Development of Intelligent Camera Systems with Artificial Intelligence Assisted Social Distance Detection to Combat COVID-19

Within the scope of the project, it was aimed to control the applicability of "social distance measures", which is one of the measures being implemented in order to reduce the possibility of contact between individuals infected or carriers and healthy individuals, and to slow down the rate and extent of disease transmission. In this context, it is planned to develop smart camera systems with artificial intelligence-assisted social distance detection to combat COVID-19. To combat COVID-19, a prototype of an artificial intelligence supported smart camera system that can follow social distance using a bird's-eye perspective has been developed. "MobileNet SSD v3", "Faster RCNN Inception v2", "Faster RCNN ResNet 50" models trained with COCO database were tested by OpenCV community to identify people in video images. With the developed model, people identified with the help of bounding boxes can be defined. By accepting the lowest points of these bounding rectangles as reference points, bird's-eye views were obtained and the binary distances of people were determined using the distance calibration and the Euclidean distances between the reference points. Developed using the Jetson Nano development kit and Raspberry Pi camera module, the software calculates all necessary actions within itself, detects social distance violations, gives sound and light warnings and reports the results to the server. It is envisaged that the smart camera prototypes produced in this way can be integrated into public spaces within the "smart city action plans" that we are on the verge of a change. Thanks to the sensors placed in the designed smart camera system, the awareness of the individuals can be increased with the warning system, which is activated in case of violating the social distance limits. The developed prototype will be able to be coordinated within the framework of the security camera to effectively scan the working environment, especially with the integration of strategically engaged professional enterprises, healthcare institutions. In addition, data will be provided to help supervisors in strategic manufacturing businesses to reorganize their workspaces. Thanks to this system, which allows individuals to continue their normal lives within the framework of the "social distance" rules, it is possible to make improvements in the economy, tourism and psychological areas where these measures cause serious problems. The proposed system includes places of worship, artistic and sports activity areas, shopping malls, airports, workplaces, tourism facilities, etc. By making it applicable in many public areas, the impact of "social distance" measures on social norms, economy and psychology within the scope of combating COVID-19 will be minimized.