建筑物多边形高精度识别的傅里叶形状描述子神经网络方法

doi:10.11947/j.AGCS.2022.20210730

测绘学报 ›› 2022, Vol. 51 ›› Issue (9): 1969-1976.doi: 10.11947/j.AGCS.2022.20210730

建筑物多边形高精度识别的傅里叶形状描述子神经网络方法

刘鹏程^1,2, 黄欣^1,2, 马宏然^1,2, 杨敏³

1. 华中师范大学地理过程分析与模拟湖北省重点实验室, 湖北武汉 430079;
2. 华中师范大学城市与环境科学学院, 湖北武汉 430079;
3. 武汉大学资源与环境科学学院, 湖北武汉 430079

收稿日期:2021-12-30 修回日期:2022-07-27 发布日期:2022-09-29
作者简介:刘鹏程(1968—),男,博士,副教授,主要研究方向为地图综合、空间模式识别和深度学习。E-mail:liupc@ccnu.edu.cn
基金资助:
国家自然科学基金（42071455；42071450）

Fourier descriptor-based neural network method for high-precision shape recognition of building polygon

LIU Pengcheng^1,2, HUANG Xin^1,2, MA Hongran^1,2, YANG Min³

1. Key Laboratory for Geographical Process Analysis & Simulation of Hubei Province, Central China Normal University, Wuhan 430079, China;
2. School of Urban and Environmental Sciences, Central China Normal University, Wuhan 430079, China;
3. School of Resource and Environment Sciences, Wuhan University, Wuhan 430079, China

Received:2021-12-30 Revised:2022-07-27 Published:2022-09-29
Supported by:
The National Natural Science Foundation of China(Nos. 42071455; 42071450)

摘要/Abstract

摘要： 形状识别是地图空间认知的重要内容之一，结合有效的形状特征向量提取方法和空间认知试验的神经网络方法是提高形状识别的有效途径。本文构建了一种融合了圆形度、偏心率和矩形度等宏观形状特征参量的傅里叶形状描述子作为形状特征向量的神经网络建筑多边形状识别器。首先，利用傅里叶变换和计算几何方法分别提取建筑多边形的傅里叶形状描述子及圆形度、偏心率、矩形度参量，并组成形状特征向量。然后，通过样本数据的训练实现了建筑多边形与形状模板之间匹配的神经网络识别器。结果表明，本文方法相较于以往的方法大幅度提高了精度（达到98.7%），而且特征提取算法不受多边形点数不一致的限制。通过对武汉、郑州两大城市的真实建筑物数据进行形状识别，证实该方法具有较好的识别效果。

关键词: 傅里叶形状描述子, 神经网络, 模板匹配, 建筑多边形形状识别

Abstract: Shape recognition is one of the important contents of map spatial cognition, and neural network combined with spatial cognitive experiment and its effective shape feature vector extraction are effective ways to improve shape recognition. In this paper, a neural network building-polygon shape recognizer is constructed, which integrates the Fourier descriptors of macro shape parameters such as roundness, eccentricity and rectangularity as shape feature vectors. Firstly, the Fourier shape descriptors, circularity, eccentricity and rectangularity parameters of building polygons are extracted by Fourier transform and computational geometry methods, and the shape feature vectors are formed. Then, the neural network recognizer matching between building polygon and shape template is realized through the training of sample data. The results show that this method greatly improves the accuracy (98.7%) compared with the previous methods, and the feature extraction algorithm is not limited by the inconsistency of polygon points. The shape recognition of real building data in Wuhan and Zhengzhou is carried out, and its information entropy is calculated. This method has good recognition effect.

Key words: Fourier shape descriptor, neural network, shape template match, building-polygon shape recognition

中图分类号:

P208

刘鹏程, 黄欣, 马宏然, 杨敏. 建筑物多边形高精度识别的傅里叶形状描述子神经网络方法[J]. 测绘学报, 2022, 51(9): 1969-1976.

LIU Pengcheng, HUANG Xin, MA Hongran, YANG Min. Fourier descriptor-based neural network method for high-precision shape recognition of building polygon[J]. Acta Geodaetica et Cartographica Sinica, 2022, 51(9): 1969-1976.

