본문 바로가기
  • Home

Unauthorized person tracking system in video using CNN-LSTM based location positioning

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2021, 26(12), pp.77-84
  • DOI : 10.9708/jksci.2021.26.12.077
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : November 22, 2021
  • Accepted : December 10, 2021
  • Published : December 31, 2021

Chan Park 1 Hyungju Kim 1 Nammee Moon 1

1호서대학교

Accredited

ABSTRACT

In this paper, we propose a system that uses image data and beacon data to classify authorized and unauthorized perosn who are allowed to enter a group facility. The image data collected through the IP camera uses YOLOv4 to extract a person object, and collects beacon signal data (UUID, RSSI) through an application to compose a fingerprinting-based radio map. Beacon extracts user location data after CNN-LSTM-based learning in order to improve location accuracy by supplementing signal instability. As a result of this paper, it showed an accuracy of 93.47%. In the future, it can be expected to fusion with the access authentication process such as QR code that has been used due to the COVID-19, track people who haven't through the authentication process.

Citation status

* References for papers published after 2022 are currently being built.

This paper was written with support from the National Research Foundation of Korea.