inis 15(4): e3

Research Article

A2Ba: Adaptive Background Modelling for Visual Aerial Surveillance Conditions

Download1049 downloads
  • @ARTICLE{10.4108/inis.2.4.e3,
        author={Francisco Sanchez-Fernandez and Philippe Brunet and Sidi-Mohammed Senouci},
        title={A2Ba: Adaptive Background Modelling for Visual Aerial Surveillance Conditions},
        journal={EAI Endorsed Transactions on Industrial Networks and Intelligent Systems},
        volume={2},
        number={4},
        publisher={ICST},
        journal_a={INIS},
        year={2015},
        month={6},
        keywords={Image processing, unmanned aerial vehicle, background modelling, background subtraction, mobile observer, moving objects, GMM, KDE},
        doi={10.4108/inis.2.4.e3}
    }
    
  • Francisco Sanchez-Fernandez
    Philippe Brunet
    Sidi-Mohammed Senouci
    Year: 2015
    A2Ba: Adaptive Background Modelling for Visual Aerial Surveillance Conditions
    INIS
    ICST
    DOI: 10.4108/inis.2.4.e3
Francisco Sanchez-Fernandez1,*, Philippe Brunet1, Sidi-Mohammed Senouci1
  • 1: DRIVE Lab, University of Burgundy
*Contact email: Francisco.Sanchez-Fernandez@u-bourgogne.fr

Abstract

Background modelling algorithms are widely used to define a part of an image that most time remains stationary in a video. In surveillance tasks, this model helps to recognize those outlier objects in an area under monitoring. Set up a background model on mobile platforms (UAVs, intelligent cars, etc.) is a challenging task due camera motion when images are acquired. In this paper, we propose A2Ba, a robust method to support instabilities caused by aerial images fusing different information about image motion. We used frame difference as first approximation, then age of pixels is estimated. This latter gives us an invariability level of a pixel over time. Gradient direction of ages and an adaptive weight are used to reduce impact from camera motion on background modelling. We tested A2Ba simulating several conditions that impair aerial image acquisition such as intentional and unintentional camera motion. Experimental results show improved performance compared to baseline algorithms GMM and KDE.