The use of computer vision technologies to augment human monitoring of secure computing facilities
- Resource Type
- Conference
- Authors
- Potgieter, Marius; Van Niekerk, Johan
- Source
- 2012 Information Security for South Africa Information Security for South Africa (ISSA), 2012. :1-6 Aug, 2012
- Subject
- Computing and Processing
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Monitoring
Security
Humans
Computer vision
Computers
Feature extraction
Object recognition
- Language
- ISSN
- 2330-9881
Humans are poorly equipped to perform repetitive tasks without adversely affecting the efficiency with which they are performing the task. Assets within a secure environment are usually protected with various controls that are enforced by users who follow operational controls associated to those assets. The current approach to security monitoring by means of video cameras are performed by a person physically needing to concentrate on multiple video feeds. This method relies on the constant vigilance of the operator and the consequence of loss of vigilance can range from minor theft of assets to missing a bomb placed within an airport. This paper will approach security monitoring using Computer Vision augmented with Speeded-Up Robust Features (SURF) as the catalyst to provide event-driven object detection to assist in securing an environment. A scenario of a secure computer environment will be used to demonstrate the problems with current approaches and present an alternative to human monitoring using Computer Vision. The paper demonstrates that some of the physical aspects of information security can be improved through the use of SURF algorithms.