自然资源要素智能解译研究进展与方向

doi:10.11947/j.AGCS.2022.20220109

摘要/Abstract

摘要： 自然资源要素解译是自然资源调查监测工作中最基础、投入工作量最大、技术难度最高的工作,存在可解译类别少、要素边界不准不全、类别属性可靠性不高等诸多挑战。本文从自然资源调查监测应用场景出发,首先从要素解译到场景要素耦合的解译范式、数据驱动到知识驱动的解译方法、人工目视到人机协同的解译手段3个方面阐述了自然资源要素自动解译的研究进展;然后探讨了6个重点研究方向及其研究内容,包括场景要素耦合解译、知识驱动语义理解、人机协同智能解译、内外一体与三维环境解译、关键参数精准计算与定量反演,以及高可信质量控制与真实性验证;最后进行了总结与展望,以期为自然资源要素智能解译研究提供思路,推动解决困扰遥感影像自动解译方法在自然资源调查监测业务应用中的瓶颈问题。

关键词: 自然资源调查监测, 智能解译, 场景要素耦合解译, 语义理解, 人机协同, 内外一体解译, 参数反演, 真实性验证

Abstract: Interpretation of natural resources features is the most basic, most widely used, most involved, and most technically difficult task in survey and monitoring work. It faces many challenges such as application understanding, accurate interpretation, and fine interpretation. Starting from the application scenarios of natural resource survey and monitoring, firstly, this article elaborates its research progress from three aspects:scene-features coupling interpretation mode, semantic understanding expression cognition, and human-computer collaborative interpretation methods. Then, it discusses six key research directions and basic ideas, including scene-feature coupling interpretation, knowledge-driven semantic understanding, human-machine collaborative intelligent interpretation, indoor and outdoor integrated and 3D environment interpretation, quantitative inversion of key parameters, high-confidence quality control and authenticity verification. Finally, summaries are given. This paper aims to provide some ideas for the research on intelligent interpretation of natural resources survey and monitoring features, and promote the solution of bottlenecks that plague the application of remote sensing image automatic interpretation methods in natural resource survey and monitoring applications.

Key words: natural resources survey and monitoring, intelligent interpretation, scene-features coupling interpretation, semantic understanding, human-computer collaboration, indoor and outdoor integrated interpretation, parameter inversion, authenticity verification

中图分类号:

P208∶P96

张继贤, 顾海燕, 杨懿, 张鹤, 李海涛, 韩文立, 沈晶. 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.

ZHANG Jixian, GU Haiyan, YANG Yi, ZHANG He, LI Haitao, HAN Wenli, SHEN Jing. Research progress and trend of intelligent interpretation for natural resources features[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(7): 1606-1617.

