
浏览全部资源
扫码关注微信
1.云南大学国际河流与生态安全研究院,云南 昆明,650500
2.云南大学地球科学学院,云南 昆明,650500
3.云南省中老孟缅自然资源遥感监测国际联合实验室,云南 昆明,650500
4.云南大学生态与环境学院,云南 昆明,650500
5.武汉大学资源与环境科学学院,湖北 武汉,430079
Received:20 July 2025,
Published:05 March 2026
移动端阅览
王湛初,赵飞,张雅欣,等.结合YOLOv8与句法模型的统计专题地图信息提取方法[J].武汉大学学报(信息科学版),2026,51(3):490-502.
WANG Zhanchu,ZHAO Fei,ZHANG Yaxin,et al.An Information Extraction Method for Statistical Thematic Maps Combining YOLOv8 and Syntactic Model[J].Geomatics and Information Science of Wuhan University,2026,51(3):490-502.
王湛初,赵飞,张雅欣,等.结合YOLOv8与句法模型的统计专题地图信息提取方法[J].武汉大学学报(信息科学版),2026,51(3):490-502. DOI:10.13203/j.whugis20250111
WANG Zhanchu,ZHAO Fei,ZHANG Yaxin,et al.An Information Extraction Method for Statistical Thematic Maps Combining YOLOv8 and Syntactic Model[J].Geomatics and Information Science of Wuhan University,2026,51(3):490-502. DOI:10.13203/j.whugis20250111
人工智能时代,从海量专题地图中快速智能地提取地图信息成为地图学研究的重要目标。首先,从符号句法的角度分析统计地图,收集133张泛源统计专题地图,标注3 512个图面元素作为训练集;其次,根据地图结构层级,分两次使用改进的YOLOv8模型,先后对地图图面元素和专题符号中的图元进行提取和分类;然后,利用多种特征识别手段提取图元中的视觉变量;最后,基于专题地图句法模型生成结构化描述信息,并转换为由专题、位置、类别、数值构成的元组。实验结果表明,改进的YOLOv8模型在地图元素及图元提取中效果极佳,均值平均精度分别达到92.6%和99.4%。此外,梳理了统计地图结构与信息表达逻辑,依此提取并解读地图信息,将其整理成元组结构,便于后续构建知识图谱等应用。
Objectives
2
With the advancement of artificial intelligence
automatic extraction and interpretation of map information from large-scale statistical thematic maps have become significant research topics in cartography. The aim to develop a method that combines the YOLOv8 model with a syntactic model to extract structured information from statistical thematic maps. The primary objectives are to enhance extraction accuracy
decode semantic meanings based on cartographic syntax
and generate tuple-structured data for applications like knowledge graph construction and intelligent cartographic recommendations.
Methods
2
We employed an improved YOLOv8 model to extract and classify various map elements. First
a dataset of 133 statistical thematic maps was compiled from diverse sources
including online atlases and scanned documents
with 3 512 map elements annotated as the training set. Elements were categorized into six types: thematic symbols
map title
legend
scale
other text
and other charts. To enhance the performance of YOLOv8 model for this specific application
the model was modified by incorporating residual hybrid attention groups (RHAG) in the Backbone and replacing the upsampling part with DySample upsampler. Subsequently
the model detected and classified map surface elements; subsequently
thematic symbols were processed to extract geometric primitives through a second YOLOv8 application. Pattern recognition techniques
such as Hough transform
were then used to extract visual variables
including construction attributes and color attributes. Finally
based on a syntactic model
structured descriptions of the map content were generated
which involved analyzing the relationships between graphical elements and reconstructing the hierarchical and syntactic structure of the symbols.
