融合LiDAR数据与高分影像特征信息的建筑物提取方法

doi:10.12082/dqxxkx.2020.190459

地球信息科学学报 ›› 2020, Vol. 22 ›› Issue (8): 1654-1665.doi: 10.12082/dqxxkx.2020.190459

融合LiDAR数据与高分影像特征信息的建筑物提取方法

郭峰¹^,²(), 毛政元¹^,²^,^*(), 邹为彬¹^,³, 翁谦⁴^,⁵

1.福州大学数字中国研究院（福建）,福州 350108
2.福州大学空间数据挖掘与信息共享教育部重点实验室,福州 350108
3.福建工程学院交通运输学院,福州 350118
4.福州大学数学与计算机科学学院,福州 350116
5.福建省网络计算与智能信息处理省重点实验室（福州大学）, 福州 350116

收稿日期:2019-08-26 修回日期:2019-10-17 出版日期:2020-08-25 发布日期:2020-10-25
作者简介:郭峰（1995— ）,男,江西宜春人,硕士生,主要从事遥感信息提取、机器学习研究。E-mail:guofeng929@foxmail.com
基金资助:
国家自然科学基金项目(41701491);福建省自然科学基金项目(2017J01464);国家自然科学基金青年基金项目(41801324);福建省自然科学基金面上项目(2019J01244)

A Method for Building Extraction by Fusing Feature Information from LiDAR Data and High-Resolution Imagery

GUO Feng¹^,²(), MAO Zhengyuan¹^,²^,^*(), ZOU Weibin¹^,³, WENG Qian⁴^,⁵

1. The Academy of Digital China, Fuzhou University, Fuzhou 350108, China
2. Key Laboratory of Spatial Data Mining & Information Sharing of Ministry of Education, Fuzhou University, Fuzhou 350108, China
3. School of Transportation, Fujian University of technology, Fuzhou 350118, China
4. College of Mathematics and Computer Science, Fuzhou University, Fuzhou 350116, China
5. Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing (Fuzhou University), Fuzhou 350116, China

Received:2019-08-26 Revised:2019-10-17 Online:2020-08-25 Published:2020-10-25
Contact: MAO Zhengyuan
Supported by:
National Natural Science Founda- tion of China(41701491);National Natural Science Foundation of Fujian province(2017J01464);National Natural Science Foundation of China(41801324);National Natural Science Foundation of Fujian province(2019J01244)

摘要/Abstract

摘要：

建筑物是城市环境中的主要地物类型,从高分影像等数据中自动提取建筑物对于提升土地利用变化检测、城市规划与土地执法等业务的质量与效率具有重要意义。本文针对现有建筑物提取方法存在的边界提取不精确的问题以及采用手工特征表达图像信息的局限性,融合LiDAR数据与高分影像两种数据源的特征信息,提出一种基于SegNet语义模型的建筑物提取新方法。首先,对LiDAR数据预处理得到数字表面模型（DSM）、数字地形模型（DTM）、归一化数字表面模型（nDSM）,利用高分影像NDVI值去除nDSM中部分树木点,得到结果影像nDSM_en;其次,分别获取LiDAR数据回波强度、表面曲率以及高分影像NDVI值 3个特征构建特征图像训练SegNet语义模型,利用训练得到的模型完成建筑物初始提取;最后,采用阈值法分割nDSM_en得到影像对象,利用影像对象约束建筑物初始提取结果,完成建筑物精提取。在以ISPRS 官方提供的标准数据集（数据采集的地理区域为德国Vaihingen,采集时间2008年7—8月）为样本的实验中,本文方法在像素层次的平均查全率、平均查准率和提取质量分别为96.4%、94.8%和91.7%;针对面积大于50 m ²的建筑物对象,上述3个指标均为100%。实验结果表明：本文提出与实现的建筑物提取方法更好地利用了反映建筑物与非建筑物本质差异的特征信息,有效地实现了2种数据源的相对优势互补,提高了建筑物的检测与提取精度。