参考文献

[1] 张继贤,李海涛,顾海燕,等.人机协同的自然资源要素智能提取方法[J].测绘学报, 2021, 50(8):1023-1032. DOI:10.11947/j.AGCS.2021.20210102. ZHANG Jixian, LI Haitao, GU Haiyan, et al. Study on man-machine collaborative intelligent extraction for natural resource features[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8):1023-1032. DOI:10.11947/j.AGCS.2021.20210102.
[2] 自然资源部.《自然资源调查监测体系构建总体方案》[EB/OL].(2020-01-17)[2020-01-20]. http://www.gov.cn:8080/zhengce/zhengceku/2020-01/18/content_5470398.htm. Ministry of Natural Resources of the People's Republic of China. Overall plan for the construction of the natural resources investigation and monitoring system[EB/OL].(2020-01-17)[2020-01-20]. http://www.gov.cn:8080/zhengce/zhengceku/2020-01/18/content_5470398.htm.
[3] 张继贤,顾海燕,杨懿,等.高分辨率遥感影像智能解译研究进展与趋势[J].遥感学报, 2021, 25(11):2198-2210. ZHANG Jixian, GU Haiyan, YANG Yi, et al. Research progress and trend of high-resolution remote sensing imagery intelligent interpretation[J]. Journal of Remote Sensing, 2021, 25(11):2198-2210.
[4] 刘巍,吴志峰,骆剑承,等.深度学习支持下的丘陵山区耕地高分辨率遥感信息分区分层提取方法[J].测绘学报, 2021, 50(1):105-116. DOI:10.11947/j.AGCS.2021.20190448. LIU Wei, WU Zhifeng, LUO Jiancheng, et al. A divided and stratified extraction method of high-resolution remote sensing information for cropland in hilly and mountainous areas based on deep learning[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(1):105-116. DOI:10.11947/j.AGCS.2021.20190448.
[5] 闾国年,俞肇元,袁林旺,等.地图学的未来是场景学吗?[J].地球信息科学学报, 2018, 20(1):1-6. LV Guonian, YU Zhaoyuan, YUAN Linwang, et al. Is the future of cartography the scenario science?[J]. Journal of Geo-Information Science, 2018, 20(1):1-6.
[6] 邓培芳,徐科杰,黄鸿.基于CNN-GCN双流网络的高分辨率遥感影像场景分类[J].遥感学报, 2021, 25(11):2270-2282. DENG Peifang, XU Kejie, HUANG Hong. CNN-GCN-based dual-stream network for scene classification of remote sensing images[J]. Journal of Remote Sensing, 2021, 25(11):2270-2282.
[7] 范鑫,胡昌苗,霍连志.耦合多源地理数据的多分辨率遥感影像场景分类方法研究[J].无线电工程, 2021, 51(12):1449-1460. FAN Xin, HU Changmiao, HUO Lianzhi. Research on multi-resolution remote sensing image scene classification method coupled with multi-source geographic data[J]. Radio Engineering, 2021, 51(12):1449-1460.
[8] 顾广华,韩晰瑛,陈春霞,等.图像场景语义分类研究进展综述[J].系统工程与电子技术, 2016, 38(4):936-948. GU Guanghua, HAN Xiying, CHEN Chunxia, et al. Survey on semantic scene classification research[J]. Systems Engineering and Electronics, 2016, 38(4):936-948.
[9] CHENG Gong, XIE Xingxing, HAN Junwei, et al. Remote sensing image scene classification meets deep learning:challenges, methods, benchmarks, and opportunities[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2020, 13:3735-3756.
[10] MA Lei, LIU Yu, ZHANG Xueliang, et al. Deep learning in remote sensing applications:a meta-analysis and review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 152:166-177.
[11] 田艳玲,张维桐,张锲石,等.图像场景分类技术综述[J].电子学报, 2019, 47(4):915-926. TIAN Yanling, ZHANG Weitong, ZHANG Qieshi, et al. Review on image scene classification technology[J]. Acta Electronica Sinica, 2019, 47(4):915-926.
[12] HINTON G E, OSINDERO S, TEH Y W. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7):1527-1554.
[13] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553):436-444.
[14] YANG Liu, TIAN Shengwei, YU Long, et al. Deep learning for extracting water body from Landsat imagery[J]. International Journal of Innovative Computing, Information and Control, 2015, 11(6):1913-1929.
