Detecting abandoned packages in a multi-camera video surveillance system

Abstract

We describe a video surveillance system that detects abandoned packages automatically. In this system, multiple cameras locate objects in space and time despite occlusions and distracting lighting effects observed by subsets of the cameras. A multiple-state model of an abandoned package provides the ability to detect realistic abandoned package events. The paper outlines the system by describing the modules for camera view segmentation, object classification, view-object association, 3D object tracking, and finally detection of the event of a package being abandoned, which highlights object association using multiple cameras and the multiple-state abandoned package model.