Learning to Match Appearances by Correlations in a Covariance Metric Space

This paper addresses the problem of appearance matching across disjoint camera views. Signi cant appearance changes, caused by variations in view angle, illumination and object pose, make the problem challenging. We propose to formulate the appearance matching problem as the task of learning a model that selects the most descriptive features for a speci c class of objects. Learning is performed in a covariance metric space using an entropy-driven criterion. Our main idea is that di erent regions of the object appearance ought to be matched using various strategies to obtain a distinctive representation. The proposed technique has been successfully applied to the person re-identi cation problem, in which a human appearance has to be matched across nonoverlapping cameras. We demonstrate that our approach improves state of the art performance in the context of pedestrian recognition.