Embedded Real-Time Video Surveillance System based on Multi-Sensor and Visual Tracking

Authors

Laith M. Fawzi, Department of Computer Engineering, University of Mosul, Mosul, IraqFollow
Sideeq Y. Ameen, Deanship of Research and Graduate Studies, Applied Science University, BahrainFollow
Salih M. Alqaraawi, Department of Computer Engineering, University of Technology, Baghdad, IraqFollow
Shefa A Dawwd, Department of Computer Engineering, University of Mosul, Mosul, IraqFollow

Author Country (or Countries)

Iraq

Abstract

This Paper describes the design and implementation of an embedded remote video surveillance system for general purposes security application. The proposed system is able to detect and report vandalism, tampering, and theft activities before they take place via SMS, Email or by a phone call. The system has been enriched with a vast range of sensors to increase its sensing capability of different types of attacks.Moreover, the proposed system has been enhanced by adding a visual verification technique to overcome false alarms generated by sensors, where a video camera is integrated within the system software to capture video footage, verify, and track the abnormal events taking into consideration bandwidth consumption and real-time processing. Finally, the system was implemented using SBC (Raspberry Pi) as a working platform supported by OpenCV and Python as a programming language. The results proved that the proposed system can achieve monitoring and reporting in real-time. Where the average processing time specified to complete all the required tasks for each frame (starting from video source to broadcasting stage) does not exceed 64%. Moreover, the proposed system achieved a reduction in the utilized data size as a result of using image processing algorithms, reaching an average of 91%, which decreased the amount of transferred data to an average of 13.4 Mbit/sec and increased the bandwidth efficiency to an average of 92%. Finally, this system is characterized by being flexible, portable, easy to install, expandable and cost-effective. Therefore, it can be considered as an efficient technology for different monitoring purposes.

Digital Object Identifier (DOI)

http://dx.doi.org/10.18576/journal/100309

Recommended Citation

M. Fawzi, Laith; Y. Ameen, Sideeq; M. Alqaraawi, Salih; and A Dawwd, Shefa (2018) "Embedded Real-Time Video Surveillance System based on Multi-Sensor and Visual Tracking," Applied Mathematics & Information Sciences: Vol. 12: Iss. 2, Article 9.
DOI: http://dx.doi.org/10.18576/journal/100309
Available at: https://digitalcommons.aaru.edu.jo/amis/vol12/iss2/9