关键词: 建筑物提取, LiDAR数据, 高分辨率影像, SegNet, 阈值分割, 边界约束

Abstract:

One of the main feature types in urban areas is building; automatic building extraction from high-resolution imagery or other data has great significance for improving the quality and efficiency of land use change detection, urban planning, land law enforcement, and so on. To deal with the problem of boundary inaccuracy of extracted buildings and the limitation caused by expressing image information with artificial features, this paper proposed a new building extraction method based on the SegNet semantic model, which fused feature information from LiDAR data and high-resolution imagery. Firstly, LiDAR data were preprocessed to obtain Digital Surface Model (DSM), Digital Terrain Model (DTM), and normalized Digital Surface Model (nDSM). The resulted image nDSM_en was acquired by removing tree points from nDSM with Normalized Differential Vegetation Index (NDVI) values derived from high-resolution imagery. Secondly, three features–LiDAR data echo intensity, and surface curvature from LiDAR data, and NDVI from high-resolution imagery were obtained to construct feature images for training the SegNet semantic model. Initial extraction of buildings was completed with the trained model. Finally, the threshold segmentation algorithm was executed with nDSM_en for generating image objects, which were used to refine the initially extracted buildings through boundary constraints. In the experiment which utilized the Standard Dataset as a sample, the average completeness, correctness, and extract quality of the proposed method at the pixel level were 96.4%, 94.8%, and 91.7% respectively. For building objects with area larger than 50 m ², the above three indicators were 100%. Our findings suggest that the proposed building extraction method makes better use of the feature information which reflects the essential difference between buildings and non-buildings, integrates effectively the relative advantages of the two data sources, and can increase the accuracy of building detection and extraction.Key words: building extraction; LiDAR data; high resolution image; SegNet; threshold segmentation; boundary constraint

Key words: building extraction, LiDAR data, high resolution image, SegNet, threshold segmentation, boundary

郭峰, 毛政元, 邹为彬, 翁谦. 融合LiDAR数据与高分影像特征信息的建筑物提取方法[J]. 地球信息科学学报, 2020, 22(8): 1654-1665.DOI:10.12082/dqxxkx.2020.190459

GUO Feng, MAO Zhengyuan, ZOU Weibin, WENG Qian. A Method for Building Extraction by Fusing Feature Information from LiDAR Data and High-Resolution Imagery[J]. Journal of Geo-information Science, 2020, 22(8): 1654-1665.DOI:10.12082/dqxxkx.2020.190459

