改进YOLOX的唐卡壁画目标检测算法

TP391.4; 热贡唐卡壁画作为人类及国家级非物质文化遗产是藏族文化中独具特色的艺术形式,其画面不仅表现出了佛教本生故事,更体现了藏地的历史、地理、文化、科技等内容.然而,不具备热贡艺术专业知识的人们很难对其进行了解.因此提出了一种唐卡壁画元素的自动检测算法,用于推动唐卡壁画的传播.通过对YOLOX算法进行改进,提出了 ECAMH-YOLOX模型对唐卡壁画图像进行检测.ECAMH-YOLOX模型是在YOLOX的基础上增加了高效通道注意力模块,在保持轻量化的同时获得更好的图像全局信息;同时为了更好地检测不同尺度的目标,在检测头模块增加了一个新的检测头,通过四个检测头对图像进行检测,以此来提高不...

Full description

Saved in:
Bibliographic Details
Published in计算机工程与应用 Vol. 60; no. 18; pp. 248 - 255
Main Authors 李洪运, 张效娟, 赵洋, 彭春燕
Format Journal Article
LanguageChinese
Published 省部共建藏语智能信息处理及应用国家重点实验室,西宁 810016%合肥工业大学计算机与信息学院,合肥 230002 15.09.2024
青海师范大学计算机学院,西宁 810016
Subjects
Online AccessGet full text
ISSN1002-8331
DOI10.3778/j.issn.1002-8331.2306-0219

