PROJECT TITLE :

Attentive Monitoring of Multiple Video Streams Driven by a Bayesian Foraging Strateg - 2015

ABSTRACT:

During this paper, we tend to shall contemplate the matter of deploying attention to the subsets of the video streams for collating the most relevant knowledge and info of interest related to a given task. We tend to formalize this monitoring downside as a foraging drawback. We propose a probabilistic framework to model observer's attentive behavior because the behavior of a forager. The forager, moment to moment, focuses its attention on the most informative stream/camera, detects fascinating objects or activities, or switches to a more profitable stream. The approach proposed here is suitable to be exploited for multistream video summarization. Meanwhile, it can function a preliminary step for more sophisticated video surveillance, e.g., activity and behavior analysis. Experimental results achieved on the UCR Videoweb Activities Information Set, a publicly obtainable information set, are presented to illustrate the utility of the proposed technique.