Abstract
In this work, an artificial intelligence network-based smart camera system prototype, which tracks social distance using a bird’s-eye perspective, has been developed. “MobileNet SSD-v3”, “Faster-R-CNN Inception-v2”, “Faster-R-CNN ResNet-50” models have been utilized to identify people in video sequences. The final prototype based on the Faster R-CNN model is an integrated embedded system that detects social distance with the camera. The software developed using the “Nvidia Jetson Nano” development kit and Raspberry Pi camera module calculates all necessary actions in itself, detects social distance violations, makes audible and light warnings, and reports the results to the server. It is predicted that the developed smart camera prototype can be integrated into public spaces within the “sustainable smart cities,” the scope that the world is on the verge of a change.
•ANN-based smart camera system prototype, which tracks social distance using a bird’s-eye perspective developed.•The best performance metrics have been obtained for Faster R-CNN with an accuracy of 97.7%.•The developed software detects social distance violations, makes audible and light warnings.