Color based tracing in real-life surveillance data

For post incident investigation a complete reconstruction of an event is needed based on surveillance footage of the crime scene and surrounding areas. Reconstruction of the whereabouts of the people in the incident requires the ability to follow persons within a camera’s field-of-view (tracking) and between different cameras (tracing). In constrained situations a combination of shape and color information is shown to be best at discriminating between persons. In this paper we focus on person tracing between uncalibrated cameras with non-overlapping field-of-view. In these situations standard image matching techniques perform badly due to large, uncontrolled variations in viewpoint, light source, background and shading. We show that in these unconstrained real-life situations, tracing results are very dependent on the appearance of the subject.