Development of smart camera systems based on artificial intelligence network for social distance detection to fight against COVID-19

KARAMAN O., Alhudhaif A., POLAT K.

APPLIED SOFT COMPUTING, cilt.110, 2021 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 110
  • Basım Tarihi: 2021
  • Doi Numarası: 10.1016/j.asoc.2021.107610
  • Dergi Adı: APPLIED SOFT COMPUTING
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Applied Science & Technology Source, Compendex, Computer & Applied Sciences, INSPEC
  • Anahtar Kelimeler: Corona virus (COVID-19), Deep learning, Convolutional neural network (CNN), Transfer learning, COMPUTER VISION, CORONAVIRUS
  • Akdeniz Üniversitesi Adresli: Evet

Özet

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-RCNN 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. (C) 2021 Elsevier B.V. All rights reserved.