Results
2
The improved YOLOv8 model demonstrates remarkable effectiveness. In map element extraction
it achieves a mean average precision (mAP)50 of 92.6% and mAP50:95 of 73.8%
with precision rates up to 99.5% for categories like scale and other text. For geometric primitive extraction
the model achieved an mAP50 of 99.4% and mAP50:95 of 90.3%
accurately identifying primitives even in complex symbols. Ablation studies confirmes the contributions of RHAG and DySample
showing improvements over the baseline model. The method successfully captures the syntactic structure of statistical thematic maps
enabling the extraction of semantic information such as thematic categories
spatial relationships
and quantitative values.
Conclusions
2
The combination of object detection and syntactic modeling can efficiently extract structured information from statistical thematic maps. This approach provides an in-depth interpretation of map content and highlights its practical utility in cartographic analysis. Future research will continue to explore and optimize this method for broader applications.
王家耀 . 地图科学技术: 由数字化到智能化 [J]. 武汉大学学报(信息科学版) , 2022 , 47 ( 12 ): 1963 - 1977 .
WANG Jiayao . Cartography: From Digital to Intelligent [J]. Geomatics and Information Science of Wuhan University , 2022 , 47 ( 12 ): 1963 - 1977 .
王家耀 , 武芳 , 闫浩文 . 大变化时代的地图学 [J]. 测绘学报 , 2022 , 51 ( 6 ): 829 - 842 .
WANG Jiayao , WU Fang , YAN Haowen . Cartography: Its Past, Present and Future [J]. Acta Geodaetica et Cartographica Sinica , 2022 , 51 ( 6 ): 829 - 842 .
张岸 , 朱俊锴 . 新一代人工智能驱动下地图学研究的机遇与挑战 [J]. 地球信息科学学报 , 2024 , 26 ( 1 ): 35 - 45 .
ZHANG An , ZHU Junkai . Opportunities and Challenges of Cartography Research Driven by New Generation Artificial Intelligence [J]. Journal of Geo⁃Information Science , 2024 , 26 ( 1 ): 35 - 45 .
黄丽娜 , 许国光 . 中国省情综合地图集的内容图谱构建与主题表达可视分析 [J]. 武汉大学学报(信息科学版) , 2023 , 48 ( 5 ): 665 - 677 .
HUANG Li'na , XU Guoguang . Construction of Content Tupu and Visual Analysis Subject Expression for Provincial Comprehensive Atlases in China [J]. Geomatics and Information Science of Wuhan University , 2023 , 48 ( 5 ): 665 - 677 .
康力成 , 姜莉莉 . 中国省域综合地图集通用内容结构知识构建方法研究 [J/OL]. 武汉大学学报(信息科学版) , 2025 , DOI: 10.13203/j.whugis20250038.KANG Licheng http://dx.doi.org/10.13203/j.whugis20250038.KANGLicheng ,
JIANG Lili . Method of Constructing General Content Knowledge System for Provincial Comprehensive Atlas of China [J/OL]. Geomatics and Information Science of Wuhan University , 2025 , DOI: 10.13203/j.whugis20250038 http://dx.doi.org/10.13203/j.whugis20250038 .
王孟琪 , 李伯钊 , 王振立 , 等 . 一种集成知识图谱和大语言模型的智能地图制图框架 [J/OL]. 武汉大学学报(信息科学版) , 2025 , DOI: 10.13203/j.whugis20240266 http://dx.doi.org/10.13203/j.whugis20240266 .
WANG Mengqi , LI Bozhao , WANG Zhenli , et al . An Automatic Cartography Framework Integrating Knowledge Graph and Large Language Model [J/OL]. Geomatics and Information Science of Wuhan University , 2025 , DOI: 10.13203/j.whugis 20240266 http://dx.doi.org/10.13203/j.whugis20240266 .
冯玉才 , 宋恩民 . 彩色地图图象的聚色算法研究 [J]. 软件学报 , 1996 , 7 ( 8 ): 466 - 470 .
FENG Yucai , SONG Enmin . An Algorithm to Gather Colors from Image of Color Maps [J]. Journal of Software , 1996 , 7 ( 8 ): 466 - 470 .