图/表 11

图1

图2

图3

图4

表1

图5

图6

图7

表2

表3

图8

参考文献 27

[1]	Syed G, Mohammad A, Guojun L. An automatic building extraction and regularization technique using LiDAR point cloud data and orthoimage[J]. Remote Sensing, 2016,8(3):258.
[2]	Sohn G, Dowman I. Data fusion of high-resolution satellite imagery and LiDAR data for automatic building extraction[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2007,62(1):43-63.
[3]	施文灶, 毛政元. 基于图分割的高分辨率遥感影像建筑物变化检测研究[J]. 地球信息科学学报, 2016,18(3):423-432.
	[ Shi W Z, Mao Z Y. The research on building change detection from high resolution remotely sensed imagery based on graph-cut segmentation[J]. Journal of Geo-information Science, 2016,18(3):423-432. ]
[4]	Wei Y, Zhao Z, Song J. Urban building extraction from high-resolution satellite panchromatic image using clustering and edge detection[C]. IGARSS 2004. 2004 IEEE International Geoscience & Remote Sensing Symposium. IEEE, 2004,3:2008-2010.
[5]	Turker M, Koc-San D . Building extraction from high-resolution optical spaceborne images using the integration of support vector machine (SVM) classification, Hough transformation and perceptual grouping[J]. International Journal of Applied Earth Observation and Geoinformation, 2015,34:58-69.
[6]	刘文涛, 李世华, 覃驭楚. 基于全卷积神经网络的建筑物屋顶自动提取[J]. 地球信息科学学报, 2018,20(11):1562-1570.
	[ Liu W T, Li S H, Qin Y C. Automatic building roof extraction with fully convolutional neural network[J]. Journal of Geo-information Science, 2018,20(11):1562-1570. ]
[7]	Guo L, Chehata N, Clément Mallet, et al. Relevance of airborne Lidar and multispectral image data for urban scene classification using Random Forests[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011,66(1):56-66.
[8]	Awrangjeb M, Lu G, Fraser C. Automatic building extraction from LiDAR data covering complex urban scenes[J]. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2014,40(3):25.
[9]	Zhou Z, Gong J. Automated residential building detection from airborne LiDAR data with deep neural networks[J]. Advanced Engineering Informatics, 2018,36:229-241.
[10]	Vu T T, Fumio Yamazaki, Masashi Matsuoka. Multi-scale solution for building extraction from LiDAR and image data[J]. International Journal of Applied Earth Observation and Geoinformation, 2009,11(4):281-289.
[11]	Wang X, Peijun L I, Jiang S, et al. Building extraction using airborne LiDAR data and very high resolution imagery over a complex urban area[J]. Remote Sensing for Land & Resources, 2016,28(2):106-111.
[12]	Rottensteiner F, Trinder J, Clode S, et al. Using the Dempster-Shafer method for the fusion of LIDAR data and multi-spectral images for building detection[J]. Information Fusion, 2005,6(4):283-300.
[13]	Mohammad A, Clive F. Automatic segmentation of raw LIDAR data for extraction of building roofs[J]. Remote Sensing, 2014,6(5):3716-3751.
[14]	何曼芸, 程英蕾, 邱浪波, 等. 一种改进顶帽变换与LBP高程纹理的城区建筑物提取算法[J]. 测绘学报, 2017,46(9):1116-1112.
	[ He M Y, Cheng Y L, Qiu L B, et al. An algorithm of building extraction in urban area based on improved top-hat transformations and LBP elevation texture[J]. Acta Geodaetica et Cartographica Sinica, 2017,46(9):1116-1122. ]
[15]	Awrangjeb M, Fraser C. Effective building detection in complex scenes[C]// 2013 IEEE International Geoscience & Remote Sensing Symposium-IGARSS. IEEE, 2013: 1533-1536.
[16]	Li Y, Wu H, An R, et al. An improved building boundary extraction algorithm based on fusion of optical imagery and LIDAR data[J]. Optik-International Journal for Light and Electron Optics, 2013,124(22):5357-5362.
[17]	程亮, 龚健雅. LiDAR辅助下利用超高分辨率影像提取建筑物轮廓方法[J]. 测绘学报, 2008,37(3):391-393.
	[ Cheng L, Gong J Y. LiDAR assisted extraction of building contour by ultra-high resolution images[J]. Acta Geodaetica et Cartographica Sinica, 2008,37(3):391-393. ]
[18]	杜守基, 邹峥嵘, 张云生, 等. 融合LiDAR点云与正射影像的建筑物图割优化提取方法[J]. 测绘学报, 2018,47(4):519-527.
	[ Du S J, Zou Z R, Zhang Y S, et al. A building extraction method via graph cuts algorithm by fusion of LiDAR data point cloud and orthoimage[J]. Acta Geodaetica et Cartographica Sinica, 2018,47(4):519-527. ]
[19]	Moussa A, El-Sheimy N. A new object based method for automated extraction of urban objects from airborne sensors data[J]. ISPAr, 2012,39:309-314.
[20]	Grigillo D, Kanjir U. Urban object extraction from digital surface model and digital aerial images[J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012,3:215-220.
[21]	Kraus K, Pfeifer N. Determination of terrain models in wooded areas with airborne laser scanner data[J]. ISPRS Journal of Photogrammetry & Remote Sensing, 1998,53(4):193-203.
[22]	崔建军, 隋立春, 徐花芝, 等. 基于边缘检测算法的LiDAR数据建筑物提取[J]. 测绘科学技术学报, 2008(2):98-100.
	[ Cui J J, Sui L C, Xu H Z, et al. Building extraction from LiDAR data based on edge detection algorithm[J]. Journal of Geomatics Science and Technology, 2008(2):98-100. ]
[23]	王金霞, 窦爱霞, 王晓青, 等. 地震后机载LiDAR点云的地物区分方法研究[J]. 震灾防御技术, 2017,12(3):677-689.
	[ Wang J X, Dou A X, Wang X Q, et al. Research on ground object classification method of airborne LiDAR point cloud after earthquake[J]. Technology for Earthquake Disaster Prevention, 2017,12(3):677-689. ]
[24]	Badrinarayanan V, Kendall A, Cipolla R. Segnet: A deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39(12):2481-2495. doi: 10.1109/TPAMI.2016.2644615 pmid: 28060704
[25]	Dalponte M, Hans Ole Ørka, Gobakken T, et al. Tree species classification in boreal forests with hyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2013,51(5):2632-2645.
[26]	Maxwell A E, Warner T A, Fang F. Implementation of machine-learning classification in remote sensing: An applied review[J]. International Journal of Remote Sensing, 2018,39(9):2784-2817.
[27]	Rottensteiner F, Sohn G, Jung J, et al. The ISPRS benchmark on urban object classification and 3D building reconstruction[J]. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012,1(1):293-298.

