Cover Image

A new unified method for detecting text from marathon runners and sports players in video (PR-D-19-01078R2)

Detecting text located on the torsos of marathon runners and sports players in video is a challenging issue due to poor quality and adverse effects caused by flexible/colorful clothing, and different structures of human bodies or actions. This paper presents a new unified method for tackling the abo...

Full description

Saved in:
Bibliographic Details
Main Authors: Nag, Sauradip, Shivakumara, Palaiahnakote, Pal, Umapada, Lu, Tong, Blumenstein, Michael
Format: Article
Published: ELSEVIER SCI LTD 2020
Subjects:
T Technology (General)
Online Access:http://eprints.um.edu.my/36308/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.um.eprints.36308
record_format eprints
spelling my.um.eprints.363082023-12-28T12:40:28Z http://eprints.um.edu.my/36308/ A new unified method for detecting text from marathon runners and sports players in video (PR-D-19-01078R2) Nag, Sauradip Shivakumara, Palaiahnakote Pal, Umapada Lu, Tong Blumenstein, Michael T Technology (General) Detecting text located on the torsos of marathon runners and sports players in video is a challenging issue due to poor quality and adverse effects caused by flexible/colorful clothing, and different structures of human bodies or actions. This paper presents a new unified method for tackling the above challenges. The proposed method fuses gradient magnitude and direction coherence of text pixels in a new way for detecting candidate regions. Candidate regions are used for determining the number of temporal frame clusters obtained by K-means clustering on frame differences. This process in turn detects key frames. The proposed method explores Bayesian probability for skin portions using color values at both pixel and component levels of temporal frames, which provides fused images with skin components. Based on skin information, the proposed method then detects faces and torsos by finding structural and spatial coherences between them. We further propose adaptive pixels linking a deep learning model for text detection from torso regions. The proposed method is tested on our own dataset collected from marathon/sports video and three standard datasets, namely, RBNR, MMM and R-ID of marathon images, to evaluate the performance. In addition, the proposed method is also tested on the standard natural scene datasets, namely, CTW1500 and MS-COCO text datasets, to show the objectiveness of the proposed method. A comparative study with the state-of-the-art methods on bib number/text detection of different datasets shows that the proposed method outperforms the existing methods. (C) 2020 Elsevier Ltd. All rights reserved. ELSEVIER SCI LTD 2020-11 Article PeerReviewed Nag, Sauradip and Shivakumara, Palaiahnakote and Pal, Umapada and Lu, Tong and Blumenstein, Michael (2020) A new unified method for detecting text from marathon runners and sports players in video (PR-D-19-01078R2). PATTERN RECOGNITION, 107. ISSN 00313203, DOI https://doi.org/10.1016/j.patcog.2020.107476 <https://doi.org/10.1016/j.patcog.2020.107476>. 10.1016/j.patcog.2020.107476
institution Universiti Malaya
building UM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaya
content_source UM Research Repository
url_provider http://eprints.um.edu.my/
topic T Technology (General)
spellingShingle T Technology (General)
Nag, Sauradip
Shivakumara, Palaiahnakote
Pal, Umapada
Lu, Tong
Blumenstein, Michael
A new unified method for detecting text from marathon runners and sports players in video (PR-D-19-01078R2)
description Detecting text located on the torsos of marathon runners and sports players in video is a challenging issue due to poor quality and adverse effects caused by flexible/colorful clothing, and different structures of human bodies or actions. This paper presents a new unified method for tackling the above challenges. The proposed method fuses gradient magnitude and direction coherence of text pixels in a new way for detecting candidate regions. Candidate regions are used for determining the number of temporal frame clusters obtained by K-means clustering on frame differences. This process in turn detects key frames. The proposed method explores Bayesian probability for skin portions using color values at both pixel and component levels of temporal frames, which provides fused images with skin components. Based on skin information, the proposed method then detects faces and torsos by finding structural and spatial coherences between them. We further propose adaptive pixels linking a deep learning model for text detection from torso regions. The proposed method is tested on our own dataset collected from marathon/sports video and three standard datasets, namely, RBNR, MMM and R-ID of marathon images, to evaluate the performance. In addition, the proposed method is also tested on the standard natural scene datasets, namely, CTW1500 and MS-COCO text datasets, to show the objectiveness of the proposed method. A comparative study with the state-of-the-art methods on bib number/text detection of different datasets shows that the proposed method outperforms the existing methods. (C) 2020 Elsevier Ltd. All rights reserved.
format Article
author Nag, Sauradip
Shivakumara, Palaiahnakote
Pal, Umapada
Lu, Tong
Blumenstein, Michael
author_facet Nag, Sauradip
Shivakumara, Palaiahnakote
Pal, Umapada
Lu, Tong
Blumenstein, Michael
author_sort Nag, Sauradip
title A new unified method for detecting text from marathon runners and sports players in video (PR-D-19-01078R2)
title_short A new unified method for detecting text from marathon runners and sports players in video (PR-D-19-01078R2)
title_full A new unified method for detecting text from marathon runners and sports players in video (PR-D-19-01078R2)
title_fullStr A new unified method for detecting text from marathon runners and sports players in video (PR-D-19-01078R2)
title_full_unstemmed A new unified method for detecting text from marathon runners and sports players in video (PR-D-19-01078R2)
title_sort new unified method for detecting text from marathon runners and sports players in video (pr-d-19-01078r2)
publisher ELSEVIER SCI LTD
publishDate 2020
url http://eprints.um.edu.my/36308/
_version_ 1787133816040587264
score 13.211869

Similar Items