Improving open-set person re-identification by statistics-driven gallery refinement

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Samenvatting

Person re-identification (re-ID) is a valuable tool for multi-camera tracking of persons. Up till now, research on person re-ID has mainly focused on the closed-set case, where a given query is assumed to always have a correct match in the gallery set, which does not hold for practical scenarios. In this study, we explore the open-set person re-ID problem with queries not always included in the gallery set. First, we convert the popular closed-set person re-ID datasets into the open-set scenario. Second, we compare the performances of six state-of-the-art closed-set person re-ID methods under open-set conditions. Third, we investigate the impact of a simple and fast statistics-driven gallery refinement approach on the open-set person re-ID performance. Extensive experimental evaluations show that, gallery refinement increases the performance of existing methods in the low false-accept rate (FAR) region, while simultaneously reducing the computational demands of retrieval. Results show an average detection and identification rate (DIR) increase of 7.91% and 3.31% on the DukeMTMC-reID and Market1501 datasets, respectively, for an FAR of 1%.

Originele taal-2Engels
Titel12th International Conference on Machine Vision, ICMV 2019
RedacteurenWolfgang Osten, Dmitry Nikolaev, Jianhong Zhou
UitgeverijSPIE
Aantal pagina's8
ISBN van elektronische versie9781510636439
DOI's
StatusGepubliceerd - 31 jan 2020
Evenement12th International Conference on Machine Vision, ICMV 2019 - Amsterdam, Nederland
Duur: 16 nov 201918 nov 2019

Publicatie series

NaamProceedings of SPIE - The International Society for Optical Engineering
Volume11433
ISSN van geprinte versie0277-786X
ISSN van elektronische versie1996-756X

Congres

Congres12th International Conference on Machine Vision, ICMV 2019
LandNederland
StadAmsterdam
Periode16/11/1918/11/19

Vingerafdruk Duik in de onderzoeksthema's van 'Improving open-set person re-identification by statistics-driven gallery refinement'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit

    Alkanat, T., Bondarev, E., & De With, P. H. N. (2020). Improving open-set person re-identification by statistics-driven gallery refinement. In W. Osten, D. Nikolaev, & J. Zhou (editors), 12th International Conference on Machine Vision, ICMV 2019 [114330V] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11433). SPIE. https://doi.org/10.1117/12.2559441