Physical Distancing Monitoring with Background Subtraction Methods Hendra Adinanta Research Center for Physics, Indonesian Institute of Sciences Tangerang Selatan, Indonesia hendra.adinanta@lipi.go.id Edi Kurniawan Research Center for Physics, Indonesian Institute of Sciences Tangerang Selatan, Indonesia edi.kurniawan@lipi.go.id Suryadi Research Center for Physics, Indonesian Institute of Sciences Tangerang Selatan, Indonesia suryadi@lipi.go.id Jalu A. Prakosa Research Center for Physics, Indonesian Institute of Sciences Tangerang Selatan, Indonesia jalu.ahmad.prakosa@lipi.go.id Abstract—World Health Organization (WHO) has confirmed that the spreading of coronavirus disease 2019 (COVID-19) could be avoided by keeping the physical distance at least 3 feet (1 meter). Then, we have a motivation to employ computer vision techniques to monitor social distancing violations. The principle of the works are to detect persons, then to assess the physical distancing violation from their distance. Most of the researchers have tried to utilize object detection methods such as faster RCNN, Yolo, and SSD to detect persons from the frame. Those methods rely on, the support of Graphics Processing Unit (GPU) to execute their heavy computation. In this works, we propose social distancing monitoring by applying background subtraction methods based on Gaussian Mixture Models (GMM) i.e. Geo- metric Multigrid (GMG), k-Nearest Neighbor (KNN), Mixture of Gaussian (MOG), and Mixture of Gaussian 2 (MOG2). These methods have been used to filter persons from the frame with computational process. Some parameters evaluation measures have been determined to check the best method suitable for this works. In terms of performance, better methods are ranked as KNN, MOG, MOG2, and GMG. Index Terms—social distancing, COVID-19, background sub- traction, monitoring I. I NTRODUCTION COVID-19 outbreak has been reported at the end of 2019. And, World Health Organization (WHO) per July 18, 2020 confirmed that the COVID-19 pandemic has spread to over 216 countries with 13,876,441 positive cases including 593,087 deaths [1]. To this date, many health institutions across the globe put their efforts to develop medicines and vaccines to combat this virus. One of the alternatives to decrease the transmission of this infectious virus is by implementing social distancing on public places. Social distancing can reduce the infection rate and delay the peak of cases if it is appropriately implemented at the early of this pandemic. This will reduce the burden of the healthcare systems and also lower the death rate [2]. Fig. 1 (a) [3] figures the effects of social distancing measures in reducing the plague peak and matching the health care system capacity. The effect (a) (b) Fig. 1. Illustration of benefits on controlling social distancing in the outbreak. of social distancing can reduce the number of infected cases and the earlier implementation as shown in Fig. 1(b) [3]. WHO announces that maintain at least 1 meter (3 feet) dis- tance between one person to another to avoid virus transmis- sion via droplet [4]. This regulation is supported by affected countries to mitigate the coronavirus pandemic with minimum economic loss. Many governments have been implemented social distanc- ing during the COVID-19 pandemic, they make policies to restrict some aspect as travel, territorial, and public area. In this case, large-scale measures are difficult to implement, because not all public places can be closed, persons still need to go outside to fulfil their daily needs. In this context, technologies 2020 International Conference on Radar, Antenna, Microwave, Electronics, and Telecommunications © IEEE 2021. This article is free to access and download, along with rights for full text and data mining, re-use and analysis. 45