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
A inspeção automática de falhas anti-espinhos de pássaros baseada em visão artificial, em vez da identificação manual, continua sendo um grande desafio. Neste artigo, propusemos um romance Objeto Posição Eincorporação Network (OPENnet), que pode melhorar a precisão da localização anti-espinhos de pássaros. OPENnet pode prever simultaneamente as caixas de localização do dispositivo de suporte e espinho anti-pássaro usando a rede dupla proposta. E então, OPENnet é otimizado usando a função de perda simbiótica proposta (SymLoss), que incorpora a posição do objeto na rede. Os experimentos abrangentes são conduzidos no conjunto de dados de vídeo ferroviário real. OPENnet produz desempenho competitivo na localização de espinhos anti-pássaros. Especificamente, o desempenho de localização ganha +3.65 AP, +2.10 AP50 e +1.22 AP75.
Zhuo WANG
Beijing Jiaotong University
Junbo LIU
China Academy of Railway Sciences Corporation Limited
Fan WANG
China Academy of Railway Sciences Corporation Limited
Jun WU
Beijing Jiaotong University
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.
Copiar
Zhuo WANG, Junbo LIU, Fan WANG, Jun WU, "OPENnet: Object Position Embedding Network for Locating Anti-Bird Thorn of High-Speed Railway" in IEICE TRANSACTIONS on Information,
vol. E106-D, no. 5, pp. 824-828, May 2023, doi: 10.1587/transinf.2022DLL0011.
Abstract: Machine vision-based automatic anti-bird thorn failure inspection, instead of manual identification, remains a great challenge. In this paper, we proposed a novel Object Position Embedding Network (OPENnet), which can improve the precision of anti-bird thorn localization. OPENnet can simultaneously predict the location boxes of the support device and anti-bird thorn by using the proposed double-head network. And then, OPENnet is optimized using the proposed symbiotic loss function (SymLoss), which embeds the object position into the network. The comprehensive experiments are conducted on the real railway video dataset. OPENnet yields competitive performance on anti-bird thorn localization. Specifically, the localization performance gains +3.65 AP, +2.10 AP50, and +1.22 AP75.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2022DLL0011/_p
Copiar
@ARTICLE{e106-d_5_824,
author={Zhuo WANG, Junbo LIU, Fan WANG, Jun WU, },
journal={IEICE TRANSACTIONS on Information},
title={OPENnet: Object Position Embedding Network for Locating Anti-Bird Thorn of High-Speed Railway},
year={2023},
volume={E106-D},
number={5},
pages={824-828},
abstract={Machine vision-based automatic anti-bird thorn failure inspection, instead of manual identification, remains a great challenge. In this paper, we proposed a novel Object Position Embedding Network (OPENnet), which can improve the precision of anti-bird thorn localization. OPENnet can simultaneously predict the location boxes of the support device and anti-bird thorn by using the proposed double-head network. And then, OPENnet is optimized using the proposed symbiotic loss function (SymLoss), which embeds the object position into the network. The comprehensive experiments are conducted on the real railway video dataset. OPENnet yields competitive performance on anti-bird thorn localization. Specifically, the localization performance gains +3.65 AP, +2.10 AP50, and +1.22 AP75.},
keywords={},
doi={10.1587/transinf.2022DLL0011},
ISSN={1745-1361},
month={May},}
Copiar
TY - JOUR
TI - OPENnet: Object Position Embedding Network for Locating Anti-Bird Thorn of High-Speed Railway
T2 - IEICE TRANSACTIONS on Information
SP - 824
EP - 828
AU - Zhuo WANG
AU - Junbo LIU
AU - Fan WANG
AU - Jun WU
PY - 2023
DO - 10.1587/transinf.2022DLL0011
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E106-D
IS - 5
JA - IEICE TRANSACTIONS on Information
Y1 - May 2023
AB - Machine vision-based automatic anti-bird thorn failure inspection, instead of manual identification, remains a great challenge. In this paper, we proposed a novel Object Position Embedding Network (OPENnet), which can improve the precision of anti-bird thorn localization. OPENnet can simultaneously predict the location boxes of the support device and anti-bird thorn by using the proposed double-head network. And then, OPENnet is optimized using the proposed symbiotic loss function (SymLoss), which embeds the object position into the network. The comprehensive experiments are conducted on the real railway video dataset. OPENnet yields competitive performance on anti-bird thorn localization. Specifically, the localization performance gains +3.65 AP, +2.10 AP50, and +1.22 AP75.
ER -