Cover

Abstract TP391.4; 热贡唐卡壁画作为人类及国家级非物质文化遗产是藏族文化中独具特色的艺术形式,其画面不仅表现出了佛教本生故事,更体现了藏地的历史、地理、文化、科技等内容.然而,不具备热贡艺术专业知识的人们很难对其进行了解.因此提出了一种唐卡壁画元素的自动检测算法,用于推动唐卡壁画的传播.通过对YOLOX算法进行改进,提出了 ECAMH-YOLOX模型对唐卡壁画图像进行检测.ECAMH-YOLOX模型是在YOLOX的基础上增加了高效通道注意力模块,在保持轻量化的同时获得更好的图像全局信息;同时为了更好地检测不同尺度的目标,在检测头模块增加了一个新的检测头,通过四个检测头对图像进行检测,以此来提高不同尺寸目标的检测结果;并使用SIoU损失函数计算回归损失以此来加快模型的收敛速度,提高模型效果.实验结果证明,ECAMH-YOLOX模型在所构建的唐卡壁画数据集上均不存在漏检错检的情况,而YOLOX算法存在对小目标的漏检现象,并且ECAMH-YOLOX 模型的mAP0.5:0.95达到了 55.9%,比YOLOX算法提升了0.049.该模型在保持轻量化的同时,进一步提高了检测效果.也增加了人们了解热贡艺术的途径.
AbstractList TP391.4; 热贡唐卡壁画作为人类及国家级非物质文化遗产是藏族文化中独具特色的艺术形式,其画面不仅表现出了佛教本生故事,更体现了藏地的历史、地理、文化、科技等内容.然而,不具备热贡艺术专业知识的人们很难对其进行了解.因此提出了一种唐卡壁画元素的自动检测算法,用于推动唐卡壁画的传播.通过对YOLOX算法进行改进,提出了 ECAMH-YOLOX模型对唐卡壁画图像进行检测.ECAMH-YOLOX模型是在YOLOX的基础上增加了高效通道注意力模块,在保持轻量化的同时获得更好的图像全局信息;同时为了更好地检测不同尺度的目标,在检测头模块增加了一个新的检测头,通过四个检测头对图像进行检测,以此来提高不同尺寸目标的检测结果;并使用SIoU损失函数计算回归损失以此来加快模型的收敛速度,提高模型效果.实验结果证明,ECAMH-YOLOX模型在所构建的唐卡壁画数据集上均不存在漏检错检的情况,而YOLOX算法存在对小目标的漏检现象,并且ECAMH-YOLOX 模型的mAP0.5:0.95达到了 55.9%,比YOLOX算法提升了0.049.该模型在保持轻量化的同时,进一步提高了检测效果.也增加了人们了解热贡艺术的途径.
Abstract_FL Regong Tangka and murals,as a distinctive art form in Tibetan culture and recognized as human and national-level intangible cultural heritage,not only depict the stories of Buddhist origins but also embody the history,geography,culture,and technology of the Tibetan region.However,people without specialized knowledge of Regong arts find it challenging to understand their significance.Therefore,an automatic detection algorithm for Tangka and mural elements is proposed to promote the dissemination of Tangka and murals.This study improves the YOLOX algorithm and introduces the ECAMH-YOLOX model for detecting Tangka mural images.The ECAMH-YOLOX model is an improvement of the YOLOX framework,incorporating an efficient channel attention module.This module allows the model to capture better global information from images while maintaining a lightweight design.Additionally,to improve the detection of objects at different scales,a new detection head is added in the detection head module,facilitating detection through four detection heads to enhance results for objects of various sizes.The SIoU loss function is employed to calculate regression loss,which accelerates model convergence and improves model effectiveness.Experimental results demonstrate that the ECAMH-YOLOX model exhibits no instances of missed or false detection on the constructed Tangka and mural dataset,while the YOLOX algorithm shows missed detection for small objects.Moreover,the ECAMH-YOLOX model achieves an mAP0.5:0.95 of 55.9%,a 0.049 improvement over the YOLOX algorithm.The proposed model not only maintains a lightweight structure but also improves detection performance.In addition,it provides a pathway for people to gain a deeper understanding of Regong arts.
Author 李洪运
张效娟
彭春燕
赵洋
AuthorAffiliation 青海师范大学计算机学院,西宁 810016;省部共建藏语智能信息处理及应用国家重点实验室,西宁 810016%合肥工业大学计算机与信息学院,合肥 230002
AuthorAffiliation_xml – name: 青海师范大学计算机学院,西宁 810016;省部共建藏语智能信息处理及应用国家重点实验室,西宁 810016%合肥工业大学计算机与信息学院,合肥 230002
Author_FL PENG Chunyan
ZHAO Yang
ZHANG Xiaojuan
LI Hongyun
Author_FL_xml – sequence: 1
  fullname: LI Hongyun
– sequence: 2
  fullname: ZHANG Xiaojuan
– sequence: 3
  fullname: ZHAO Yang
– sequence: 4
  fullname: PENG Chunyan
Author_xml – sequence: 1
  fullname: 李洪运
– sequence: 2
  fullname: 张效娟
– sequence: 3
  fullname: 赵洋
– sequence: 4
  fullname: 彭春燕
BookMark eNo9jT9Lw0AcQG-oYG37JdwEE393v1zuMkrxHwSyVNCp3CW50iBX8BDJpiA4iOAQEeyidO8iDuLgp0nix7CgOD14w3sbpGNnNidkk4KPQsidwp86Z30KwDyJSH2GEHrAaNQh3X-7TgbOTTVwioILjLpku6k-vr_mp0mcnLTPN3X1UN-_1ovrtvps58vm5bZZXDXvd-3yqXl77JM1o85cPvhjjxzv742Gh16cHBwNd2PPUQjR48gizWmWIw0V05lmMuApclSZiJTOjVy9eZAK0EaqXGWgMhmkgTaaozQR9sjWb_dSWaPsZFzMLs7t6jguXDFJy7JkwAIqgSH-ANqyVwc
ClassificationCodes TP391.4
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.3778/j.issn.1002-8331.2306-0219
