Implementing a real-time, AI-based, people detection and social distancing measuring system for Covid-19

Abstract

COVID-19 is a disease caused by a severe respiratory syndrome coronavirus. It was identified in December 2019 in Wuhan, China. It has resulted in an ongoing pandemic that caused infected cases including many deaths. Coronavirus is primarily spread between people during close contact. Motivating to this notion, this research proposes an artificial intelligence system for social distancing classification of persons using thermal images. By exploiting YOLOv2 (you look at once) approach, a novel deep learning detection technique is developed for detecting and tracking people in indoor and outdoor scenarios. An algorithm is also implemented for measuring and classifying the distance between persons and to automatically check if social distancing rules are respected or not. Hence, this work aims at minimizing the spread of the COVID-19 virus by evaluating if and how persons comply with social distancing rules. The proposed approach is applied to images acquired through thermal cameras, to establish a complete AI system for people tracking, social distancing classification, and body temperature monitoring. The training phase is done with two datasets captured from different thermal cameras. Ground Truth Labeler app is used for labeling the persons in the images. The proposed technique has been deployed in a low-cost embedded system (Jetson Nano) which is composed of a fixed camera. The proposed approach is implemented in a distributed surveillance video system to visualize people from several cameras in one centralized monitoring system. The achieved results show that the proposed method is suitable to set up a surveillance system in smart cities for people detection, social distancing classification, and body temperature analysis.

Keywords: COVID-19; Distributed surveillance system; Jetson nano; Neural network; Social distancing; Temperature analysis.

Fig. 1

The schematic diagram for R-CNN detector

Fig. 2

The schematic diagram for Fast R-CNN detector

Fig. 3

Schematic diagram for YOLO: input image which splits into S×S grids, each grid predicts the bounding boxes and the confidence scores and finally, the score encodes the probability with bounding box on the detected class

Fig. 4

The steps involved for people detection and social distancing classification on thermal images

Fig. 5

Architecture of YOLOv2 Neural Network

Fig. 6

a Mini-Batch Loss Curve before fine-tuning, b Mini-Batch Loss Curve after fine-tuning

Fig. 7

The measured distance (D) between the center of each bounding box for a detected person

Fig. 8

Sample Images from a, b Dataset I, c, d Dataset II

Fig. 9

The comparison of this work vs other competing deep learning detectors (R-CNN, Fast R-CNN, and YOLOv3) for real-time detection

Fig. 10

Comparison of the proposed approach verses other pre-trained models in terms of memory size

Fig. 11

Smart Surveillance distributed video system for people detection and social distancing classification