BALLARD D H . Generalizing the Hough Transform to Detect Arbitrary Shapes [J]. Pattern Recognition , 1981 , 13 ( 2 ): 111 - 122 .
田宽 . 彩色地形图中的点状符号识别算法研究 [D]. 西安 : 西安电子科技大学 , 2017 .
TIAN Kuan . Research on Point Symbols Recognition in Color Topographic Map [D]. Xi'an : Xidian University , 2017 .
MIAO Q G , XU P F , LIU T G , et al . Linear Feature Separation from Topographic Maps Using Energy Density and the Shear Transform [J]. IEEE Transactions on Image Processing , 2013 , 22 ( 4 ): 1548 - 1558 .
钟英铭 . 基于深度学习的面向制图综合的建筑物群组模式识别研究 [D]. 武汉 : 华中师范大学 , 2021 .
ZHONG Yingming . Research on Building Group Pattern Recognition for Cartographic Generalization Based on Deep Learning [D]. Wuhan : Central China Normal University , 2021 .
白又达 , 刘纪平 , 黄龙 , 等 . 面向地图图片识别的两种卷积神经网络分析 [J]. 测绘科学 , 2021 , 46 ( 11 ): 126 - 134 .
BAI Youda , LIU Jiping , HUANG Long , et al . Analysis of Two Convolutional Neural Networks for Map Image Recognition [J]. Science of Surveying and Mapping , 2021 , 46 ( 11 ): 126 - 134 .
崔腾腾 , 刘纪平 , 罗安 . 一种卷积神经网络的地图图片智能识别方法 [J]. 测绘科学 , 2019 , 44 ( 1 ): 118 - 123 .
CUI Tengteng , LIU Jiping , LUO An . Intelligent Identification Method of Network Map Images Based on Convolutional Neural Network [J]. Science of Surveying and Mapping , 2019 , 44 ( 1 ): 118 - 123 .
任加新 , 刘万增 , 李志林 , 等 . 利用卷积神经网络进行“问题地图”智能检测 [J]. 武汉大学学报(信息科学版) , 2021 , 46 ( 4 ): 570 - 577 .
REN Jiaxin , LIU Wanzeng , LI Zhilin , et al . Intelligent Detection of “Problematic Map” Using Convolutional Neural Network [J]. Geomatics and Information Science of Wuhan University , 2021 , 46 ( 4 ): 570 - 577 .
WU S D , SCHINDLER K , HEITZLER M , et al . Domain Adaptation in Segmenting Historical Maps: A Weakly Supervised Approach Through Spatial Co-Occurrence [J]. ISPRS Journal of Photogrammetry and Remote Sensing , 2023 , 197 : 199 - 211 .
任福 , 侯宛玥 . 面向机器阅读的地图名称注记类别识别方法 [J]. 武汉大学学报(信息科学版) , 2020 , 45 ( 2 ): 273 - 280 .
REN Fu , HOU Wanyue . Identification Method of Map Name Annotation Category for Machine Reading [J]. Geomatics and Information Science of Wuhan University , 2020 , 45 ( 2 ): 273 - 280 .
李想 . 基于深度学习的地图点注记识别及配置研究 [D]. 郑州 : 郑州大学 , 2022 .
LI Xiang . Research on Map Point Annotation Recognition and Configuration Based On Deep Learning [D]. Zhengzhou : Zhengzhou University , 2022 .]
周翰林 . 基于深度学习的GIS图例符号识别系统研建 [D]. 北京 : 北京林业大学 , 2018 .
ZHOU Hanlin . Study on GIS Similar Legend Recognition System Based on Deep Learing [D]. Beijing : Beijing Forestry University , 2018 .
HU Y J , GUI Z P , WANG J M , et al . Enriching the Metadata of Map Images: A Deep Learning Approach with GIS-Based Data Augmentation [J]. International Journal of Geographical Information Science , 2022 , 36 ( 4 ): 799 - 821 .
