Comparative Evaluation of Stationary Foreground Object Detection Algorithms Based on Background Subtraction Techniques

Citations Over TimeTop 10% of 2009 papers

Abstract

In several video surveillance applications, such as the detection of abandoned/stolen objects or parked vehicles,the detection of stationary foreground objects is a critical task. In the literature, many algorithms have been proposed that deal with the detection of stationary foreground objects, the majority of them based on background subtraction techniques. In this paper we discuss various stationary object detection approaches comparing them in typical surveillance scenarios (extracted from standard datasets). Firstly, the existing approaches based on background-subtraction are organized into categories. Then, a representative technique of each category is selected and described. Finally, a comparative evaluation using objective and subjective criteria is performed on video surveillance sequences selected from the PETS 2006 and i-LIDS for AVSS 2007 datasets, analyzing the advantages and drawbacks of each selected approach.

Related Papers

• → Queue based fast background modelling and fast hysteresis thresholding for better foreground segmentation(2004)23 cited
• → Reliable real-time foreground detection for video surveillance applications(2005)8 cited
• → The effect of color space and block size on foreground detection(2013)5 cited
• → Ghosts and stationary foreground detection by dual-direction background modeling(2012)1 cited
• → On the Role and the Importance of Features for Background Modeling and Foreground Detection(2016)8 cited