Applying deep learning algorithm to maintain social distance in public place through drone technology. Issue 3 (10th June 2020)

• Record Type: Journal Article
• Authors: Ramadass, Lalitha; Arunachalam, Sushanth; Z., Sagayasree
• Is Part Of: International journal of pervasive computing and communications. Volume 16:Issue 3(2020)
• Page Start: 223
• Page End: 234
• Publication Date: 2020-06-10
• Subjects: Deep learning -- Drone -- Social distancing -- Covid19 -- Novel corona virus -- Drone unit; Ubiquitous computing -- Periodicals; Mobile computing -- Periodicals; Computer network protocols -- Periodicals; Computer network architectures -- Periodicals; Application software -- Development -- Periodicals; 004.6
• DOI: 10.1108/IJPCC-05-2020-0046
• Languages: English
• ISSNs: 1742-7371

Abstract

Abstract : Purpose: The purpose of this paper is to inspect whether the people in a public place maintain social distancing. It also checks whether every individual is wearing face mask. If both are not done, the drone sends alarm signal to nearby police station and also give alarm to the public. In addition, it also carries masks and drop them to the needed people. Nearby, traffic police will also be identified and deliver water packet and mask to them if needed. Design/methodology/approach: The proposed system uses an automated drone which is used to perform the inspection process. First, the drone is being constructed by considering the parameters such as components selection, payload calculation and then assembling the drone components and connecting the drone with the mission planner software for calibrating the drone for its stability. The trained yolov3 algorithm with the custom data set is being embedded in the drone's camera. The drone camera runs the yolov3 algorithm and detects the social distance is maintained or not and whether the people in public is wearing masks. This process is carried out by the drone automatically. Findings: The proposed system delivers masks to people who are not wearing masks and tells importance of masks and social distancing. Thus, this proposed system would work in an efficient manner after the lockdown period ends and helps in easy social distance inspection in an automatic manner. The algorithm can be embedded in public cameras and then details can be fetched to the camera unit same as the drone unit which receives details from the drone location details and store it in database. Thus, the proposed system favours the society by saving time and helps in lowering the spread of corona virus. Practical implications: It can be implemented practically after lockdown to inspect people in public gatherings, shopping malls, etc. Social implications: Automated inspection reduces manpower to inspect the public and also can be used in any place. Originality/value: This is the original project done with the help of under graduate students of third year B.E. CSE. The system was tested and validated for accuracy with real data.