Please wait a minute...
 
Remote Sensing for Natural Resources    2022, Vol. 34 Issue (4) : 113-121     DOI: 10.6046/zrzyyg.2021402
|
RandLA-Net-based detection of urban building change using airborne LiDAR point clouds
MENG Congtang1(), ZHAO Yindi1(), HAN Wenquan2, HE Chenyang1, CHEN Xiqiu2
1. School of Environment Science and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, China
2. Nanjing Insititute of Surveying, Mapping and Geotechnical Investigation Co. Ltd., Nanjing 210019, China
Download: PDF(9633 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

Using remote sensing to detect changes in urban buildings can obtain the change information of building coverage quickly and accurately. However, it is difficult to detect 3D changes quickly and accurately based on image data alone. Moreover, conventional point cloud-based methods have low automation and poor precision. To address these problems, this study used the airborne LiDAR point clouds and employed the RandLA-Net’s point cloud semantic segmentation method to improve the accuracy and automation of change detection. Meanwhile, the failure in differentiating two-period data due to point cloud disorder was overcome through point cloud projection. The standard RandLA-Net method, with the location and color information of points as features, is mainly used for semantic segmentation of street-level point clouds. In this study, urban large-scale airborne point clouds combined with the inherent reflection intensity and the spectral information of point clouds given by images were used to explore the influence of different feature information on the precision of the results. Furthermore, it was found that in addition to the point cloud intensity and spectral features, the coordinate information of points is equally important and can be converted into relative coordinates to significantly improve the result precision. The experimental findings show that the results obtained using RandLA-Net are significantly better than those using conventional methods for building extraction and change detection. This study also verified the feasibility of using deep learning methods to process LiDAR data for building extraction and change detection, which can realize reliable 3D building change detection.
Keywords airborne LiDAR      point cloud      change detection      3D semantic segmentation     
ZTFLH:  TP79  
Issue Date: 27 December 2022
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Congtang MENG
Yindi ZHAO
Wenquan HAN
Chenyang HE
Xiqiu CHEN
Cite this article:   
Congtang MENG,Yindi ZHAO,Wenquan HAN, et al. RandLA-Net-based detection of urban building change using airborne LiDAR point clouds[J]. Remote Sensing for Natural Resources, 2022, 34(4): 113-121.
URL:  
https://www.gtzyyg.com/EN/10.6046/zrzyyg.2021402     OR     https://www.gtzyyg.com/EN/Y2022/V34/I4/113
Fig.1  Examples of LiDAR point cloud data
Fig.2  Point cloud structure after sampling
Fig.3  Examples of point cloud dataset
Fig.4  RandLA-Net overall structure
Fig.5  LFA module structure
Tab.1  Point cloud building extraction results in 2017
Tab.2  Point cloud building extraction results in 2019
Fig.6  Low buildings and trees
年份 方法 准确率/% 精准率/% 召回率/% F1分数 Kappa系数
2017年 RandLA-Net IRGB C 98.52 88.21 97.45 92.60 0.917 8
RandLA-Net RGB C 98.49 88.83 96.45 92.48 0.916 4
RandLA-Net I C 98.32 88.15 95.45 91.65 0.907 2
RandLA-Net I 97.27 92.59 83.23 87.66 0.861 3
ENVI LiDAR 91.91 24.24 94.24 38.39 0.358 1
TerraScan 95.76 73.58 83.96 78.43 0.760 9
DSM高程阈值法 93.55 88.61 63.85 74.22 0.706 4
2019年 RandLA-Net IRGB C 98.54 86.10 97.69 91.53 0.907 3
