Cognitive Data Association for Visual Person Tracking

In this paper, we introduce a cognitive approach for person tracking on a mobile platform. The approach is based on a biologically motivated attention system which is able to detect regions of interest in images based on concepts of the human visual system. A top-down guided visual search module of the system enables to especially highlight features which fit to a previously learned target object. Here, the appearance of a person is learned ad-hoc within the first image in which the person is detected. In subsequent images, the attention system searches for the target features and builds a top-down, target-related saliency map. This enables to focus on the most relevant features of especially this person in especially this scene without knowing anything about a particular person or scene in advance. The system is able to operate in real-time and to cope with the requirements of real-world tasks such as illumination variations.