The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Dans de nombreux systèmes de communication écran-caméra (S2C), la méthode de prétraitement des codes-barres est une condition préalable importante, car les codes-barres peuvent être déformés en raison de divers facteurs environnementaux. Cependant, des études antérieures se sont concentrées sur la détection de codes-barres dans des conditions statiques ; à ce jour, peu d'études ont été réalisées sur des conditions dynamiques (par exemple, le flux vidéo code-barres ou l'émetteur et le récepteur sont en mouvement). Par conséquent, nous présentons une méthode de détection et de suivi de codes-barres dynamiques basée sur un réseau siamois. L'épine dorsale du CNN dans le réseau siamois est améliorée par SE-ResNet. La précision de détection a atteint 89.5 %, ce qui se distingue des autres réseaux de détection classiques. L'EAO atteint 0.384, ce qui est meilleur que les méthodes de suivi précédentes. Elle est également supérieure aux autres méthodes en termes de précision et de robustesse. Le SE-ResNet dans cet article a amélioré l'EAO de 1.3 % par rapport au ResNet dans SiamMask. De plus, notre méthode n'est pas seulement applicable aux codes-barres statiques, mais permet également le suivi et la segmentation en temps réel des codes-barres capturés dans des situations dynamiques.
Menglong WU
North China University of Technology
Cuizhu QIN
North China University of Technology
Hongxia DONG
North China University of Technology
Wenkai LIU
North China University of Technology
Xiaodong NIE
State Grid Beijing Information & Telecommunication Company
Xichang CAI
North China University of Technology
Yundong LI
North China University of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Menglong WU, Cuizhu QIN, Hongxia DONG, Wenkai LIU, Xiaodong NIE, Xichang CAI, Yundong LI, "Detection and Tracking Method for Dynamic Barcodes Based on a Siamese Network" in IEICE TRANSACTIONS on Communications,
vol. E105-B, no. 7, pp. 866-875, July 2022, doi: 10.1587/transcom.2021EBP3112.
Abstract: In many screen to camera communication (S2C) systems, the barcode preprocessing method is a significant prerequisite because barcodes may be deformed due to various environmental factors. However, previous studies have focused on barcode detection under static conditions; to date, few studies have been carried out on dynamic conditions (for example, the barcode video stream or the transmitter and receiver are moving). Therefore, we present a detection and tracking method for dynamic barcodes based on a Siamese network. The backbone of the CNN in the Siamese network is improved by SE-ResNet. The detection accuracy achieved 89.5%, which stands out from other classical detection networks. The EAO reaches 0.384, which is better than previous tracking methods. It is also superior to other methods in terms of accuracy and robustness. The SE-ResNet in this paper improved the EAO by 1.3% compared with ResNet in SiamMask. Also, our method is not only applicable to static barcodes but also allows real-time tracking and segmentation of barcodes captured in dynamic situations.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2021EBP3112/_p
Copier
@ARTICLE{e105-b_7_866,
author={Menglong WU, Cuizhu QIN, Hongxia DONG, Wenkai LIU, Xiaodong NIE, Xichang CAI, Yundong LI, },
journal={IEICE TRANSACTIONS on Communications},
title={Detection and Tracking Method for Dynamic Barcodes Based on a Siamese Network},
year={2022},
volume={E105-B},
number={7},
pages={866-875},
abstract={In many screen to camera communication (S2C) systems, the barcode preprocessing method is a significant prerequisite because barcodes may be deformed due to various environmental factors. However, previous studies have focused on barcode detection under static conditions; to date, few studies have been carried out on dynamic conditions (for example, the barcode video stream or the transmitter and receiver are moving). Therefore, we present a detection and tracking method for dynamic barcodes based on a Siamese network. The backbone of the CNN in the Siamese network is improved by SE-ResNet. The detection accuracy achieved 89.5%, which stands out from other classical detection networks. The EAO reaches 0.384, which is better than previous tracking methods. It is also superior to other methods in terms of accuracy and robustness. The SE-ResNet in this paper improved the EAO by 1.3% compared with ResNet in SiamMask. Also, our method is not only applicable to static barcodes but also allows real-time tracking and segmentation of barcodes captured in dynamic situations.},
keywords={},
doi={10.1587/transcom.2021EBP3112},
ISSN={1745-1345},
month={July},}
Copier
TY - JOUR
TI - Detection and Tracking Method for Dynamic Barcodes Based on a Siamese Network
T2 - IEICE TRANSACTIONS on Communications
SP - 866
EP - 875
AU - Menglong WU
AU - Cuizhu QIN
AU - Hongxia DONG
AU - Wenkai LIU
AU - Xiaodong NIE
AU - Xichang CAI
AU - Yundong LI
PY - 2022
DO - 10.1587/transcom.2021EBP3112
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E105-B
IS - 7
JA - IEICE TRANSACTIONS on Communications
Y1 - July 2022
AB - In many screen to camera communication (S2C) systems, the barcode preprocessing method is a significant prerequisite because barcodes may be deformed due to various environmental factors. However, previous studies have focused on barcode detection under static conditions; to date, few studies have been carried out on dynamic conditions (for example, the barcode video stream or the transmitter and receiver are moving). Therefore, we present a detection and tracking method for dynamic barcodes based on a Siamese network. The backbone of the CNN in the Siamese network is improved by SE-ResNet. The detection accuracy achieved 89.5%, which stands out from other classical detection networks. The EAO reaches 0.384, which is better than previous tracking methods. It is also superior to other methods in terms of accuracy and robustness. The SE-ResNet in this paper improved the EAO by 1.3% compared with ResNet in SiamMask. Also, our method is not only applicable to static barcodes but also allows real-time tracking and segmentation of barcodes captured in dynamic situations.
ER -