大模型赋能智能摄影测量:现状、挑战与前景

P237; 大模型从深度学习和迁移学习技术发展而来,依靠大量的训练数据和庞大的参数容量产生规模效应,从而激发了模型的涌现能力,在众多下游任务中展现了强大的泛化性和适应性.以ChatGPT、SAM为代表的大模型标志着通用人工智能时代的到来,为地球空间信息处理的自动化与智能化提供了新的理论与技术.为了进一步探索大模型赋能泛摄影测量领域的方法与途径,本文回顾了摄影测量领域的基本问题和任务内涵,总结了深度学习方法在摄影测量智能处理中的研究成果,分析了面向特定任务的监督预训练方法的优势与局限;阐述了通用人工智能大模型的特点及研究进展,关注大模型在基础视觉任务中的场景泛化性以及三维表征方面的潜力;从训练数...

Full description

Saved in:
Bibliographic Details
Published in测绘学报 Vol. 53; no. 10; pp. 1955 - 1966
Main Authors 王密, 程昫, 潘俊, 皮英冬, 肖晶
Format Journal Article
LanguageChinese
Published 武汉大学测绘遥感信息工程国家重点实验室,湖北武汉 430079%武汉大学计算机学院,湖北武汉 430072 26.11.2024
Subjects
智能摄影测量
多模态
deep learning
深度学习
大模型
intelligent photogrammetry
multi-modal
large models
Online AccessGet full text
ISSN1001-1595
DOI10.11947/j.AGCS.2024.20240068

