图形、图像融合利用的集成学习智能化简方法及其在岛屿岸线化简中的应用

doi:10.11947/j.AGCS.2022.20210135

摘要/Abstract

摘要： 为充分利用已有化简成果及其蕴含的化简知识，本文集成几种机器学习算法提出图形、图像融合利用的智能化简方法，实现顶点取舍决策的学习和优化。首先，分别利用全连接神经网络和卷积神经网络设计、构建基于图形的顶点取舍模型和基于图像的顶点取舍模型，通过样本训练各模型拟合从图形特征到顶点取舍和从栅格图像到顶点取舍的映射；然后，基于线性加权、朴素贝叶斯、支持向量机、人工神经网络构建多种融合决策模型，实现基于图形和基于图像的顶点取舍的融合利用；最后，通过试验用例对所有模型进行测试。试验结果表明：基于图形和基于图像的顶点取舍模型在一定程度上学习、掌握了化简算子，融合利用后还能进一步提高化简准确性、实现优势互补。

关键词: 地图综合, 化简, 机器学习, 人工神经网络

Abstract: To make use of accumulated simplification data and their contained simplification knowledge sufficiently, we propose an intelligent method based on the integration of several machine learning algorithms, which can use vector features and raster images to learn the vertex selection of polyline simplification in this paper. First, vertex selection models based on vector features and raster images are constructed by the fully connected neural network and the convolutional neural network respectively. Trained by corresponding samples, these two models can be utilized to generate vertex selection decisions via inputting vector features or raster images respectively. Second, some fusion models are constructed based on the linear weighting method, naive Bayes method, support vector machine, and artificial neural network to utilize outputs of vector-based and raster-based models to generate better decisions for vertex simplification. Finally, the proposed method applies into a use case. Experimental results show that the vector-based model and the raster-based model can learn and master vertex simplification in different levels, and fusion models can make complementary advantages of raster-based and vector-based models to improve the simplification accuracy further, and the best fusion model is better than some other simplification methods.

Key words: map generalization, simplification, machine learning, artificial neural network

中图分类号:

P283.7

杜佳威, 武芳, 朱丽, 刘呈熠, 王安东. 图形、图像融合利用的集成学习智能化简方法及其在岛屿岸线化简中的应用[J]. 测绘学报, 2022, 51(3): 373-387.

DU Jiawei, WU Fang, ZHU Li, LIU Chengyi, WANG Andong. An ensemble learning simplification approach based on multiple machine-learning algorithms with the fusion using of raster and vector data and a use case of coastline simplification[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(3): 373-387.

