In this paper, a novel study for an automated scene interpretation system, named ELEVIEW, is reported to outline the design of the system. It is motivated by the reported crimes that happen inside elevators. The main goal is to investigate techniques that make an ordinary elevator monitoring system intelligent, i.e. see the scene and understand actions that are occurring. The system could filter out normal actions and trigger an alarm once abnormal events are detected. The paper focuses on the system overview, segmentation techniques as well as scenario classification. A double thresholded segmentation is employed to enhance the segmentation outcomes. This paper mainly presents an overview of the system and significant results so far achieved.
展开▼
