Please use this identifier to cite or link to this item:
Title: TGCRbNW: a dataset for runner bib number detection (and recognition) in the wild
Authors: Hernández-Carrascosa, Pablo
Peñate Sánchez, Adrián 
Lorenzo-Navarro, Javier 
Freire-Obregón, David 
Castrillón-Santana, Modesto 
UNESCO Clasification: 220990 Tratamiento digital. Imágenes
Issue Date: 2020
Publisher: Institute of Electrical and Electronics Engineers (IEEE) 
Journal: Proceedings - International Conference on Pattern Recognition 
Conference: 25th International Conference on Pattern Recognition (ICPR 2020) 
Abstract: Racing bib number (RBN) detection and recognition is a specific problem related to text recognition in natural scenes. In this paper, we present a novel dataset created after registering participants in a real ultrarunning competition which comprises a wide range of acquisition conditions in five different recording points, including nightlight and daylight. The dataset contains more than 3K samples of over 400 different individuals. The aim is to provide an”in the wild” benchmark for both RBN detection and recognition problems. To illustrate the present difficulties, the dataset is evaluated for RBN detection using different Faster R-CNN specific detection models, filtering its output with heuristics based on body detection to improve the overall detection performance. Initial results are promising, but there is still significant room for improvement. And detection is just the first step to accomplish”in the wild” RBN recognition.
ISBN: 978-1-7281-8808-9
ISSN: 1051-4651
DOI: 10.1109/ICPR48806.2021.9412220
Source: Proceedings - International Conference on Pattern Recognition [ISSN 1051-4651], p. 9445-9451, (Enero 2020)
Appears in Collections:Actas de congresos
Show full item record


checked on Oct 2, 2022

Page view(s)

checked on Sep 24, 2022

Google ScholarTM




Export metadata

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