“问题地图”智能检测发展现状与关键技术

doi:10.13474/j.cnki.11-2246.2023.0304

摘要/Abstract

摘要： 为在保护国家领土主权和地理信息安全的前提下,促进测绘地理信息行业的发展,推进“问题地图”智能检测的研究进展,本文综述了“问题地图”检测的发展现状,分析了“问题地图”智能检测的痛点问题,提出通过地理空间大数据挖掘技术获取训练样本,构建统一的地图审查模型和计算模式等关键技术。本文对“问题地图”智能检测的进展有积极的借鉴和促进作用。

关键词: 智能化测绘, 深度学习, 问题地图, 卷积神经网络, 先验知识库

Abstract: In order to promote the development of the surveying and mapping geographic information industry and the research progress of intelligent check for problem map under the premise of protecting national territorial sovereignty and geographic information security, this paper summarizes the development status of problem mapcheck and analyzes the pain points of problem map intelligent check.This study proposes key technologies such as obtaining training samples through geospatial big data mining technology, which includes a unified map review and unified calculation model. This paper is able to have positive references and promotion effect on the progress of intelligent check of problem map.

Key words: intelligent surveying and mapping, deep learning, problem map, convolution neural network, the priori knowledge base

中图分类号:

梁宇, 左栋. “问题地图”智能检测发展现状与关键技术[J]. 测绘通报, 2023, 0(10): 111-116.

LIANG Yu, ZUO Dong. The development status and key technologies of intelligent check for “problem maps”[J]. Bulletin of Surveying and Mapping, 2023, 0(10): 111-116.