CHANG S , PALZER D , LI J , et al . MapQA: A Aataset for Question Answering on Choropleth Maps [PP/OL].[ 2025-06-11 ]. https://arxiv.org/abs/2211.08545 https://arxiv.org/abs/2211.08545 .
赵飞 , 杜清运 , 任福 , 等 . 专题地图符号的句法结构及其自动构建机制 [J]. 测绘学报 , 2014 , 43 ( 6 ): 653 - 660 .
ZHAO Fei , DU Qingyun , REN Fu , et al . Syntactic Characteristics and Smart Construction Mechanism of Thematic Map Symbol [J]. Acta Geodaetica et Cartographica Sinica , 2014 , 43 ( 6 ): 653 - 660 .
田江鹏 , 游雄 , 贾奋励 , 等 . 移动地图制图的句法模型 [J]. 测绘学报 , 2016 , 45 ( 11 ): 1352 - 1360 .
TIAN Jiangpeng , YOU Xiong , JIA Fenli , et al . The Syntax Model of Mobile Maps Generation [J]. Acta Geodaetica et Cartographica Sinica , 2016 , 45 ( 11 ): 1352 - 1360 .
闫晓婧 . 微地图符号智能化生成方法 [D]. 兰州 : 兰州交通大学 , 2023 .
YAN Xiaojing . Approach to Intelligently Generating We-Map Symbols [D]. Lanzhou : Lanzhou Jiatong University , 2023 .
王海鹰 . 后现代环境哲学视角下微地图的存在及特征 [D]. 兰州 : 兰州交通大学 , 2023 .
WANG Haiying . The Ontology and Characteristics of WeMaps from the Perspective of Postmodern Environmental Philosophy [D]. Lanzhou : Lanzhou Jiaotong University .
SCHNABEL O , HURNI L . Primitive-Based Construction Theory for Diagrams in Thematic Maps [J]. The Cartographic Journal , 2009 , 46 ( 2 ): 136 - 145 .
吴明光 , 乔莉鸽 , 闾国年 . 从视觉神经科学的视角看地图视觉变量理论 [J]. 地理学报 , 2024 , 79 ( 9 ): 2191 - 2205 .
WU Mingguang , QIAO Lige , LÜ Guonian . Revisiting Cartographic Visual Variables from a Perspective of Visual Neuroscience [J]. Acta Geographica Sinica , 2024 , 79 ( 9 ): 2191 - 2205 .
TERVEN J , CÓRDOVA-ESPARZA D M , ROMERO-GONZÁLEZ J A . A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS [J]. Machine Learning and Knowledge Extraction , 2023 , 5 ( 4 ): 1680 - 1716 .
CHEN X Y , WANG X T , ZHOU J T , et al . Activating more Pixels in Image Super-Resolution Transformer [C]// 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , Vancouver, Canada , 2023 .
LIU W Z , LU H , FU H T , et al . Learning to Upsample by Learning to Sample [C]// 2023 IEEE/CVF International Conference on Computer Vision (ICCV) , Paris, France , 2024 .
广东省地图院 . 广东省地图集 [CM]. 北京 : 中国地图出版社 , 2020 .
Map Institute of Guangdong Province . Map Institute of Guangdong Province [CM]. Beijing : Sino Maps Press , 2020 .
广西壮族自治区测绘地理信息局 , 广西壮族自治区民族宗教事务委员会 , 广西壮族自治区国土资源厅 . 庆祝改革开放40周年暨广西壮族自治区成立60周年成就地图集 [CM]. 北京 : 中国地图出版社 , 2018 .
Surveying and Mapping Bureau of Guangxi Zhuang Autonomous Region , Ethnic and Religious Affairs Commission of Guangxi Zhuang Autonomous Region , Department of Land and Resources of Guangxi Zhuang Autonomous Region . Atlas of Achievements Celebrating the 40th Anniversary of Reform and Opening-up and the 60th Anniversary of the Founding of Guangxi Zhuang Autonomous Region [CM]. Beijing : Sino Maps Press , 2018 .
0
Views
1
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621