参考文献

[1] 艾廷华,帅赟,李精忠.基于形状相似性识别的空间查询[J].测绘学报,2009,38(4):356-362. AI Tinghua,SHUAI Yun, LI Jingzhong.A spatial query based on shape similarity cognition[J]. Acta Geodaetica et Cartographica Sinica,2009,38(4):356-362.
[2] 晏雄锋,袁拓,杨敏,等.建筑物形状特征分析表达与自适应化简方法[J].测绘学报,2022,51(2):269-278. DOI:10.11947/j.AGCS.2022.20210302. YAN Xiongfeng, YUAN Tuo, YANG Min, et al. An adaptive building simplification approach based on shape analysis and representation[J]. Acta Geodaetica et Cartographica Sinica,2022,51(2):269-278. DOI:10.11947/j.AGCS.2022.20210302.
[3] RAINSFORD D,MACKANESS W.Template matching in support of generalization of rural buildings[M]//RICHARDSON D E,VAN OOSTEROM P.Advances in Spatial Data Handling.Berlin:Springer,2002:137-151.
[4] 刘鹏程,艾廷华,胡晋山,等.基于原型模板形状匹配的建筑多边形化简[J].武汉大学学报(信息科学版),2010, 35(11):1369-1372. LIU Pengcheng,AI Tinghua,HU Jinshan, et al. Building polygon simplification based on shape matching of prototypetemplate[J].Geomatics and Information Science of Wuhan University,2010,35(11):1369-1372.
[5] WANG Zeshen,LEE Dan.Building simplification based on pattern recognition and shape analysis[C]//Proceedings of the 9th International Symposium on Spatial Data Handling. Beijing:Springer,2000:58-72.
[6] 晏雄锋, 艾廷华, 杨敏. 居民地要素化简的形状识别与模板匹配方法[J]. 测绘学报, 2016, 45(7):874-882. DOI:10.11947/j.AGCS.2016.20150162. YAN Xiongfeng, AI Tinghua, YANG Min. A simplification of residential feature by the shape cognition and template matching method[J]. Acta Geodaetica et Cartographica Sinica, 2016, 45(7):874-882. DOI:10.11947/j.AGCS.2016.20150162.
[7] 安晓亚. 空间数据几何相似性度量理论方法与应用研究[J]. 测绘学报, 2013,42(1):157. AN Xiaoya. Research on theory, methods and applications of geometry similarity measurement for spatial data[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(1):157.
[8] 韩敏,郑丹晨. 基于模糊形状上下文特征的形状识别算法[J]. 自动化学报,2012, 38(1):68-75. DOI:10.3724/SP.J.1004.2012.00068. HAN Min, ZHENG Danchen. Shape recognition based on fuzzy shape context[J].Acta Automatica Sinica, 2012, 38(1):68-75. DOI:10.3724/SP.J.1004.2012.00068.
[9] GUO W, YU A, SUN Q, et al. A multisource contour matching method considering the similarity of geometric features[J].The Journal of Geodesy and Geoinformation Science, 2020,3(3):76-87. DOI:10.11947/j.JGGS.2020.0308.
[10] 吴绍根,聂为清,路利军,等.典型的基于区域的形状表示方法比较[J].中国图象图形学报,2018,23(8):1242-1253. WU Shaogen,NIE Weiqing,LU Lijun, et al. Comparative study of classic region-based shape descriptors[J]. Journal of Image and Graphics, 2018, 23(8):1242-1253.
[11] FREEMAN H. On theencoding of arbitrary geometric configurations[J]. IEEE Transactions on Electronic Computers,1961,10(2):260-268. DOI:10.1109/tec.1961.5219197.
[12] FREEMAN H. Computer processing of line drawing images[J].ACM Computing Surveys,1974,6(1):57-97.
[13] ZAHNC T, ROSKIES R Z. Fourier descriptors for plane closed curves[J].IEEE Transactions on Computers, 2009, C-21(3):269-281. DOI:10.1109/TC.1972.5008949.
[14] MOELLERING H, RAYNER J N. The harmonic analysis of spatial shapes using dual axis Fourier shape analysis (DAFSA)[J].Geographical Analysis, 2010, 13(1):64-77. DOI:10.1109/TSMC.1977.4309681.
[15] 刘鹏程. 形状识别在地图综合中的应用研究[J]. 测绘学报, 2012,41(2):316. LIU Pengcheng. Applications of shape recognition in map generalization[J]. Acta Geodaetica et Cartographica Sinica, 2012, 41(2):316.
[16] AI T, CHENG X, LIU P, et al. A shape analysis and template matching of building features by the Fourier transform method[J].Computers Environment & Urban Systems, 2013, 41(sep.):219-233.
[17] ARKIN E,CHEW L,HUTTENLOCHE R D,et al.An efficiently computable metric for comparing polygonal shapes[J].IEEE Transaction on Pattern Analysis and Machine Intelligence,1991,13(3):209-216.
[18] ATTALLA E, SIY P. Robust shape similarity retrieval based on contour segmentation polygonal multiresolution and elastic matching[J].Pattern Recognition, 2005, 38(12):2229-2241.DOI:10.1016/j.patcog.2005.02.009.
[19] 丁险峰,吴洪,张宏江,等. 形状匹配综述[J]. 自动化学报,2001, 27(5):678-694. DING Xianfeng, WU Hong, ZHANG Hongjiang, et al. Review on shape matching[J].Acta Automatica Sinica, 2001, 27(5):678-694.
[20] 周瑜,刘俊涛,白翔.形状匹配方法研究与展望[J].自动化学报,2012,38(6):889-910. ZHOU Yu, LIU Juntao, BAI Xiang. Research and perspective on shape matching[J]. Acta Automatica Sinica, 2012,38(6):889-910.
[21] 刘鹏程,艾廷华,杨敏.基于傅里叶级数的等高线网络渐进式传输模型[J].测绘学报,2012,41(2):284-290. LIU Pengcheng,AI Tinghua,YANG Min. The internet progressive transmission model for contour based on Fourier series[J]. Acta Geodaetica et Cartographica Sinica,2012,41(2):284-290.
[22] 刘鹏程,罗静,艾廷华,等.基于线要素综合的形状相似性评价模型[J].武汉大学学报(信息科学版),2012,37(1):114-117. LIU Pengcheng, LUO Jing, AI Tinghua, et al. Evaluation model for similarity based on curve generalization[J].Geomatics and Information Science of Wuhan University, 2012,37(1):114-117.
[23] 刘鹏程,肖天元,肖佳,等.曲线多尺度表达的Head-Tail信息量分割法[J].测绘学报,2020,49(7):921-933. DOI:10.11947/j.AGCS.2020.20200004. LIU Pengcheng, XIAO Tianyuan, XIAO Jia, et al. A head-tail information break method oriented to multi-scale representation of polyline[J]. Acta Geodaetica et Cartographica Sinica, 2020,49(7):921-933. DOI:10.11947/j.AGCS.2020.20200004.
[24] 刘鹏程,肖天元,艾廷华,等.基于傅里叶能量度量的曲线多尺度表达[J].中国矿业大学学报,2020,49(3):587-594. LIU Pengcheng, XIAO Tianyuan, AI Tinghua, et al.Multi-scale representation of curves based on Fourier energy metric[J].Journal of China University of Mining & Technology,2020,49(3):587-594.
[25] YAN X, AI T, YANG M, et al. Graph convolutional autoencoder model for the shape coding and cognition of buildings in maps[J]. International Journal of Geographical Information Science, 2020,35(3):490-512.