参考文献

[1] 王家耀,成毅. 论地图学的属性和地图的价值[J]. 测绘学报,2015,44(3): 237-241.
[2] 张广运,张荣庭,戴琼海,等. 测绘地理信息与人工智能2.0融合发展的方向[J]. 测绘学报,2021,50(8): 1096-1108.
[3] 孟立秋. 自主导航地图的昨天、今天和明天[J]. 测绘学报,2022,51(6): 1029-1039.
[4] 李德仁,洪勇,王密,等. 测绘遥感能为智能驾驶做什么？[J]. 测绘学报,2021,50(11): 1421-1431.
[5] 朱庆,张利国,丁雨淋,等. 从实景三维建模到数字孪生建模[J]. 测绘学报,2022,51(6): 1040-1049.
[6] KIM C,CHO S,SUNWOO M,et al. Updating point cloud layer of high definition (HD) map based on crowd-sourcing of multiple vehicles installed LiDAR[J]. IEEE Access,2021,9: 8028-8046.
[7] KIM K,CHO S,CHUNG W. HD map update for autonomous driving with crowdsourced data[J]. IEEE Robotics and Automation Letters,2021,6(2): 1895-1901.
[8] 张文晖,白敬辉,黄龙,等. 把好地图审核关维护国家主权和安全[J]. 地图研究,2021(1): 13-20.
[9] 刘经南,詹骄,郭迟,等. 智能高精地图数据逻辑结构与关键技术[J]. 测绘学报,2019,48(8): 939-953.
[10] 朱长青,任娜,徐鼎捷. 地理信息安全技术研究进展与展望[J]. 测绘学报,2022,51(6): 1017-1028.
[11] 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.
[12] 王家耀. 人工智能开启地图学的新时代[J]. 地图研究,2021(1): 1-9.
[13] 张继贤,顾海燕,杨懿,等. 自然资源要素智能解译研究进展与方向[J]. 测绘学报,2022,51(7): 1606-1617.
[14] 刘瑜,郭浩,李海峰,等. 从地理规律到地理空间人工智能[J]. 测绘学报,2022,51(6): 1062-1069.
[15] 梁宇,陈会仙,石磊,等. 地图学视角下的公开地图表示要点[J]. 北京测绘,2021,35(8): 991-996.
[16] 陈会仙,白敬辉. 浅析我国公开地图上国界线附近地名注记的表示方法[J]. 测绘通报,2019(2): 137-140.
[17] 狄琳. 导航电子地图中重要线状要素表示方法初探[J]. 测绘通报,2013(8): 87-90.
[18] 周昕薇,韩权卫,褚雪梅,等. 公开地图上重要地理信息的表示方法研究[J]. 测绘通报,2018(7): 67-70.
[19] 门计林,刘越岩,张斌,等. 多结构卷积神经网络特征级联的高分影像土地利用分类[J]. 武汉大学学报(信息科学版),2019,44(12): 1841-1848.
[20] 张海明,王明常,陈学业,等. 领域知识优化深度置信网络的遥感变化检测[J]. 武汉大学学报(信息科学版),2022,47(5): 762-768.
[21] 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.
[22] 杜凯旋,王亮,王勇,等. 主动学习和卷积神经网络的地图图片识别方法[J]. 测绘科学,2020,45(7): 139-147.
[23] YANG Renfei,LUO Fang,REN Fu,et al. Identifying urban wetlands through remote sensing scene classification using deep learning: a case study of Shenzhen,China[J]. ISPRS International Journal of Geo-Information,2022,11(2): 131.
[24] LIU Shengjie,SHI Qian. Local climate zone mapping as remote sensing scene classification using deep learning: a case study of metropolitan China[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2020,164: 229-242.
[25] TUIA D,PACIFICI F,KANEVSKI M,et al. Classification of very high spatial resolution imagery using mathematical morphology and support vector machines[J]. IEEE Transactions on Geoscience and Remote Sensing,2009,47(11): 3866-3879.
[26] 黄龙,吴佳桐. 图像识别在互联网“问题地图”监控中的应用[J]. 测绘通报,2020(6): 145-148.
[27] MIAO Qiguang,LIU Tiange,SONG Jianfeng,et al. Guided superpixel method for topographic map processing[J]. IEEE Transactions on Geoscience and Remote Sensing,2016,54(11): 6265-6279.
[28] CHIANG Yaoyi,LEYK S,HONARVAR N N,et al.Assessing the impact of graphical quality on automatic text recognition in digital maps[J]. Computers & Geosciences,2016,93: 21-35.
[29] SHEN Yilang,AI Tinghua,LI Jingzhong,et al. A tile-map-based method for the typification of artificial polygonal water areas considering the legibility[J]. Computers & Geosciences,2020,143: 104552.
[30] SHEN Yilang,AI Tinghua,LI Jingzhong,et al. A progressive method for the collapse of river representation considering geographical characteristics[J]. International Journal of Digital Earth,2020,13(12): 1366-1390.
[31] 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.
