闵春平,姚敏,赵岱虹,李治君,杨帆,涂强,吴豪,金明哲
MIN Chunping,YAO Min,ZHAO Daihong,LI Zhijun,YANG Fan,TU Qiang,WU Hao,JIN Mingzhe

• 1:自然资源部信息中心

摘要(Abstract)：

为推进全国采矿损毁土地现状普查工作，推进矿山生态环境修复的科学化、规范化，数据采集分析及核查评估的智能技术应用亟须加强。本文梳理总结了国内外遥感图像智能解译的研究现状，尝试融合多源、多模态大数据技术，将遥感图像智能解译技术与知识图谱和图神经网络相结合，构建了知识引导的全国采矿损毁土地状况智能化调查框架。该框架分为大数据采集汇聚层、大数据存储管理层、智能解译层和应用层，有助于优化采矿损毁土地状况调查流程，形成采矿损毁土地数据智能化采集更新机制，为盘活利用采矿废弃土地、分区分类实施矿山生态修复、促进煤矸石和尾矿等资源综合利用提供科学依据和技术支撑。
To advance the nationwide survey of mining-damaged land conditions and accelerate the scientific and standardized development of mine ecological restoration, it is urgent to enhance the application of intelligent technologies in data collection, analysis, verification and calibration. This study first systematically reviews the research status of intelligent interpretation of remote sensing images both domestically and internationally. Subsequently, through the integration of multi-source and multi-modal big data technologies, it combines intelligent remote sensing image interpretation techniques with knowledge graphs and graph neural networks to construct a knowledge-guided intelligent survey framework for nationwide mining-damaged land. This framework consists of four layers: big data collection and convergence, big data storage management, intelligent interpretation, and application layer. The framework optimizes the mining-damaged land survey process, establishes an intelligent mechanism for mining-damaged land data collection and updates, and provides scientific basis and technical support for revitalizing and utilizing abandoned mining land, implementing ecological restoration of mines through zoning and classification, and promoting the comprehensive utilization of resources such as coal gangue and tailings.

关键词(KeyWords)： 采矿损毁土地;遥感图像智能解译;深度学习;语义分割;知识图谱
mining-damaged land;intelligent interpretation of remote sensing images;deep learning;semantic segmentation;knowledge graph

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 闵春平,姚敏,赵岱虹,李治君,杨帆,涂强,吴豪,金明哲
MIN Chunping,YAO Min,ZHAO Daihong,LI Zhijun,YANG Fan,TU Qiang,WU Hao,JIN Mingzhe

