Autonomous Spherical Surveillance Robot with Vision-Based Human Recognition and Tracking

  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract

    Managing and securing university grounds poses quite a challenge. This research mainly focused on assisting security personnel in identifying specific persons-of-interest within a given area through the construction of a spherical mobile robot. This structure was conceptualized to protect the mechanical parts and electronics used for the robot's movement. Serial communication using Bluetooth modules imposed effective communication between the electronics that were both inside and outside of the sphere. Different sensors processed different signals inside an Arduino module to achieve the robot’s autonomous state. Additionally, Open Source Computer Vision (OpenCV) was used on a Raspberry Pi 3 module and machine learning on a laptop, for facial detection and recognition, respectively. Whenever faces were detected, the robot-captured images were sent to a base station via file transfer protocol (FTP) through a virtual private network (VPN) over the Internet. A selected image is then compared to a trained set of images within the system’s database to identify if that specific individual is a person-of-interest. If the identity matches, then the operator will alert security personnel. All in all, the researchers successfully constructed an autonomous surveillance robot that identified specific persons-of-interest and scouted a specific area inside De La Salle University (DLSU).

  • References

      [1] Abad, A., Gomez, C.B.C., Gonzales, P.J.M., Mallari, N., Opulencia, A.F.M., & Soriano, A.C. (2016). SPHEMO: A Teleoperated SPHErical Mobile Robot with Video-streaming Capability. 4th DLSU Innovation and Technology Fair, November 2016

      [2] Dahake, R., Kharat, M., Lahane, P. International Journal of Advanced Trends in Computer Science and Engineering, Volume 5, No.6, December 2016

      [3] Gupta, H. One shot learning with Siamese networks in PyTorch. Retrieved from, 2017

      [4] Pietikäinen, M. Local binary patterns. Retrieved from, 2010

      [5] Devi, Y., Kumar, M., &Nagaraju C. (2014). Face Detection and Classification based on Local Binary Patterns. International Journal of Advanced Trends in Computer Science and Engineering, Volume 3, No. 6., 2014

      [6] Rosebrock, A. Face recognition with OpenCV, Python and deep learning. Retrieved from, 2018

      [7] The Data Science Blog. An intuitive explanation of convolutional neural networks. Retrieved from, 2016

      [8] CA, A., Jose, H., T, J., Wilson, A. Security Alert Using Face Recognition. International Journal of Advances in Computer Science and Technology. Volume 5, No. 12, December 2016

      [9] Makwana, K., A Survey on Face Recognition Eigen face and PCA method. International Journal of Advance Research in Computer Science and Management Studies, Volume 2, Issue 2, February 2014

      [10] Mishra, S., Bhagat, K. Human Motion Detection and Video Surveillance using MATLAB, International Journal of Scientific Engineering and Research, 2015




Article ID: 22889
DOI: 10.14419/ijet.v7i4.16.22889

Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.