Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/105822
Title: TGC20ReId: a dataset for sport event re-identification in the wild
Authors: Peñate Sánchez, Adrián 
Freire Obregón, David Sebastián 
Lorenzo-Melián, Adrián
Lorenzo Navarro, José Javier 
Castrillón Santana, Modesto Fernando 
UNESCO Clasification: 120304 Inteligencia artificial
Keywords: Sport
Re-identification
Dataset
Issue Date: 2020
Project: Identificación Automática de Oradores en Sesiones Parlamentarias Usando Características Audiovisuales. 
Journal: Pattern Recognition Letters 
Abstract: Person re-identification (Re-ID) is the task of retrieving a person of interest taken from different cameras or from the same camera in different occasions. To address this challenging task, a large amount of labelled data is required both for testing and for learning. Such high quality annotated data is still rare for many Re-ID applications. In this paper, we introduce a novel dataset to evaluate Re-ID methods in complex real-world scenarios. In this case, we will be using a sporting event as the scenario. For this aim, participants in a 128 km night and day course were captured in five different recording points along the track and later manually identified and annotated. The dataset is evaluated using state-of-the-art techniques and wide array of experimental setups are considered, such as: day vs. night, motion blur, changes in clothing, etc. The evaluation suggests that the features present in the proposed dataset (time difference, unrestricted weather and illumination capture conditions, and the possibility of clothes changes between probe and gallery) pose a challenging scenario for future development in the Re-ID problem.
URI: http://hdl.handle.net/10553/105822
ISSN: 0167-8655
DOI: 10.1016/j.patrec.2020.08.003
Source: Pattern Recognition Letters [0167-8655], v. 138 (october), p. 355-361
Appears in Collections:Artículos
Show full item record

Page view(s)

24
checked on May 30, 2021

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.