Improving Object Tracking by Adapting Detectors

The goal of model-based object trackers is to automatically detect and track specific objects, such as cars or pedestrians. To solve this problem, many modern trackers train a detector on a collection of annotated object images and use the trained detector in a tracking-by-detection framework. A major limitation of such an approach is that a single, generic detector is used to track specific objects, the additional information on the visual appearance of the particular object under consideration that is available after the initial detection is ignored. This paper proposes an approach that addresses this limitation by adapting the appearance model for each particular object using online learning techniques. We demonstrate the effectiveness of the approach in a state-of-the-art object detector based on deformable template models, the parameters of which are adapted online using an online structured SVM. We further improve the performance of the resulting model-based trackers by online learning a prior distribution over the size of objects. The experimental evaluation of our tracker demonstrates its effectiveness in pedestrian tracking.