参考文献

[1] 王家耀, 钱海忠. 制图综合知识及其应用[J]. 武汉大学学报(信息科学版), 2006, 31(5):382-386, 439. WANG Jiayao, QIAN Haizhong. Cartographic-generalization-knowledge and its application[J]. Geomatics and Information Science of Wuhan University, 2006, 31(5):382-386, 439.
[2] 武芳, 巩现勇, 杜佳威. 地图制图综合回顾与前望[J]. 测绘学报, 2017, 46(10):1645-1664. WU Fang, GONG Xianyong, DU Jiawei. Overview of the research progress in automated map generalization[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10):1645-1664.
[3] 钱海忠, 武芳, 王家耀. 自动制图综合及其过程控制的智能化研究[M]. 北京:测绘出版社, 2012. QIAN Haizhong, WU Fang, WANG Jiayao. Study of automated cartographic generalization and intelligentized generalization process control[M]. Beijing:Surveying and Mapping Press, 2012.
[4] TOUYA G, ZHANG X, LOKHAT I. Is deep learning the new agent for map generalization[J]. International Journal of Cartography, 2019, 5(2-3):142-157.
[5] 王家耀, 范亦爱, 韩同春, 等. 普通地图制图综合原理[M]. 北京:测绘出版社, 1993. WANG Jiayao, FAN Yi'ai, Han Tongchun, et al. Cartographic generalization theory of general map[M]. Beijing:Surveying and Mapping Press, 1993.
[6] 武芳, 邓红艳. 基于遗传算法的线要素自动化简模型[J]. 测绘学报, 2003, 32(4):349-355. WU Fang, DENG Hongyan. Using genetic algorithms for solving problems in automated line simplification[J]. Acta Geodaetica et Cartographica Sinica, 2003, 32(4):349-355.
[7] 郑春燕, 郭庆胜, 胡华科. 基于蚁群优化算法的线状目标简化模型[J]. 测绘学报, 2011, 40(5):635-638. ZHENG Chunyan, GUO Qingsheng, HU Huake. The simplification model of linear objects based on ant colony optimization algorithm[J]. Acta Geodaetica et Cartographica Sinica, 2011, 40(5):635-638.
[8] 李进, 马劲松, 沈婕, 等. 一种基于顶点聚类的线要素简化算法改进[J]. 测绘科学技术学报, 2013, 30(5):525-529, 534. LI Jin, MA Jinsong, SHEN Jie, et al. Improvements of linear features simplification algorithm based on vertexes clustering[J]. Journal of Geomatics Science and Technology, 2013, 30(5):525-529, 534.
[9] 段佩祥, 钱海忠, 何海威, 等. 基于支持向量机的线化简方法[J]. 武汉大学学报(信息科学版), 2020, 45(5):744-752, 783. DUAN Peixiang, QIAN Haizhong, HE Haiwei, et al. A line simplification method based on support vector machine[J]. Geomatics and Information Science of Wuhan University, 2020, 45(5):744-752, 783.
[10] CHENG Boyan, LIU Qiang, LI Xiaowen, et al. Building simplification using backpropagation neural networks:a combination of cartographers' expertise and raster-based local perception[J]. GIScience & Remote Sensing, 2013, 50(5):527-542.
[11] MA L. Features extraction of buildings and generalization using deep learning[C]//Proceedings of the 28th International Cartographic Conference. Washington, DC, USA:[s.n.], 2017.
[12] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[C]//Proceedings of 2014 Conference on Advances in Neural Information Processing Systems. Montreal, Canada:[s.n.], 2014.
[13] KANG Yuhao, GAO Song, ROTH R E. Transferring multiscale map styles using generative adversarial networks[J]. International Journal of Cartography, 2019, 5(2-3):115-141.
[14] COURTIAL A, El AYEDI A, TOUYA G, et al. Exploring the potential of deep learning segmentation for mountain roads generalisation[J]. ISPRS International Journal of Geo-Information, 2020, 9(5):338-359.
[15] DU Jiawei, WU Fang, XING Ruixing, et al. Segmentation and sampling method for complex polyline generalization based on a generative adversarial network[J]. Geocarto International, 2021. DOI:10.1080/10106049.2021.1878288.
[16] ZHANG Cha, MA Yunqian. Ensemble machine learning:methods and applications[M]. New York, NY:Springer-Verlag, 2012.
[17] 杜佳威. 海岸线自动化简方法研究[D]. 郑州:信息工程大学, 2018. DU Jiawei. Research on automated coastline simplification methods[D]. Zhengzhou:Information Engineering University, 2018.
[18] SAALFELD A. Topologically consistent line simplification with the Douglas-Peucker algorithm[J]. Cartography and Geographic Information Science, 1999, 26(1):7-18.
[19] 翟京生, 陆毅. 数字海图线性特征的识别、量测与综合[J]. 测绘学报, 2000, 29(3):273-279. ZHAI Jingsheng, LU Yi. Recognition, measurement and generalization for line features in digital nautical chart[J]. Acta Geodaetica et Cartographica Sinica, 2000, 29(3):273-279.
[20] HAYKIN S. Neural networks and learning machines[M]. 3rd ed. New York, NY:Pearson Hall, 2008.
[21] HARRIS S L, HARRIS D M. Digital design and computer architecture[M]. San Francisco, CA:Morgan Kaufmann, 2015.
[22] LI Zhilin, OPENSHAW S. Algorithms for automated line generalization based on a natural principle of objective generalization[J]. International Journal of Geographical Information Systems, 1992, 6(5):373-389.
