Pedestrian Detection and Tracking in Challenging Surveillance Videos

Abstract

In this chapter we propose a novel approach for real-time robust pedestrian tracking in surveillance images. Typical surveillance images are challenging to analyse since the overall image quality is low (e.g. low resolution and high compression). Furthermore often birds-eye viewpoint wide-angle lenses are used to achieve maximum coverage with a minimal amount of cameras. These specific viewpoints make it unfeasible to directly apply existing pedestrian detection techniques. Moreover, real-time processing speeds are required. To overcome these problems we introduce a pedestrian detection and tracking framework which exploits and integrates these scene constraints to achieve high accuracy results. We performed extensive experiments on publically available challenging real-life video sequences concerning both speed and accuracy. Our approach achieves excellent accuracy results while still meeting the stringent real-time demands needed for these surveillance applications, using only a single-core CPU implementation.

Crane Safety System with Monocular and Controlled Zoom Cameras

“…Many different proposed methodologies have been proposed, however, these are not really suited to our needs. These approaches often times make use of the fact that either the camera itself is static [31,33] or uses distinct features of the background, like a street [3]. Some methodologies use features which are prevalent even in top view images, like the head-shoulder shape [34], which may be different due to helmets or carried objects in an construction site environment.…”