A new deep wavefront based model for text localization in 3D video

With the evolution of electronic devices, such as 3D cameras, addressing the challenges of text localization in 3D video (e.g., for indexing) is increasingly drawing the attention of the multimedia and video processing community. Existing methods focus on 2D video and their performance in the presen...

Full description

Saved in:
Bibliographic Details
Main Authors: Nandanwar, Lokesh, Shivakumara, Palaiahnakote, Ramachandra, Raghavendra, Lu, Tong, Pal, Umapada, Antonacopoulos, Apostolos, Lu, Yue
Format: Article
Published: Institute of Electrical and Electronics Engineers 2022
Subjects:
Online Access:http://eprints.um.edu.my/42144/
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Universiti Malaya
id my.um.eprints.42144
record_format eprints
spelling my.um.eprints.421442023-10-16T04:02:05Z http://eprints.um.edu.my/42144/ A new deep wavefront based model for text localization in 3D video Nandanwar, Lokesh Shivakumara, Palaiahnakote Ramachandra, Raghavendra Lu, Tong Pal, Umapada Antonacopoulos, Apostolos Lu, Yue QA75 Electronic computers. Computer science With the evolution of electronic devices, such as 3D cameras, addressing the challenges of text localization in 3D video (e.g., for indexing) is increasingly drawing the attention of the multimedia and video processing community. Existing methods focus on 2D video and their performance in the presence of the challenges in 3D video, such as shadow areas associated with text and irregularly sized and shaped text, degrades. This paper proposes the first approach that successfully addresses the challenges of 3D video in addition to those of 2D. It employs a number of innovations, among which, the first is the Generalized Gradient Vector Flow (GGVF) for dominant points detection. The second is the Wavefront concept for text candidate point detection from those dominant points. In addition, an Adaptive B-Spline Polygon Curve Network (ABS-Net) is proposed for accurate text localization in 3D videos by constructing tight fitting bounding polygons using text candidate points. Extensive experiments on custom (3D video) and standard datasets (2D video and scene text) show that the proposed method is practical and useful, and overall outperforms existing state-of-the-art methods. Institute of Electrical and Electronics Engineers 2022-06 Article PeerReviewed Nandanwar, Lokesh and Shivakumara, Palaiahnakote and Ramachandra, Raghavendra and Lu, Tong and Pal, Umapada and Antonacopoulos, Apostolos and Lu, Yue (2022) A new deep wavefront based model for text localization in 3D video. IEEE Transactions on Circuits and Systems for Video Technology, 32 (6). pp. 3375-3389. ISSN 1051-8215, DOI https://doi.org/10.1109/TCSVT.2021.3110990 <https://doi.org/10.1109/TCSVT.2021.3110990>. 10.1109/TCSVT.2021.3110990
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 QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Nandanwar, Lokesh
Shivakumara, Palaiahnakote
Ramachandra, Raghavendra
Lu, Tong
Pal, Umapada
Antonacopoulos, Apostolos
Lu, Yue
A new deep wavefront based model for text localization in 3D video
description With the evolution of electronic devices, such as 3D cameras, addressing the challenges of text localization in 3D video (e.g., for indexing) is increasingly drawing the attention of the multimedia and video processing community. Existing methods focus on 2D video and their performance in the presence of the challenges in 3D video, such as shadow areas associated with text and irregularly sized and shaped text, degrades. This paper proposes the first approach that successfully addresses the challenges of 3D video in addition to those of 2D. It employs a number of innovations, among which, the first is the Generalized Gradient Vector Flow (GGVF) for dominant points detection. The second is the Wavefront concept for text candidate point detection from those dominant points. In addition, an Adaptive B-Spline Polygon Curve Network (ABS-Net) is proposed for accurate text localization in 3D videos by constructing tight fitting bounding polygons using text candidate points. Extensive experiments on custom (3D video) and standard datasets (2D video and scene text) show that the proposed method is practical and useful, and overall outperforms existing state-of-the-art methods.
format Article
author Nandanwar, Lokesh
Shivakumara, Palaiahnakote
Ramachandra, Raghavendra
Lu, Tong
Pal, Umapada
Antonacopoulos, Apostolos
Lu, Yue
author_facet Nandanwar, Lokesh
Shivakumara, Palaiahnakote
Ramachandra, Raghavendra
Lu, Tong
Pal, Umapada
Antonacopoulos, Apostolos
Lu, Yue
author_sort Nandanwar, Lokesh
title A new deep wavefront based model for text localization in 3D video
title_short A new deep wavefront based model for text localization in 3D video
title_full A new deep wavefront based model for text localization in 3D video
title_fullStr A new deep wavefront based model for text localization in 3D video
title_full_unstemmed A new deep wavefront based model for text localization in 3D video
title_sort new deep wavefront based model for text localization in 3d video
publisher Institute of Electrical and Electronics Engineers
publishDate 2022
url http://eprints.um.edu.my/42144/
_version_ 1781704601172443136