[23] 孙家广, 胡事民. 计算机图形学基础教程[M]. 2版. 北京:清华大学出版社, 2009. SUN Jiaguang, HU Shimin. Fundamentals and principles of computer graphics[M]. 2nd ed. Beijing:Tsinghua University Press, 2009.
[24] KRIZHEVSKY A, SUTSKEVER I, HINTON G. ImageNet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems 25:26th Annual Conference on Neural Information Processing Systems 2012. Lake Tahoe, NV:NIPS, 2012:1097-1105.
[25] 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. DOI:10.11947/j.AGCS.2018.20170265. HE Haiwei, QIAN Haizhong, XIE Limin, et al. Interchange recognition method based on CNN[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(3):385-395. DOI:10.11947/j.AGCS.2018.20170265.
[26] 陆川伟, 孙群, 陈冰, 等. 车辆轨迹数据的道路学习提取法[J]. 测绘学报, 2020, 49(6):692-702. DOI:10.11947/j.AGCS.2020.20190305. LU Chuanwei, SUN Qun, CHEN Bing, et al. Road learning extraction method based on vehicle trajectory data[J]. Acta Geodaetica et Cartographica Sinica, 2020, 49(6):692-702. DOI:10.11947/j.AGCS.2020.20190305.
[27] IOFFE S, SZEGEDY C. Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on Machine Learning. Lille, France:JMLR.org, 2015.
[28] SANTURKAR S, TSIPRAS D, ILYAS A, et al. How does batch normalization help optimization?[C]//Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montreal, Canada:Curran Associates Inc., 2018.
[29] HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV:IEEE, 2016:770-778.
[30] YAN Bo, JANOWICZ K, MAI Gengchen, et al. xNet+SC:classifying places based on images by incorporating spatial contexts[C]//Proceedings of the 10th International Conference on Geographic Information Science (GIScience 2018). Melbourne, Australia:Schloss Dagstuhl-Leibniz-Zentrum für Informatik, 2018.
[31] JOSHI M, KUMAR V, AGARWAL R. Evaluating boosting algorithms to classify rare classes:comparison and improvements[C]//Proceedings of 2001 IEEE International Conference on Data Mining. San Jose, CA:IEEE, 2001:257-264.
[32] 杜佳威, 武芳, 李靖涵, 等. 一种河口湾海岸线渐进化简方法[J]. 测绘学报, 2018, 47(4):547-556. DOI:10.11947/j.AGCS.2018.20170440. DU Jiawei, WU Fang, LI Jinghan, et al. A progressive simplification method for the estuary coastline[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(4):547-556. DOI:10.11947/j.AGCS.2018.20170440.
[33] KINGMA D P, BA J L. Adam:a method for stochastic optimization[C]//Proceedings of 2015 International Conference on Learning Representations. Ithaca, NY:ICLR, 2015.
[34] 何海威, 钱海忠, 段佩祥, 等. 线要素化简及参数自动设置的案例推理方法[J]. 武汉大学学报(信息科学版), 2020, 45(3):344-352. HE Haiwei, QIAN Haizhong, DUAN Peixiang, et al. Automatic line simplification algorithm selecting and parameter setting based on case-based reasoning[J]. Geomatics and Information Science of Wuhan University, 2020, 45(3):344-352.
[35] KRONENFELD B J, STANISLAWSKI L V, BUTTENFIELD B P, et al. Simplification of polylines by segment collapse:minimizing areal displacement while preserving area[J]. International Journal of Cartography, 2020, 6(1):22-46.
[36] CHROBAK T, SZOMBARA S, KOZOŁ K, et al. A method for assessing generalized data accuracy with linear object resolution verification[J]. Geocarto International, 2017, 32(3):238-256.
[37] 刘鹏程. 形状识别在地图综合中的应用研究[D]. 武汉:武汉大学, 2009. LIU Pengcheng. Applications of shape recognition in map generalization[D]. Wuhan:Wuhan University, 2009.
[38] 钱海忠, 何海威, 王骁, 等. 采用三元弯曲组划分的线要素化简方法[J]. 武汉大学学报(信息科学版), 2017, 42(8):1096-1103. QIAN Haizhong, HE Haiwei, WANG Xiao, et al. Line feature simplification method based on bend group division[J]. Geomatics and Information Science of Wuhan University, 2017, 42(8):1096-1103.
[39] RAPOSO P. Scale-specific automated line simplification by vertex clustering on a hexagonal tessellation[J]. Cartography and Geographic Information Science, 2013, 40(5):427-443.
[40] 朱鲲鹏, 武芳, 王辉连, 等. Li-Openshaw算法的改进与评价[J]. 测绘学报, 2007, 36(4):450-456. ZHU Kunpeng, WU Fang, WANG Huilian, et al. Improvement and assessment of Li-Openshaw algorithm[J]. Acta Geodaetica et Cartographica Sinica, 2007, 36(4):450-456.
[41] DU Jiawei, WU Fang, XING Ruixing, et al. An automated approach to coastline simplification for maritime structures with collapse operation[J]. Marine Geodesy, 2021, 44(3):157-195.
[42] YAN Xiongfeng, AI Tinghua, YANG Min, et al. Graph convolutional autoencoder model for the shape coding and cognition of buildings in maps[J]. International Journal of Geographical Information Science, 2021, 35(3):490-512.