参考文献(References)：

• [1] CHEN L C, PAPANDREOU G, KOKKINOS I, et al.Semantic image segmentation with deep convolutional nets and fully connected CRFs[EB/OL].(2018-08-09)[2024-10-10]. https://ui.adsabs.harvard.edu/abs/2014arXiv1412.7062C/abstrac.
• [2] CHEN L C, PAPANDREOU G, KOKKINOS I, et al.DeepLab:semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4):834-848.
• [3] CHEN L C, PAPANDREOU G, SCHROFF F, et al.Rethinking atrous convolution for semantic image segmentation[EB/OL].(2018-05-09)[2024-10-10].https://arxiv.org/abs/1706.05587v3.
• [4] CHEN L C, ZHU Y K, PAPANDREOU G, et al.Encoder-decoder with atrous separable convolution for semantic image segmentation[EB/OL].(2018-10-06)[2024-10-10]. https://link.springer.com/chapt er/10.1007/978-3-030-01234-2_49.
• [5] MA Y T, MENG J M, SUN L N, et al. Oceanic internal wave signature extraction in the Sulu Sea by a pixel attention U-Net:PAU-Net[J]. IEEE Geoscience and Remote Sensing Letters, 2023, 20:1-5.
• [6] LIU Z, LIN Y, CAO Y, et al. Swin Transformer:hierarchical vision transformer using shifted windows[C]//2021 IEEE/CVF International Conference on Computer Vision(ICCV),Montreal, QC, Canada, 2021:9992-10002.
• [7] ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks[C]//Computer Vision-ECCV 2014.Cham:Springer International Publishing, 2014:818-833.
• [8] YANG Y, NEWSAM S. Bag-of-visual-words and spatial extensions for land-use classification[C]//Proceedings of the18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, San Jose California,2010.
• [9] ZHAO B, ZHONG Y F, XIA G S, et al. Dirichlet-derived multiple topic scene classification model for high spatial resolution remote sensing imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(4):2108-2123.
• [10] CHENG G, HAN J W, LU X Q. Remote sensing image scene classification:benchmark and state of the art[J].Proceedings of the IEEE, 2017, 105(10):1865-1883.
• [11]徐盛.基于主题模型的高空间分辨率遥感影像分类研究[D].上海：上海交通大学，2012.
• [12] ZITNICK C L, DOLLáR P. Edge boxes:locating object proposals from edges[M]//Computer Vision-ECCV 2014.Cham:Springer International Publishing, 2014:391-405.
• [13]石秋萍.基于多层网络的遥感图像场景分类[D].西安：西安电子科技大学，2018.
• [14] REN S, HE K, GIRSHICK R, et al. Faster R-CNN:Towards Real-Time Object Detection with Region Proposal Networks[C]//Advances in Neural Information Processing Systems 28, Montreal, Canada, 2015:91-99.
• [15] SUN W W, WANG R S. Fully convolutional networks for semantic segmentation of very high resolution remotely sensed images combined with DSM[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(3):474-478.
• [16] CASTELLUCCIO M, POGGI G, SANSONE C, et al. Land use classification in remote sensing images by convolutional neural networks[EB/OL].(2015-08-01)[2024-10-10].https://arxiv.org/abs/1508.00092v1.
• [17] HU F, XIA G S, HU J W, et al. Transferring deep convolutional neural networks for the scene classification of high-resolution remote sensing imagery[J]. Remote Sensing, 2015, 7(11):14680-14707.
• [18] DAI J, QI H, XIONG Y, et al. Deformable Convolutional Networks[C]//2017 IEEE International Conference on Computer Vision(ICCV), Venice, Italy, 2017:764-773.
• [19] KAMPFFMEYER M, SALBERG A B, JENSSEN R.Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops(CVPRW), Las Vegas, NV, USA, 2016:680-688.
• [20] CAO X, ZHANG Y, Lang S, et al. Swin-transformer-based YOLOv5 for small-object detection in remote sensing images[J]. Sensors(Basel), 2023, 23(7):3634.
• [21] HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Las Vegas, NV, USA, 2016:770-778.
• [22] SUN Y, TIAN Y, XU Y P. Problems of encoder-decoder frameworks for high-resolution remote sensing image segmentation:Structural stereotype and insufficient learning[J]. Neurocomputing, 2019, 330:297-304.
• [23]张媛.基于OpenLayers的地理对象遥感解译在线知识库的设计与开发[D].武汉：武汉大学，2018.
• [24]张海林.遥感影像解译标志库设计与开发[D].长春：吉林大学，2015.
• [25] CHENG G, HAN J W. A survey on object detection in optical remote sensing images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 117:11-28.
• [26] PAN J Z, VETERE G, GOMEZ-PEREZ J M, et al.Exploiting linked data and knowledge graphs in large organisations[M]. Cham:Springer International Publishing,2017.
• [27] JIA J, ZHANG Y Z, SAAD M. An approach to capturing and reusing tacit design knowledge using relational learning for knowledge graphs[J]. Advanced Engineering Informatics,2022, 51:101505.
• [28] CHEN J F, ZHU J, SONG L. Stochastic training of graph convolutional networks with variance reduction[EB/OL].(2017-10-29)[2024-10-10]. https://arxiv.org/abs/1710.10568v3.
• [29] KHAN N, MA Z M, MA R Z, et al. Continual knowledge graph embedding enhancement for joint interaction-based next click recommendation[J]. Knowledge-Based Systems,2024, 304:112475.
• [30]欧阳松.地学知识嵌入的遥感影像深度语义分割方法研究[D].武汉：武汉大学，2021.
• [31] ZHENG D H, SHI X M. A multi-scale GNN-based personalized recommender system for online consumption decision[J]. Journal of Circuits, Systems and Computers,2024, 33(18):2550014.
• [32] GUO Q H, YANG X B, LI M, et al. Collaborative graph neural networks for augmented graphs:a local-to-global perspective[J]. Pattern Recognition, 2025, 158:111020.
• [33]王熠明.遥感图像智能解译系统的设计与实现[D].银川：宁夏大学，2021.
• [34]周毅.基于高分辨一维距离像的目标特征提取及融合识别研究[D].成都：电子科技大学，2018.
• [35]许彪.基于航空影像的真正射影像制作关键技术研究[D].武汉：武汉大学，2012.