[15] LUUS F P S, SALMON B P, VAN DEN BERGH F, et al. Multiview deep learning for land-use classification[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(12):2448-2452.
[16] HUANG Bo, ZHAO Bei, SONG Yimeng. Urban land-use mapping using a deep convolutional neural network with high spatial resolution multispectral remote sensing imagery[J]. Remote Sensing of Environment, 2018, 214:73-86.
[17] SU Yu, ZHONG Yanfei, ZHU Qiqi, et al. Urban scene understanding based on semantic and socioeconomic features:from high-resolution remote sensing imagery to multi-source geographic datasets[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 179:50-65.
[18] JI Shaoxiong, PAN Shirui, CAMBRIA E, et al. A survey on knowledge graphs:representation, acquisition, and applications[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(2):494-514.
[19] 王志华,杨晓梅,周成虎.面向遥感大数据的地学知识图谱构想[J].地球信息科学学报, 2021, 23(1):16-28. WANG Zhihua, YANG Xiaomei, ZHOU Chenghu. Geographic knowledge graph for remote sensing big data[J]. Journal of Geo-Information Science, 2021, 23(1):16-28.
[20] 周黎鸣,陈璐,刘金明,等.基于迁移学习的高分辨率遥感影像场景分类研究[J].河南大学学报(自然科学版), 2020, 50(4):443-450. ZHOU Liming, CHEN Lu, LIU Jinming, et al. Research on high resolution remote sensing image scene classification based on transfer learning[J]. Journal of Henan University (Natural Science), 2020, 50(4):443-450.
[21] 骆剑承,胡晓东,吴田军,等.高分遥感驱动的精准土地利用与土地覆盖变化信息智能计算模型与方法研究[J].遥感学报, 2021, 25(7):1351-1373. LUO Jiancheng, HU Xiaodong, WU Tianjun, et al. Research on intelligent calculation model and method of precision land use/cover change information driven by high-resolution remote sensing[J]. National Remote Sensing Bulletin, 2021, 25(7):1351-1373.
[22] BELOUADAH E, POPESCU A, KANELLOS I. A comprehensive study of class incremental learning algorithms for visual tasks[J]. Neural Networks, 2021, 135:38-54.
[23] SAGI O, ROKACH L. Ensemble learning:a survey[J]. WIREs Data Mining and Knowledge Discovery, 2018, 8(4):e1249.
[24] 刘大鹏,曹永锋,张伦.深度迁移主动学习研究综述[J].现代计算机, 2021(10):88-93. LIU Dapeng, CAO Yongfeng, ZHANG Lun. Review of research on deep transfer active learning[J]. Modern Computer, 2021(10):88-93.
[25] 张洪岩,周成虎,闾国年,等.试论地学信息图谱思想的内涵与传承[J].地球信息科学学报, 2020, 22(4):653-661. ZHANG Hongyan, ZHOU Chenghu, LV Guonian, et al. The connotation and inheritance of Geo-information Tupu[J]. Journal of Geo-Information Science, 2020, 22(4):653-661.
[26] 范向民,范俊君,田丰,等.人机交互与人工智能:从交替浮沉到协同共进[J].中国科学:信息科学, 2019, 49(3):361-368. FAN Xiangmin, FAN Junjun, TIAN Feng, et al. Human-computer interaction and artificial intelligence:from competition to integration[J]. Scientia Sinica (Informationis), 2019, 49(3):361-368.
[27] WANG Guoli, FAN Bin, XIANG Shiming, et al. Aggregating rich hierarchical features for scene classification in remote sensing imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 10(9):4104-4115.
[28] 单卫东.强化自然地理认知合理利用自然资源[N].中国自然资源报, 2021-01-08(3). SHAN Weidong. Strengthen the cognition of natural geography and make rational use of natural resources[N]. China Natural Resources News, 2021-01-08(3).
[29] 顾海燕,李海涛,闫利,等.地理本体驱动的遥感影像面向对象分析方法[J].武汉大学学报(信息科学版), 2018, 43(1):31-36. GU Haiyan, LI Haitao, YAN Li, et al. A geographic object-based image analysis methodology based on geo-ontology[J]. Geomatics and Information Science of Wuhan University, 2018, 43(1):31-36.
