iBotGuard: an Internet-based Intelligent Robot security system using Invariant Face Recognition against intruder

  • Authors:
  • J. N.K. Liu;Meng Wang;Bo Feng

  • Affiliations:
  • Dept. of Comput., Hong Kong Polytech. Univ., China;-;-

  • Venue:
  • IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

One crucial application of intelligent robotic systems is remote surveillance using a security robot. A fundamental need in security is the ability to automatically verify an intruder into a secure or restricted area, to alert remote security personnel, and then to enable them to track the intruder. In this article, we propose an Internet-based security robot system. The face recognition approach possesses "invariant" recognition characteristics, including face recognition where facial expressions, viewing perspectives, three-dimensional poses, individual appearance, and lighting vary and occluding structures are present. The experiment uses a 33.6-kb/s modem Internet connection to successfully remotely control a mobile robot, proving that the streaming technology-based approach greatly improves the "sensibility" of robot teleoperation. This improvement ensures that security personnel can effectively and at low cost use the Internet to remotely control a mobile robot to track and identify a potential intruder.