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
DocumentTitle_FL Object Detection Algorithm for Thangka and Mural with Improved YOLOX
EndPage 255
ExternalDocumentID jsjgcyyy202418023
GrantInformation_xml – fundername: (青海省重点研发与成果转化项目); (国家自然科学基金); (国家重点研发计划); (青海师范大学大学生创新创业训练计划项目)
  funderid: (青海省重点研发与成果转化项目); (国家自然科学基金); (国家重点研发计划); (青海师范大学大学生创新创业训练计划项目)
GroupedDBID -0Y
2B.
4A8
5XA
5XJ
92H
92I
93N
ABJNI
ACGFS
ALMA_UNASSIGNED_HOLDINGS
CCEZO
CUBFJ
CW9
PSX
TCJ
TGT
U1G
U5S
ID FETCH-LOGICAL-s1063-5329b51de316a2bdb2845c353ad79abef857354c70bf8aead0ad84c4bfb538f93
ISSN 1002-8331
IngestDate Thu May 29 04:10:55 EDT 2025
IsPeerReviewed false
IsScholarly false
Issue 18
Keywords 壁画
Thangka
mural
YOLOX
目标检测
channel attention
object detection
唐卡
通道注意力
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1063-5329b51de316a2bdb2845c353ad79abef857354c70bf8aead0ad84c4bfb538f93
PageCount 8
ParticipantIDs wanfang_journals_jsjgcyyy202418023
PublicationCentury 2000
PublicationDate 2024-09-15
PublicationDateYYYYMMDD 2024-09-15
PublicationDate_xml – month: 09
  year: 2024
  text: 2024-09-15
  day: 15
PublicationDecade 2020
PublicationTitle 计算机工程与应用
PublicationTitle_FL Computer Engineering and Applications
PublicationYear 2024
Publisher 省部共建藏语智能信息处理及应用国家重点实验室,西宁 810016%合肥工业大学计算机与信息学院,合肥 230002
青海师范大学计算机学院,西宁 810016
Publisher_xml – name: 省部共建藏语智能信息处理及应用国家重点实验室,西宁 810016%合肥工业大学计算机与信息学院,合肥 230002
– name: 青海师范大学计算机学院,西宁 810016
SSID ssib051375739
ssib001102935
ssj0000561668
ssib023646291
ssib057620132
Score 1.9688108
Snippet TP391.4;...
SourceID wanfang
SourceType Aggregation Database
StartPage 248
Title 改进YOLOX的唐卡壁画目标检测算法
URI https://d.wanfangdata.com.cn/periodical/jsjgcyyy202418023
Volume 60
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9QwEI5Ke4ED4ineqhA-lZQkjmP76OwmqlBLD7RSOVVJNinqYZFoObQnkJA4ICQORUj0Auq9F8QBceDX7C4_g5mJd7PbFlSQVivLM575PJP12Fl77Dj3Sl-VHY-XrhAld0NdcDeHSOvyLAshGklZZfiP7tKjaGE1fLgm1qamJ06XbOfzxe6J50r-x6tQB37FU7L_4NmRUKiAMvgXvsHD8H0qH7MkYjpksWaJYnHKdPxkeXF5jSWSacNUyBKBdO1hQbWZ8bFgOEwfiQeaxlSImUlQmPGYklTguAUCCjE0JB5g0ESKOasvrBzOaVE5UI0_waZbLDaoLoZKQSRFokApFBIiGcRQIzGjPbXUuk0soA0oZtg9r2GBxi2Ei7wAUVHHFNNpw6IQPHxqKSqeaAzGaFNjZdFBv2237DuQIMQNG_UpUHpqCWiLbKeZ4qgOzQrCyKxgypiQQv9VSkZJh0q0JUEr0IwmSMleEUoDNgQfksMkektFJDllyhw3Ezk1JjkCzR1HhEeig7EfAT0PRNIJksB-qmVrQEvQImwCMdSVyp9TmCQrYoEg6R4ZVKEsI8Z8SK7TxsI1kgpgyeivj8DI4Sd2u26u0UYmIHBHAczB-tXzxl5P-xRfh2fwbHyt74sYjiNqPFrWSVbtxCuo8zUfjekwXiiK6ahhfqQBTzDg9nkbcCdzpm9ubW4UOzs7-KxQisMzzkwgJe7jmDHtpcXHzYoBJti6WTHgdQpR0KSPEj6XQjaJc2F1Hng22am9PiDyI3vg1iKrUxsj7Ad_Bk1nBLtV1t0Ym86uXHDO23XorKkHlYvO1O7TS865seykl537_b3vv37u05Ay-PS6t_e-9-5L7-DVYO_HYP-w__lN_-Bl_9vbweHH_tcPV5zVNFlpLbj2chV3y4dliSt4oHPhd0ruR1mQd3KYp4qCC551pM7yslLQbxEW0ssrlUG88bKOCoswr3KYI1WaX3Wmu8-65TVnVkUSVwUiwPShfhVqvxRRqHURwvjvS--6c9f2dd0Onlvrxzx04zRMN52zzc__ljO9_fxFeRsWBdv5HevY38AZtpA
linkProvider EBSCOhost
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E6%94%B9%E8%BF%9BYOLOX%E7%9A%84%E5%94%90%E5%8D%A1%E5%A3%81%E7%94%BB%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B%E7%AE%97%E6%B3%95&rft.jtitle=%E8%AE%A1%E7%AE%97%E6%9C%BA%E5%B7%A5%E7%A8%8B%E4%B8%8E%E5%BA%94%E7%94%A8&rft.au=%E6%9D%8E%E6%B4%AA%E8%BF%90&rft.au=%E5%BC%A0%E6%95%88%E5%A8%9F&rft.au=%E8%B5%B5%E6%B4%8B&rft.au=%E5%BD%AD%E6%98%A5%E7%87%95&rft.date=2024-09-15&rft.pub=%E7%9C%81%E9%83%A8%E5%85%B1%E5%BB%BA%E8%97%8F%E8%AF%AD%E6%99%BA%E8%83%BD%E4%BF%A1%E6%81%AF%E5%A4%84%E7%90%86%E5%8F%8A%E5%BA%94%E7%94%A8%E5%9B%BD%E5%AE%B6%E9%87%8D%E7%82%B9%E5%AE%9E%E9%AA%8C%E5%AE%A4%2C%E8%A5%BF%E5%AE%81+810016%25%E5%90%88%E8%82%A5%E5%B7%A5%E4%B8%9A%E5%A4%A7%E5%AD%A6%E8%AE%A1%E7%AE%97%E6%9C%BA%E4%B8%8E%E4%BF%A1%E6%81%AF%E5%AD%A6%E9%99%A2%2C%E5%90%88%E8%82%A5+230002&rft.issn=1002-8331&rft.volume=60&rft.issue=18&rft.spage=248&rft.epage=255&rft_id=info:doi/10.3778%2Fj.issn.1002-8331.2306-0219&rft.externalDocID=jsjgcyyy202418023
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fjsjgcyyy%2Fjsjgcyyy.jpg