[30] 陈军,刘万增,武昊,等.基础地理知识服务的基本问题与研究方向[J].武汉大学学报(信息科学版), 2019, 44(1):38-47. CHEN Jun, LIU Wanzeng, WU Hao, et al. Basic issues and research agenda of geospatial knowledge service[J]. Geomatics and Information Science of Wuhan University, 2019, 44(1):38-47.
[31] ZHONG Yanfei, WU Siqi, ZHAO Bei. Scene semantic understanding based on the spatial context relations of multiple objects[J]. Remote Sensing, 2017, 9(10):1030.
[32] 周小程,高冬明.人机协同,"智"在必得[N].解放军报, 2019-12-06(11). ZHOU Xiaocheng, GAO Dongming. Human-machine collaboration, "wisdom" must be won[N]. People's Liberation Army Daily, 2019-12-06(11).
[33] 薛兆元,连恒,仲星,等.基于"互联网+"的自然资源利用监测模式研究[J].安徽农业科学, 2021, 49(7):237-239. XUE Zhaoyuan, LIAN Heng, ZHONG Xing, et al. Research on the monitoring mode of natural resources utilization based on" Internet+"[J]. Journal of Anhui Agricultural Sciences, 2021, 49(7):237-239.
[34] 王占宏,白穆,李宏建.地理空间大数据服务自然资源调查监测的方向分析[J].地理信息世界, 2019, 26(1):1-5. WANG Zhanhong, BAI Mu, LI Hongjian. Direction analysis on service for natural resource investigation and monitoring using geospatial big data[J]. Geomatics World, 2019, 26(1):1-5.
[35] 自然资源部.实景三维中国建设技术大纲(2021版):自然资办发[2021] 56号[N]. 2021-08-11. Department of Natural Resources. Real 3D China construction technology outline (2021 edition):natural resources development [2021] no. 56[N]. 2021-08-11.
[36] 梁顺林,白瑞,陈晓娜,等. 2019年中国陆表定量遥感发展综述[J].遥感学报, 2020, 24(6):618-671. LIANG Shunlin, BAI Rui, CHEN Xiaona, et al. Review of China's land surface quantitative remote sensing development in 2019[J]. Journal of Remote Sensing, 2020, 24(6):618-671.
[37] WU Jianguo. Urban ecology and sustainability:the state-of-the-science and future directions[J]. Landscape and Urban Planning, 2014, 125:209-221.
[38] SRIVASTAVA S, VARGAS-MUÑOZ J E, TUIA D. Understanding urban landuse from the above and ground perspectives:a deep learning, multimodal solution[J]. Remote Sensing of Environment, 2019, 228:129-143.
[39] 陈军,陈斐,武昊,等.互联网+地表覆盖验证及应用[J].武汉大学学报(信息科学版), 2018, 43(12):2225-2232. CHEN Jun, CHEN Fei, WU Hao, et al. Internet⁺ land cover validation:methodology and practice[J]. Geomatics and Information Science of Wuhan University, 2018, 43(12):2225-2232.
[40] 孟雯,童小华,谢欢,等.基于空间抽样的区域地表覆盖遥感制图产品精度评估——以中国陕西省为例[J].地球信息科学学报, 2015, 17(6):742-749. MENG Wen, TONG Xiaohua, XIE Huan, et al. Accuracy assessment for regional land cover remote sensing mapping product based on spatial sampling:a case study of Shaanxi province, China[J]. Journal of Geo-Information Science, 2015, 17(6):742-749.
[41] 应申,李程鹏,郭仁忠,等.自然资源全要素概念模型构建[J].中国土地科学, 2019, 33(3):50-58. YING Shen, LI Chengpeng, GUO Renzhong, et al. Conceptual model construction of natural resource full factors[J]. China Land Science, 2019, 33(3):50-58.
[42] XUE Zhaohui, NIE Xiangyu. Low-rank and sparse representation with adaptive neighborhood regularization for hyperspectral image classification[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(1):73-90. DOI:10.11947/j.JGGS.2022.0108.
[43] LIU Wensong, JI Xinyuan, LIU Jie, et al. A novel unsupervised change detection method with structure consistency and GFLICM based on UAV images[J]. Journal of Geodesy and Geoinformation Science, 2022, 5(1):91-102. DOI:10.11947/j.JGGS.2022.0109.