Open-Set Person Re-Identification through Error Resilient Recurring Gallery Building

In person re-identification, individuals must be correctly identified in images that come from different cameras or are captured at different points in time. In the open-set case, the above needs be achieved for people who have not been previously recognised. In this paper, we propose a universal method for building a multi-shot gallery of observed reference identities recurrently online. We perform L2-norm descriptor matching for gallery retrieval using descriptors produced by a generic closed-set re-identification system. Multi-shot gallery is continuously updated by replacing outliers with newly matched descriptors. Outliers are detected using the Isolation Forest algorithm, thus ensuring that the gallery is resilient to erroneous assignments, leading to improved re-identification results in the open-set case.