Evaluating Appearance Models for Recognition, Reacquisition, and Tracking

Traditionally, appearance models for recognition, reacquisition and tracking problems have been evaluated independently using metrics applied to a complete system. It is shown that appearance models for these three problems can be evaluated using a cumulative matching curve on a standardized dataset, and that this one curve can be converted to a synthetic disambiguation rate for single camera tracking or a synthetic reacquisition rate for cross camera tracking. A challenging new dataset for viewpoint invariant pedestrian recognition (VIPeR) is provided as an example. This dataset contains 632 pedestrian image pairs from arbitrary viewpoints. Several baseline methods are tested on this dataset and the results are presented as a benchmark for future appearance models and matching methods.