建筑物多边形高精度识别的傅里叶形状描述子神经网络方法

Fourier descriptor-based neural network method for high-precision shape recognition of building polygon

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	张爽, 陈西宏, 刘强, 刘赞, 王庆力. 耦合PSO与扩展RBF神经网络估计NWM模型ZTD计算精度[J]. 测绘学报, 2022, 51(9): 1911-1919.
[2]	陶庭叶, 李江洋, 朱勇超, 汪俊涛, 陈皓, 时梦杰. 阶段模型修正的星载GNSS-R土壤湿度反演方法[J]. 测绘学报, 2022, 51(9): 1942-1950.
[3]	徐天河, 李耸, 王帅民, 江楠. 顾及气象数据的中国区域对流层延迟RBF神经网络优化模型[J]. 测绘学报, 2022, 51(8): 1690-1707.
[4]	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.
[5]	张玉鑫, 颜青松, 邓非. 高分辨率遥感影像建筑物提取多路径RSU网络法[J]. 测绘学报, 2022, 51(1): 135-144.
[6]	杨秋莲, 刘艳飞, 丁乐乐, 孟凡效. 高分影像场景分类的半监督深度卷积神经网络学习方法[J]. 测绘学报, 2021, 50(7): 930-938.
[7]	叶发茂, 孟祥龙, 董萌, 聂运菊, 葛芸, 陈晓勇. 遥感图像蚁群算法和加权图像到类距离检索法[J]. 测绘学报, 2021, 50(5): 612-620.
[8]	张传辉, 姚国标, 张力, 艾海滨, 满孝成, 黄鹏飞. 多分支网络联合的倾斜影像仿射不变特征匹配[J]. 测绘学报, 2021, 50(5): 641-651.
[9]	施慧慧, 徐雁南, 滕文秀, 王妮. 高分辨率遥感影像深度迁移可变形卷积的场景分类法[J]. 测绘学报, 2021, 50(5): 652-663.
[10]	蓝朝桢, 卢万杰, 于君明, 徐青. 异源遥感影像特征匹配的深度学习算法[J]. 测绘学报, 2021, 50(2): 189-202.
[11]	汤寓麟, 金绍华, 边刚, 张永厚, 李凡. 侧扫声呐识别沉船影像的迁移学习卷积神经网络法[J]. 测绘学报, 2021, 50(2): 260-269.
[12]	成飞飞, 付志涛, 黄亮, 陈朋弟, 黄琨. 结合自适应PCNN的非下采样剪切波遥感影像融合[J]. 测绘学报, 2021, 50(10): 1380-1389.
[13]	樊仲藜, 张力, 王庆栋, 刘思婷, 叶沅鑫. SAR影像和光学影像梯度方向加权的快速匹配方法[J]. 测绘学报, 2021, 50(10): 1390-1403.
[14]	阳凡林, 朱正任, 李家彪, 冯成凯, 邢喆, 吴自银. 利用深层卷积神经网络实现地形辅助的多波束海底底质分类[J]. 测绘学报, 2021, 50(1): 71-84.
[15]	王旭, 柴洪洲, 王昶, 种洋. 优选小波函数的小波神经网络预报GPS卫星钟差[J]. 测绘学报, 2020, 49(8): 983-992.