An Interactive Pedestrian Re-Identification Tool with Semantic Based Re-Identification



Journal Title

Journal ISSN

Volume Title



Person re-identification is an essential task of recognizing and matching people from non-overlapping cameras. A typical application of person re-identification is identifying a particular person in a gallery of pedestrian images from a camera with one or more given probe images of this person from another camera. This is a chal- lenging and practical task that provides solutions for video-surveillance. In this work, we present a person re-identification software which is called Interactive Pedestrian Re-identification GUI (IPRG), and a semantic-based labelling tool named Reid It (Reidit). According to the growing need for surveillance applications, we develop IPRG to address the person searching and matching problem with the dataset from on-campus security camera videos. From these video frames, we can get semantic in- formation of the candidate such as height, ethnicity, cloth color, etc. By customizing these semantic features in IPRG, we can identify a candidate in the video database rapidly. We also propose a light-labelling tool, Reidit, for labelling pedestrian images with semantic features as the pre-processing for pedestrian recognition. We present an experiment on IPRG with Viewpoint Invariant Pedestrian Recognition (VIPeR) dataset which contains 632 identities. Our experiment shows that our software is more efficient and accurate compared with traditional manual solutions. Moreover, IPRG can handle the situation of missing query person in the database, and it will return the top ten possible individuals. Our software is compatible with different platforms and user-friendly with customizable databases and semantic features.



Person re-identification, Semantic