A system for automatic and interactive detection of static objects

Abstract

Designing static object detection systems that are able to incorporate user interaction conveys a great benefit in many surveillance applications, since some correctly detected static objects can be considered to have no interest by a human operator. Interactive systems allow the user to include these decisions into the system, making automated surveillance systems more attractive and comfortable to use. In this paper we present a system for the detection of static objects that, based on the detection of a dual background model, classifies pixels by means of a finite-state machine. The state machine provides the meaning for the interpretation of the results obtained from background subtraction and it can be optionally used to integrate user input. The system can thus be used both in an automatic and an interactive manner without requiring any expert knowledge from the user. We successfully validated the system with several public datasets.