1. How to submit my research paper? What’s the process of publication of my paper?
The journal receives submitted manuscripts via email only. Please submit your research paper in .doc or .pdf format to...
2. Can I submit an abstract?
The journal publishes full research papers. So only full paper submission should be considered...[Read More]

Enabling Open-Set Person Re-Identification for Real-World Scenarios

Tunc Alkanat, Egor Bondarev, and Peter H. N. De With
Electrical Engineering Department, Eindhoven University of Technology, Eindhoven, The Netherlands

Abstract—Person re-identification (re-ID) is a significant problem of computer vision with increasing scientific attention. To date, numerous studies have been conducted to improve the accuracy and robustness of person re-ID to meet the practical demands. However, most of the previous efforts concentrated on solving the closed-set variant of the problem, where a query is assumed to always have a correct match within the set of known people (the gallery set). However, this assumption is usually not valid for the industrial re-ID use cases. In this study, we focus on the open-set person re-ID problem, where, in addition to the similarity ranking, the solution is expected to detect the presence or absence of a given query identity within the gallery set. To determine good practices and to assess the practicality of the person re-ID in industrial applications, first, we convert popular closed-set person re-ID datasets into the open-set scenario. Second, we compare performance of eight state-of-the-art closed-set person re-ID methods under the open-set conditions. Third, we experimentally determine the efficiency of using different loss function combinations for the open-set problem. Finally, we investigate the impact of a statistics-driven gallery refinement approach on the open-set person re-ID performance in the low false-acceptance rate (FAR) region, while simultaneously reducing the computational demands of retrieval. Results show an average detection and identification rate increase of 8.38% and 3.39% on the DukeMTMC-reID and Market1501 datasets, respectively, for a FAR of 1%.

Index Terms—person re-identification, open-set, image retrieval

Cite: Tunc Alkanat, Egor Bondarev, and Peter H. N. De With, "Enabling Open-Set Person Re-Identification for Real-World Scenarios," Journal of Image and Graphics, Vol. 8, No. 2, pp. 26-36, June 2020. doi: 10.18178/joig.8.2.26-36

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.

Copyright © 2012-2020 Journal of Image and Graphics, All Rights Reserved
E-mail: joig@ejournal.net