Fusion of Motion and Appearance for Robust People Detection in Cluttered Scenes - Intelligent Video Event Analysis and Understanding - page 111

Fusion of Motion and Appearance for Robust
People Detection in Cluttered Scenes

Jianguo Zhang and Shaogang Gong

Abstract. Robust detection of people in video is critical in visual surveillance. In
this work we present a framework for robust people detection in highly cluttered
scenes with low resolution image sequences. Our model utilises both human ap-
pearance and their long-term motion information through a fusion formulated in a
Bayesian framework. In particular, we introduce a spatial pyramid Gaussian Mix-
ture approach to model variations of long-term human motion information, which
is computed via an improved background modeling using spatial motion constrains.
Simultaneously, people appearance is modeled by histograms of oriented gradients.
Experiments demonstrate that our method reduces significantly false positive rate
compared to that of a state of the art human detector under very challenging lighting
condition, occlusion and background clutter.

1 Introduction

Accurate and robust pedestrian detection in a busy public scene is an essential yet
challenging task in visual surveillance. The difficulties lie in modelling both object
and background clutter contributed by a host of factors including changing object
appearance, diversity of pose and scale, moving background, occlusion, imaging
noise, and lighting change. Usually pedestrians in public space are characterized
by two dominant visual features: appearance and motion . There is a large body of