真实情况	预测结果
真实情况	正例	反例
正例	TP（真正例）	FN（假反例）
反例	FP（假正例）	TN（真反例）

测试数据	per-area 基于像素			per-object 基于对象			per-object（>50 m²）基于对象（>50 m²）
测试数据	查全率	查准率	质量	查全率	查准率	质量	查全率	查准率	质量
区域一	95.8	94.1	90.9	86.0	100.0	86.0	100.0	100.0	100.0
区域二	96.6	95.3	91.7	85.7	100.0	85.7	100.0	100.0	100.0
区域三	96.9	95.1	92.6	83.3	100.0	83.3	100.0	100.0	100.0
平均值	96.4	94.8	91.7	85.0	100.0	85.0	100.0	100.0	100.0

研究方法	per-area 基于像素			per-object 基于对象			per-object（>50 m²）基于对象（>50 m²）
研究方法	查全率	查准率	质量	查全率	查准率	质量	查全率	查准率	质量
CAL1	89.8	95.1	85.8	76.2	100.0	76.2	96.5	100.0	96.5
CAL2	89.2	97.2	87.2	78.2	100.0	78.2	100.0	100.0	100.0
LJU1	94.2	94.6	89.4	83.0	100.0	83.0	100.0	100.0	100.0
LJU2	94.6	94.4	89.5	87.9	100.0	87.9	100.0	100.0	100.0
TUM	89.7	92.9	83.9	80.9	99.0	80.2	99.1	100.0	99.1
HAND	93.6	90.3	85.0	80.3	88.8	73.0	97.4	97.2	94.6
RMA	92.8	90.2	84.2	82.7	81.0	68.1	100.0	100.0	100.0
ZJU	92.8	96.4	89.7	76.4	97.0	74.8	99.1	100.0	99.1
SZU	94.9	89.5	85.4	91.1	71.8	67.7	100.0	97.2	97.2
MON3	94.8	83.9	80.2	83.0	97.5	81.4	99.1	100.0	99.1
MON4	94.3	82.9	85.6	83.9	93.8	80.0	99.1	100.0	99.1
MON5	89.9	90.3	82.0	87.2	96.3	84	99.1	100.0	99.1
WHU_YD	89.8	98.6	89.3	87.8	99.3	87.0	99.1	100.0	99.1
CSU	94.0	94.9	90.9	83.3	97.2	82.0	100.0	100.0	100.0
HKP	91.4	97.8	90.9	79.7	96.5	77.5	99.3	100.0	99.3
本文方法	96.4	94.8	91.7	85.0	100.0	85.0	100.0	100.0	100.0

