Download PDFOpen PDF in browser

Social Distance and Face Mask Detection

EasyChair Preprint no. 6060

5 pagesDate: July 14, 2021


With the recent outbreak and rapid transmission of the Covid-19 pandemic, the need for the public to comply with social distancing standards, and to wear masks in public places, is only growing. According to the World Health Organization (WHO), in order to comply with the necessary social distancing, people should maintain a distance of at least 3 feet from one another. This research paper focuses on a solution that will help you to secure the relevant social distance, by the use of the YOLO (You Only Look Once) object detection on in the video footages and images in real-time. The experimental results presented in the paper show that the detection of masked faces, faces and the human subjects, which is based on the YOLO, has a faster, safer and more secure, and better recognition rate when compared with its competitors. Our proposed object detection models have reached a high level of accuracy in excess of 90% with a very good output speed. The network is faster, and also makes sure that the output speed is capable of producing real-time results without compromising on accuracy. The model also provides promising results in variable scenarios.

Keyphrases: Convolutional Neural Network(CNN), Single Shot object Detection (SSD), You Only Look Once YOLO (You Only Look Once)

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Fahad Hassan and Soumya Roy and Mridula Prabhakar and Himanshu Rawat},
  title = {Social Distance and Face Mask Detection},
  howpublished = {EasyChair Preprint no. 6060},

  year = {EasyChair, 2021}}
Download PDFOpen PDF in browser