Widiatmoko, Fuad and Berchmans, Hanny J. and Setiawan, Widi (2021) Computer Vision and Deep Learning Approach for Social Distancing Detection During Covid-19 Pandemic. Masters thesis, Swiss German University.

Preview	Text Fuad Widiatmoko 21952008 TOC.pdf Download (1MB) | Preview
	Text Fuad Widiatmoko 21952008 1.pdf Restricted to Registered users only Download (1MB)
	Text Fuad Widiatmoko 21952008 2.pdf Restricted to Registered users only Download (3MB)
	Text Fuad Widiatmoko 21952008 3.pdf Restricted to Registered users only Download (4MB)
	Text Fuad Widiatmoko 21952008 4.pdf Restricted to Registered users only Download (2MB)
	Text Fuad Widiatmoko 21952008 5.pdf Restricted to Registered users only Download (294kB)
Preview	Text Fuad Widiatmoko 21952008 Ref.pdf Download (532kB) | Preview

Abstract

Since December 2019, cases of the coronavirus or known as COVID-19 have spread throughout the world through several types of disease spread. to date, the total cases of COVID-19 have reached 78 million cases and the death rate has reached 1.7 deaths. one way to reduce the spread of this virus besides wearing a mask and always washing hands is social distancing. social distancing allows people to be 6 feet (2 meters) away from other people so that the potential for spread can stop. So far, the regulations for maintaining social distance are still being guarded by officers as well as several signs to maintain their social distance. This research aims to make new breakthroughs to maintain human social distance using computer vision and deep learning and this system can encourage humans to always maintain their social distance in the form of an alarm sound by combining the YOLO and Detectron2 detection algorithms. Research has been conducted by the development of cameras to record people in queues and send video to deep learning to detect people and their distance from each other. The results show significant distance measurement results with only 1 centimetre error, as well as proper human detection with an alarm form to encourage humans to maintain their social distance.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	COVID-19, Social Distance, Computer Vision, Deep Learning, YOLO, Detectron2
Subjects:	R Medicine > RA Public aspects of medicine > RA644 Malaria, COVID-19 T Technology > TJ Mechanical engineering and machinery T Technology > TJ Mechanical engineering and machinery > TJ163.12 Mechatronics T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7872 Sensor Networks
Divisions:	Faculty of Engineering and Information Technology > Department of Mechatronics Engineering
Depositing User:	Faisal Ifzaldi
Date Deposited:	20 Aug 2021 02:16
Last Modified:	03 Jan 2022 15:49
URI:	http://repository.sgu.ac.id/id/eprint/2180

Actions (login required)

View Item