use yolo method
For the neural network need for 3 sample video (attached one video) and image
The simulation only for the recorded video, Not in the real-time
Attached article related to our work right for the methodology and experiment part
Attached Project Proposal
Attached 2 sample videos (Find another 1 videos and show me before using, or you may suggest me for the videos)
Download all files from gdrive here: [login to view URL]
Tell me how long it will take to complete (Start immediately and give progress every day)
Tell me the charges also