融合LiDAR数据与高分影像特征信息的建筑物提取方法

A Method for Building Extraction by Fusing Feature Information from LiDAR Data and High-Resolution Imagery

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 27

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	衡雪彪, 许捍卫, 唐璐, 汤恒, 许怡蕾. 基于改进全卷积神经网络模型的土地覆盖分类方法研究[J]. 地球信息科学学报, 2023, 25(3): 495-509.
[2]	刘洋, 康健, 管海燕, 汪汉云. 基于双注意力残差网络的高分遥感影像道路提取模型[J]. 地球信息科学学报, 2023, 25(2): 396-408.
[3]	于明洋, 陈肖娴, 张文焯, 刘耀辉. 融合网格注意力阀门和特征金字塔结构的高分辨率遥感影像建筑物提取[J]. 地球信息科学学报, 2022, 24(9): 1785-1802.
[4]	张华, 郑祥成, 郑南山, 史文中. 基于MAEU-CNN的高分辨率遥感影像建筑物提取[J]. 地球信息科学学报, 2022, 24(6): 1189-1203.
[5]	吴新辉, 毛政元, 翁谦, 施文灶. 利用基于残差多注意力和ACON激活函数的神经网络提取建筑物[J]. 地球信息科学学报, 2022, 24(4): 792-801.
[6]	林禹, 赵泉华, 李玉. 一种基于深度传递迁移学习的遥感影像分类方法[J]. 地球信息科学学报, 2022, 24(3): 495-507.
[7]	朱昱, 潘耀忠, 张杜娟. 基于深度卷积网络和分水岭分割的耕地地块识别方法[J]. 地球信息科学学报, 2022, 24(12): 2389-2403.
[8]	刘亚坤, 刘会云, 李永强, 赵上斌, 杨亚伦. 基于多源激光点云融合的建筑物BIM建模[J]. 地球信息科学学报, 2021, 23(5): 763-772.
[9]	许泽宇, 沈占锋, 李杨, 柯映明, 李硕, 王浩宇, 焦淑慧. 结合模糊度和形态学指数约束的深度学习建筑物提取[J]. 地球信息科学学报, 2021, 23(5): 918-927.
[10]	唐璎, 刘正军, 杨懿, 顾海燕, 杨树文. 基于特征增强和ELU的神经网络建筑物提取研究[J]. 地球信息科学学报, 2021, 23(4): 692-709.
[11]	李传林, 黄风华, 胡威, 曾江超. 基于Res_AttentionUnet的高分辨率遥感影像建筑物提取方法[J]. 地球信息科学学报, 2021, 23(12): 2232-2243.
[12]	徐佳伟, 刘伟, 单浩宇, 史嘉诚, 李二珠, 张连蓬, 李行. 基于PRCUnet的高分遥感影像建筑物提取[J]. 地球信息科学学报, 2021, 23(10): 1838-1849.
[13]	刘浩, 骆剑承, 黄波, 杨海平, 胡晓东, 徐楠, 夏列钢. 基于特征压缩激活Unet网络的建筑物提取[J]. 地球信息科学学报, 2019, 21(11): 1779-1789.
[14]	邵磊, 董广军, 于英, 姚强强, 张阿龙. 车载激光扫描数据中建筑物立面快速提取[J]. 地球信息科学学报, 2018, 20(4): 462-470.
[15]	陈亭, 祝善友, 张桂欣, 高玚. 高分辨率遥感影像阴影与立体像对提取建筑物高度比较研究[J]. 地球信息科学学报, 2016, 18(9): 1267-1275.