Novel context-aware methodology for risk assessment in intelligent video-surveillance systems
by Isaac Martín de Diego; Alberto Fernández-Isabel; Ignacio San Román; Cristina Conde; Enrique Cabello
International Journal of Sensor Networks (IJSNET), Vol. 40, No. 3, 2022

Abstract: Nowadays, the presence of multiple cameras is steadily increasing. Therefore, video-vigilance systems need to be massively produced. These systems are controlled by human experts who spend excessive amount of time detecting problems or possible impediments. Intelligent video-surveillance systems appear to mitigate this issue. Nevertheless, these systems present their drawbacks. One of the most important drawbacks is their inability to process the obtained visual information and use it to modify their parameters according to the environmental requirements. In this paper, a novel methodology has been developed to provide information to a previously implemented intelligent video-surveillance system becoming sensible to the context. The methodology is based on the advice of experts to adapt the system for a given scenario. It includes both the information from generated alarms and knowledge about the environment. The experimental results have been promising and the proposed methodology can serve as the foundation for future enhancements.

Online publication date: Tue, 22-Nov-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Sensor Networks (IJSNET):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com