[32] CARDOSO A B,MARTINS B,ESTIMA J. A novel deep learning approach using contextual embeddings for toponym resolution[J]. ISPRS International Journal of Geo-Information,2021,11(1): 28.
[33] FIZE J,MONCLA L,MARTINS B. Deep learning for toponym resolution: geocoding based on pairs of toponyms[J]. ISPRS International Journal of Geo-Information,2021,10(12): 818.
[34] 马超,孙群,陈换新,等. 志愿者地理信息中天桥的自动识别方法[J]. 测绘学报,2017,46(2): 246-252.
[35] 何海威,钱海忠,谢丽敏,等. 立交桥识别的CNN卷积神经网络法[J]. 测绘学报,2018,47(3): 385-395.
[36] ARAVENA PELIZARI P,GEIß C,AGUIRRE P,et al. Automated building characterization for seismic risk assessment using street-level imagery and deep learning[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2021,180: 370-386.
[37] TERRONE M,PIANA P,PALIAGA G,et al. Coupling historical maps and LiDAR data to identify man-made landforms in urban areas[J]. ISPRS International Journal of Geo-Information,2021,10(5): 349.
[38] HE Xianjin,ZHANG Xinchang,XIN Qinchuan. Recognition of building group patterns in topographic maps based on graph partitioning and random forest[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2018,136: 26-40.
[39] LIU Tiange,XU Pengfei,ZHANG Shihui. A review of recent advances in scanned topographic map processing[J]. Neurocomputing,2019,328: 75-87.
[40] UHL J H,LEYK S,CHIANG Yaoyi,et al. Automated extraction of human settlement patterns from historical topographic map series using weakly supervised convolutional neural networks[J]. IEEE Access,2019,8: 6978-6996.
[41] 单巍,王江涛,方振国,等. 基于深度学习的可见光图像中行人检测方法[J]. 武汉大学学报(理学版),2021,67(2): 127-135.
[42] 范荣双,陈洋,徐启恒,等. 基于深度学习的高分辨率遥感影像建筑物提取方法[J]. 测绘学报,2019,48(1): 34-41.
[43] 崔卫红,熊宝玉,张丽瑶. 多尺度全卷积神经网络建筑物提取[J]. 测绘学报,2019,48(5): 597-608.
[44] 余东行,郭海涛,张保明,等. 级联卷积神经网络的遥感影像飞机目标检测[J]. 测绘学报,2019,48(8): 1046-1058.
[45] 杨必胜,陈驰,董震. 面向智能化测绘的城市地物三维提取[J]. 测绘学报,2022,51(7): 1476-1484.
[46] 方莉娜,王爽,赵志远,等. 车载激光点云中交通标线自动分类与矢量化[J]. 测绘学报,2021,50(9): 1251-1265.
[47] 姚连璧,秦长才,张邵华,等. 车载激光点云的道路标线提取及语义关联[J]. 测绘学报,2020,49(4): 480-488.
[48] 李永强,李鹏鹏,董亚涵,等. 车载LiDAR点云数据中杆状地物自动提取与分类[J]. 测绘学报,2020,49(6): 724-735.
[49] 张丽. 智能化全息测绘成果质量检查方法研究[J]. 测绘通报,2021(S2): 260-263.
[50] 韩文立,张继贤,陈海鹏,等. 新型基础测绘质检技术探讨[J]. 测绘通报,2022(7): 148-153.
[51] 陈军,刘万增,武昊,等. 智能化测绘的基本问题与发展方向[J]. 测绘学报,2021,50(8): 995-1005.
[52] 陈军,刘万增,任加新. 地图审核的智能化问题与发展方向[J]. 地图研究,2022(1): 16-21.
[53] 梁宇,张文晖,邹辉东,等. 地图技术审查知识库建设和应用[J]. 地图研究,2022(1): 48-58.
[54] 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.
[55] 左栋,张雨心. 国内互联网地图POI存在的涉密问题及其解决办法[J]. 测绘通报,2016(9): 108-111.
[56] LI Huali,LIU Jun,ZHOU Xiran. Intelligent map reader: a framework for topographic map understanding with deep learning and gazetteer[J]. IEEE Access,2018,6: 25363-25376.
[57] WANG Zhou,BOVIK A C,SHEIKH H R,et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing,2004,13(4): 600-612.
[58] 刘纪平,王勇,胡燕祝,等. 互联网泛在地理信息感知融合技术综述[J]. 测绘学报,2022,51(7): 1618-1628.
[59] 董卫华,廖华,詹智成,等. 2008年以来地图学眼动与视觉认知研究新进展[J]. 地理学报,2019,74(3): 599-614.
[60] 万刚,武易天. 地图空间认知的数学基础[J]. 测绘学报,2021,50(6): 726-738.
[61] 张雨心,左栋. 高精度导航电子地图的国家安全防控要点探究[J]. 测绘通报,2020(10): 148-151.
[62] 周昕薇,狄琳,白敬辉,等. 浅析动画效果地图的公开表示[J]. 测绘通报,2020(2): 118-120.
[63] 邓国臣,褚雪梅. 学术论文中避免出现“问题地图”的建议[J]. 科技与出版,2018(1): 50-55.
[64] 白敬辉,韩权卫,陈会仙,等. 地图中国界线与经纬线关系表示方法探究[J]. 测绘通报,2020(4): 143-146.
[65] 梁宇,陈会仙,吴佳桐. 公开世界地图表示要点探究[J]. 测绘科学,2021,46(11): 153-158.