TIME DEPENDENT ON-LINE BOOSTING FOR ROBUST

BACKGROUND MODELING

Helmut Grabner, Christian Leistner and Horst Bischof

Institute for Computer Graphics and Vision, Graz University of Technology, Austria

Keywords:

On-line learning, boosting, background modeling.

Abstract:

In modern video surveillance systems change and outlier detection is of highest interest. Most of these systems

are based on standard pixel-by-pixel background modeling approaches. In this paper, we propose a novel ro-

bust block-based background model that is suitable for outlier detection using an extension to on-line boosting

for feature selection. In order to be robust our system incorporates several novelties for previous proposed on-

line boosting algorithms and classiﬁer-based background modeling systems. We introduce time-dependency

and control for on-line boosting. Our system allows for automatically adjusting its temporal behavior to the un-

derlying scene by using a control system which regulates the model parameters. The beneﬁts of our approach

are illustrated on several experiments on challenging standard datasets.

1 INTRODUCTION

For most video surveillance systems the detection

of moving or intruding objects is of crucial impor-

tance. As they are easy to implement and fast to com-

pute, frequently simple background subtraction meth-

ods are applied where objects are detected by blobs

of pixels which do not correspond to the background

model.

In its simplest form the background model (BGM)

is solely one image, called the background im-

age. Having this image, pixels are marked as fore-

ground if they do not ﬁt to it, i.elet@tokeneonedot,

are more than a certain threshold above or be-

low each pixel value. For realistic applications

and in order to handle different environmental con-

ditions (e.glet@tokeneonedot, changing lightening

conditions or foreground models moving to back-

ground and vice versa), more sophisticated, multi-

modal statistical models such as Mixture of Gaussians

(GMM) (Stauffer and Grimson, 1999) or Eigenback-

grounds (Oliver et al., 2000) are often used. More

efﬁcient systems analyzing foreground models (Tian

et al., 2005) have been proposed. In order to further

improve the robustness some recent approaches ex-

ploit the spatial correlation between pixels arranged

in blocks (e.glet@tokeneonedot, (Russell and Gong,

2005)), e.glet@tokeneonedot, by describing statis-

tics within one block using features (Heikkil

a and

Pietik

ainen, 2006), the entire block is decided to be

either background or foreground, which signiﬁcantly

improves the detection reliability.

Furthermore, several adaptive methods for esti-

mating a pixel-based BGM have been proposed which

update the existing image with respect to the cur-

rent input frame (e.glet@tokeneonedot, running av-

erage (Koller et al., 1994), temporal median ﬁlter

(Lo and Velastin, 2001), approximate median ﬁlter

(McFarlane and Schoﬁeld, 1995)). For block-based

BGMs adaptiveness can be achieved by describing

each block with an on-line classiﬁer (Grabner et al.,

2006). This, additionally, allows to adapt to con-

tinuous changes (e.glet@tokeneonedot, illumination

changes in outdoor scenes) while observing the scene.

Although being effective for describing highly dy-

namic scenes, yet, the main drawback (see also sec-

tion 2) of this on-line learner-based BGM is that its

update strategy is similar to a self-learning method

since the model updates are directly based on its

own classiﬁer predictions and can therefore end up in

a catastrophic state (i.elet@tokeneonedot, the model

drifts away). Due to this dependency on its own

predictions, the model performs quite well for a

relatively short period of time but ﬁnally tends to

learn foreground objects very quickly without offer-

ing any control on its temporal behavior (see also Fig-

ure 1). Furthermore, the cumbersome update strategy

is highly scene dependent and, therefore, has to be

hand-tuned every now and then.

To sum up, previously proposed background mod-

612

Grabner H., Leistner C. and Bischof H. (2008).

TIME DEPENDENT ON-LINE BOOSTING FOR ROBUST BACKGROUND MODELING.

In Proceedings of the Third International Conference on Computer Vision Theory and Applications, pages 612-618

 SciTePress