Abstract

NINO RONDON, Carlos Vicente et al. Video image processing to verify social distancing during the COVID-19 pandemic. Rev. logos cienc. tecnol. [online]. 2021, vol.13, n.1, pp.116-127.  Epub Dec 13, 2020. ISSN 2145-594X.  https://doi.org/10.22335/rlct.v13i1.1305.

The exponential increase in the number of COVID-19 infections around the world has prompted governments, in conjunction with medical and scientific communities, to recommend a social distance of at least two meters between people, to avoid increasing the number of infections. With the purpose of determining compliance with the measure of social distancing, a pilot test is carried out through video image processing for the people detection in open spaces in the central area of the city of Cúcuta, Colombia. The proposed method consists of the analysis of information from videos of people with static background, taken from a height of 4.5 meters, in addition to location of centroids by the method of moments and distance estimation by the euclidean method, this, by means of Python programming language. As a result, it is obtained a success in the people detection of 92.43 % and that 84.21 % of those who circulated through the video frame and transit in the central zone of the city of Cúcuta, Colombia, do not comply with the social distance of two meters recommended by the scientific community and exposed in the municipal circular 023 of 2020.

Keywords : COVID-19; social distancing; people detection; centroid location; euclidean distance.

        · abstract in Spanish | Portuguese     · text in Spanish     · Spanish ( pdf )