Attention-aware Human-Machine Interface to Support Video Surveillance Task

Abstract

There is a growing and pressing need to monitor dense, unconstrained pedestrian crowds and to detect suspicious individuals, e.g., suicide bombers. However, this is a perceptually and cognitively challenging task for human operators, because they need to track and inspect a constant stream of moving people, to make real-time decisions, and also maintain a high level of vigilance. An attention-aware human-machine interface (HMI) is proposed and prototyped, which monitors human operators’ attention allocation and supports eye gaze based interaction to support operator surveillance task. The goals are to reduce the operators’ cognitive load and fatigue, and speed up visual search, thus enabling the surveillance of dense pedestrian streams with increased accuracy. A preliminary user study showed promising results for enhancing operators’ detection performance using the attention-aware HMI, especially while searching at the high density crowds.