Global Journal of Computer Science and Technology, D: Neural & Artificial Intelligence, Volume 22 Issue 1

Global Journal of Computer Science and Technology: D Neural & Artificial Intelligence Volume 22 Issue 1 Version 1.0 Year 2022 Type: Double Blind Peer Reviewed International Research Journal Publisher: Global Journals Online ISSN: 0975-4172 & Print ISSN: 0975-4350 Strictly as per the compliance and regulations of: © 2022. Ranjith K.H.V.S, Jayasekara A.S, Ratnasooriya K.A.L.L., J.L Thilini Randika, Dr. Lakmal Rupasinghe & Ms. Chethana Liyanapathirana. This research/review article is distributed under the terms of the Attribution-NonCommercial-NoDerivatives 4.0 International (CC BYNCND 4.0). You must give appropriate credit to authors and reference this article if parts of the article are reproduced in any manner. Applicable licensing terms are at https://creativecommons.org/licenses/by-nc-nd/4.0/. Human Tracking and Profiling for Risk Management By Ranjith K.H.V.S, Jayasekara A.S, Ratnasooriya K.A.L.L., J.L Thilini Randika, Dr. Lakmal Rupasinghe & Ms. Chethana Liyanapathirana Institute of Information Technology Abstract- Infectious viruses are conveyed via respiratory droplets produced by an infected person when they speak, sneeze, or cough. So, to combat virus transmission, the World Health Organization (WHO) has imposed severe regulations such as mandatory face mask use and social segregation in public spaces. The ’Human Tracking and Profiling for Risk Management System (HTPRM)’ is an online application that identifies the risk associated with failing to follow proper health practices. This proposed approach, which is divided into four components, utilizes ’You Only Live Once YOLO (V3)’ to detect face- mask danger, which would be determined based on two factors: wearing the face mask properly and the type of mask (Surgical, k95, homemade, and bare). The second phase is to use Open CV and SSD- Mobilenet to evaluate the value of a one-meter space (Social Distance) between people. The system recognizes the maximum number of individuals that can be in the vicinity of the specific hall that uses YOLO( V3) and image processing as the third procedure. In the last processing, the system identifies each person’s behavior, classifies it as uncommon or not, and calculates the risk associated with each category. Finally, the system computes the overall risk and generates a warning alarm to notify the user that they are in a dangerous scenario. Index Terms: YOLO (V3), SSD (single shot detector), mobile- net, open-CV, image processing, open pose, tenser-flow. GJCST-D Classification: H.3.4 HumanTrackingandProfilingforRiskManagement