Cover

Abstract P237; 大模型从深度学习和迁移学习技术发展而来,依靠大量的训练数据和庞大的参数容量产生规模效应,从而激发了模型的涌现能力,在众多下游任务中展现了强大的泛化性和适应性.以ChatGPT、SAM为代表的大模型标志着通用人工智能时代的到来,为地球空间信息处理的自动化与智能化提供了新的理论与技术.为了进一步探索大模型赋能泛摄影测量领域的方法与途径,本文回顾了摄影测量领域的基本问题和任务内涵,总结了深度学习方法在摄影测量智能处理中的研究成果,分析了面向特定任务的监督预训练方法的优势与局限;阐述了通用人工智能大模型的特点及研究进展,关注大模型在基础视觉任务中的场景泛化性以及三维表征方面的潜力;从训练数据、模型微调策略和异构多模态数据融合处理3个方面,探讨了大模型技术在摄影测量领域当前面临的挑战与发展趋势.
AbstractList P237; 大模型从深度学习和迁移学习技术发展而来,依靠大量的训练数据和庞大的参数容量产生规模效应,从而激发了模型的涌现能力,在众多下游任务中展现了强大的泛化性和适应性.以ChatGPT、SAM为代表的大模型标志着通用人工智能时代的到来,为地球空间信息处理的自动化与智能化提供了新的理论与技术.为了进一步探索大模型赋能泛摄影测量领域的方法与途径,本文回顾了摄影测量领域的基本问题和任务内涵,总结了深度学习方法在摄影测量智能处理中的研究成果,分析了面向特定任务的监督预训练方法的优势与局限;阐述了通用人工智能大模型的特点及研究进展,关注大模型在基础视觉任务中的场景泛化性以及三维表征方面的潜力;从训练数据、模型微调策略和异构多模态数据融合处理3个方面,探讨了大模型技术在摄影测量领域当前面临的挑战与发展趋势.
Abstract_FL Developed from deep learning and transfer learning techniques,large models leverage vast training datasets and im-mense parameter capacities to create scale effects,thus inspiring the model's emergent capabilities and demonstrating strong generalization and adaptability in numerous downstream tasks.Large models,represented by ChatGPT and SAM,signify the arrival of the era of general artificial intelligence,providing new theories and techniques for the automation and intelligence of Earth's spatial information processing.To further explore the methods and pathways for large models to empower the field of photogrammetry,this paper reviews the basic problems and mission tasks in the field of photogrammetry,summarizes the re-search achievements of deep learning methods in intelligent photogrammetric processing,analyzes the advantages and limita-tions of supervised pre-training methods aimed at specific tasks;Besides,we elaborates on the characteristics and research pro-gress of general artificial intelligence large models,focusing on the generalizability of large models in basic visual tasks and the potential in three-dimensional representation;Finally,this paper explores the current challenges and future trends of large model technologies in the field of photogrammetry,from the perspectives of training data,model fine-tuning strategies,and heterogeneous multi-modal data fusion strategies.
Author 皮英冬
王密
程昫
潘俊
肖晶
AuthorAffiliation 武汉大学测绘遥感信息工程国家重点实验室,湖北武汉 430079%武汉大学计算机学院,湖北武汉 430072
AuthorAffiliation_xml – name: 武汉大学测绘遥感信息工程国家重点实验室,湖北武汉 430079%武汉大学计算机学院,湖北武汉 430072
Author_FL PAN Jun
PI Yingdong
WANG Mi
CHENG Xu
XIAO Jing
Author_FL_xml – sequence: 1
  fullname: WANG Mi
– sequence: 2
  fullname: CHENG Xu
– sequence: 3
  fullname: PAN Jun
– sequence: 4
  fullname: PI Yingdong
– sequence: 5
  fullname: XIAO Jing
Author_xml – sequence: 1
  fullname: 王密
– sequence: 2
  fullname: 程昫
– sequence: 3
  fullname: 潘俊
– sequence: 4
  fullname: 皮英冬
– sequence: 5
  fullname: 肖晶
BookMark eNrjYmDJy89LZWCQNTTQMzS0NDHXz9JzdHcO1jMyMDIBEwYGZhYsDJyGBgaGuoamlqYcDLzFxZlJBgamJsbmpsaWnAxWT5csf7Zi4dN53S-2dr9o3vts5i4QObHl6d6Nz7Z2v2zvt3ret-F517bHDY3PeiY-65jxZEff087eZzPX8zCwpiXmFKfyQmluhlA31xBnD10ff3dPZ0cf3WKgvQa6KabJhklm5qkpxibJKaaJySaJqYlpyYmmFuaJyYnJBolmRmaGiUnm5mkmRpbmFompBpZmacZmRskpRpZAEQtLY24GVYi55Yl5aYl56fFZ-aVFeUAb45MzKpJA3gT5z8AYAFThXrE
ClassificationCodes P237
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 10.11947/j.AGCS.2024.20240068
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 Astronomy & Astrophysics
DocumentTitle_FL Large models enabling intelligent photogrammetry:status,challenges and prospects
EndPage 1966
ExternalDocumentID chxb202410010
GroupedDBID -01
2B.
4A8
5VS
5XA
5XB
7X2
92E
92I
93N
ABJNI
ACGFS
