Deep Learning - Based COVID-19 Safety Monitoring

Computer Engineering

As of June 2, 2021, the fatal coronavirus illness 2019 (COVID-19) has spread to over 180 nations, resulting in 28,175,044 confirmed cases and 331,895 deaths in India alone. The population's vulnerability is heightened by the lack of effective treatment drugs and immunity to COVID-19. The population's vulnerability is heightened by the lack of effective treatment drugs and immunity to COVID-19. Because there are no effective vaccines or medications available, the only viable way to combat the pandemic is to follow covid guidelines, such as social distancing and wearing masks etc. In order to automate the task of monitoring social-distancing, mask, and age of a person using surveillance footage, this study provides a deep learning-based system. The suggested framework employs the YOLO v3 object detection model to distinguish persons from the background using bounding boxes and assigned IDs.It was discovered that it had improved accuracy for all of the input videos that were evaluated.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.