AEUYN
AFKRA
ALMA_UNASSIGNED_HOLDINGS
ATCPS
BBNVY
BENPR
BHPHI
BKSAR
CCEZO
CCPQU
CCVFK
CW9
HCIFZ
IPNFZ
M0K
M7P
OK1
P2P
PATMY
PCBAR
PHGZM
PHGZT
PIMPY
PMFND
PSX
PYCSY
RIG
TCJ
TGP
U1G
U5K
ID FETCH-LOGICAL-s1000-d5c1b67ed34cd5ac4aeafca587acac0a6261ab77f42978ae096f362cd29429893
ISSN 1001-1595
IngestDate Thu May 29 04:11:08 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 10
Keywords 智能摄影测量
多模态
deep learning
深度学习
大模型
intelligent photogrammetry
multi-modal
large models
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1000-d5c1b67ed34cd5ac4aeafca587acac0a6261ab77f42978ae096f362cd29429893
PageCount 12
ParticipantIDs wanfang_journals_chxb202410010
PublicationCentury 2000
PublicationDate 2024-11-26
PublicationDateYYYYMMDD 2024-11-26
PublicationDate_xml – month: 11
  year: 2024
  text: 2024-11-26
  day: 26
PublicationDecade 2020
PublicationTitle 测绘学报
PublicationTitle_FL Acta Geodaetica et Cartographica Sinica
PublicationYear 2024
Publisher 武汉大学测绘遥感信息工程国家重点实验室,湖北武汉 430079%武汉大学计算机学院,湖北武汉 430072
Publisher_xml – name: 武汉大学测绘遥感信息工程国家重点实验室,湖北武汉 430079%武汉大学计算机学院,湖北武汉 430072
SSID ssib005437539
ssib038074662
ssib051373695
ssib002263888
ssib000862384
ssj0058465
Score 2.4320838
Snippet P237;...
SourceID wanfang
SourceType Aggregation Database
StartPage 1955
Title 大模型赋能智能摄影测量:现状、挑战与前景
URI https://d.wanfangdata.com.cn/periodical/chxb202410010
Volume 53
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LaxRBEB5ivHgRn8RX2IPlRTbuzPT0I7eezaxBURATyC30vMzFDbgJaE6Kgo9oJDdzEQRBb-ohIkJ-je4m_guremZ3Jxow8dLb24-ar-qb7a6e7epxnIvK-CJDt5gillWdJcyvx1me1nOGsxFPc-P6FJx84yafnmXX5oK5kVGvsmtpeSmeSFb2jCv5H1axDHmlKNkDMDsQigWYR34xRYYx3RfHEAWgGWgBEQctQbtUoiKQIUQSwqDMSB_CKWqjFIR6d4kLklEv_Bq6VFL2UiAFyBZCgQgzEYQNm9EQcoh82iEhbXvZJCGUkaAkRAxCSe1RpkQh_evqXRsIKxcSEIa2I-oyBZpbURp00L8XyutTW2zSAsmrNag21XASocNhDSeNSjzYR1f7KBQfWTOEVmkEgvZrVp-AeIxCAYswe3vPWhP38WEn1G1o_Qr0P7VSZCYdWK0YqFYJSBcmc0khsr6wbQbqIIuhZSggpGTxgo8pawwPQlVWIdlYpTXRUJQgJK9pkShQ3CqHDIm_8V9mPrpuCrxgf7pJK921KKNSomraG2rQRlmqvQMhqDx4pqO66uj6BtWZszjmuT9CNCrzoKuKw5dLnwqHeb73fK2YsBO2vtq8PUHk2oQCl4YOymDbaLJwP6ZqAtM45Bz2hLBbM67fqi4p0KGXVZcVZ5jKkXwB83GFPnDh6X0LjA-PzAxcX_hcDZbQ5J8HdsdEqX8ZBUjAr-wF2wb_tXPTvlPxU2eOOUfLBWZNF6PFcWdkZeGEM6Y79JfX4t0HtUs1my-eaHZOOpPd9x96H991367ubK7uPN7qbXyndP1Jd-tLb3P119PXk9trn7dffP3x8FHv5Xrv2Zuf39a6z1_1Nj6dcmZb0Uxzul6-UKXeob_x6mmQuDEXWeqzJA1Mwkxm8sQEUpjEJA3DPe6aWIgcnVQhTdZQPEcHN0k9xehNDf5pZ7S92M7GnJqIWZp6rmtMaliKHzLluTF-ljZUbNz0jDNemmG-HDA787voO_uvBuecI8Mf-3lndOnecnYBFwBL8bhl_DeaALqt
linkProvider Colorado Alliance of Research Libraries
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=%E5%A4%A7%E6%A8%A1%E5%9E%8B%E8%B5%8B%E8%83%BD%E6%99%BA%E8%83%BD%E6%91%84%E5%BD%B1%E6%B5%8B%E9%87%8F%3A%E7%8E%B0%E7%8A%B6%E3%80%81%E6%8C%91%E6%88%98%E4%B8%8E%E5%89%8D%E6%99%AF&rft.jtitle=%E6%B5%8B%E7%BB%98%E5%AD%A6%E6%8A%A5&rft.au=%E7%8E%8B%E5%AF%86&rft.au=%E7%A8%8B%E6%98%AB&rft.au=%E6%BD%98%E4%BF%8A&rft.au=%E7%9A%AE%E8%8B%B1%E5%86%AC&rft.date=2024-11-26&rft.pub=%E6%AD%A6%E6%B1%89%E5%A4%A7%E5%AD%A6%E6%B5%8B%E7%BB%98%E9%81%A5%E6%84%9F%E4%BF%A1%E6%81%AF%E5%B7%A5%E7%A8%8B%E5%9B%BD%E5%AE%B6%E9%87%8D%E7%82%B9%E5%AE%9E%E9%AA%8C%E5%AE%A4%2C%E6%B9%96%E5%8C%97%E6%AD%A6%E6%B1%89+430079%25%E6%AD%A6%E6%B1%89%E5%A4%A7%E5%AD%A6%E8%AE%A1%E7%AE%97%E6%9C%BA%E5%AD%A6%E9%99%A2%2C%E6%B9%96%E5%8C%97%E6%AD%A6%E6%B1%89+430072&rft.issn=1001-1595&rft.volume=53&rft.issue=10&rft.spage=1955&rft.epage=1966&rft_id=info:doi/10.11947%2Fj.AGCS.2024.20240068&rft.externalDocID=chxb202410010
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fchxb%2Fchxb.jpg