RandLA-Net RGB C 98.94 90.30 97.93 93.96 0.933 7
RandLA-Net I C 98.59 86.67 97.72 91.86 0.910 9
RandLA-Net I 94.26 38.24 97.94 55.00 0.525 7
ENVI LiDAR 97.93 86.17 90.76 88.41 0.872 7
TerraScan 94.83 72.68 71.46 72.06 0.692 2
DSM高程阈值法 97.29 77.23 91.93 83.94 0.824 7
Tab.3  Accuracy comparison of the building extraction method
Tab.4  Change detection results
方法 变化
类型		 准确
率/%		 精准
率/%		 召回
率/%		 F1
分数		 Kappa
系数
RandLA-
Net IRBG C		 增高 97.22 70.40 97.65 81.57 0.856 6
降低 87.23 99.71 93.05
新建 87.42 92.07 89.68
拆除 77.74 79.05 78.39
RandLA-
Net RBG C		 增高 97.61 82.23 97.71 89.30 0.876 9
降低 88.22 98.52 93.09
新建 87.73 93.24 90.40
拆除 78.91 84.54 81.63
RandLA-
Net I C		 增高 97.10 85.62 98.94 91.80 0.849 2
降低 91.63 99.54 95.42
新建 77.33 90.63 83.45
拆除 78.20 82.85 80.46
RandLA-
Net I		 增高 91.77 31.10 96.60 47.05 0.606 0
降低 36.72 100.00 53.72
新建 38.85 94.24 55.02
拆除 86.21 42.94 57.33
ENVI
LiDAR		 增高 90.46 11.05 64.22 18.86 0.502 4
降低 9.61 69.44 16.88
新建 79.55 35.58 49.17
拆除 30.27 88.06 45.05
TerraScan 增高 91.67 33.31 80.18 47.07 0.628 9
降低 21.82 73.95 33.70
新建 67.19 36.26 47.10
拆除 85.90 65.65 74.42
DSM高程阈值法 增高 91.65 84.08 88.39 86.18 0.642 4
降低 71.99 100.00 83.71
新建 63.90 81.50 71.63
拆除 83.83 41.62 55.62
Tab.5  Accuracy comparison of building change detection results
[1] Murakami H, Nakagawa K, Hasegawa H, et al. Change detection of buildings using an airborne laser scanner[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 1999, 54(2):148-152.
doi: 10.1016/S0924-2716(99)00006-4 url: https://linkinghub.elsevier.com/retrieve/pii/S0924271699000064
[2] Vu T, Matsuoka M, Yamazaki F. LiDAR-based change detection of buildings in dense urban areas[C]// IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2004:3413-3416.
[3] Pang S, Hu X, Wang Z, et al. Object-based analysis of airborne LiDAR data for building change detection[J]. Remote Sensing, 2014, 6(11):10733-10749.
doi: 10.3390/rs61110733 url: http://www.mdpi.com/2072-4292/6/11/10733
[4] Pirasteh S, Rashidi P, Rastiveis H, et al. Developing an algorithm for buildings extraction and determining changes from airborne LiDAR,and comparing with R-CNN method from drone images[J]. Remote Sensing, 2019, 11(11):1272.
doi: 10.3390/rs11111272 url: https://www.mdpi.com/2072-4292/11/11/1272
[5] 曾静静, 张晓刚, 王刚. 基于LiDAR点云的城区地表变化检测[J]. 城市勘测, 2021(2):92-95.
[5] Zeng J J, Zhang X G, Wang G. Urban land surface change detection based on LiDAR point cloud[J]. Urban Geotechnical Investigation and Surveying, 2021(2):92-95.
[6] Matikainen L, Hyyppä J, Ahokas E, et al. Automatic detection of buildings and changes in buildings for updating of maps[J]. Remote Sensing, 2010, 2(5):1217-1248.
doi: 10.3390/rs2051217 url: http://www.mdpi.com/2072-4292/2/5/1217
[7] Malpica J A, Alonso M C. Urban changes with satellite imagery and LiDAR data[J]. International Archives of the Photogrammetry,Remote Sensing and Spatial Information Science, 2010, 38(8):853-858.
[8] Du S, Zhang Y, Qin R, et al. Building change detection using old aerial images and new LiDAR data[J]. Remote Sensing, 2016, 8(12):1030.
doi: 10.3390/rs8121030 url: http://www.mdpi.com/2072-4292/8/12/1030
[9] Shelhamer E, Long J, Darrell T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(4):640-651.
doi: 10.1109/TPAMI.2016.2572683 pmid: 27244717
[10] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J/OL]. arXiv, 2014(2015-04-10)[2022-10/15]. https://arxiv.org/abs/1409.1556 .
url: https://arxiv.org/abs/1409.1556
[11] 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
[12] He K, Zhang X, Ren S, et al. Deep residual learning for image reco-gnition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016:770-778.
[13] Ronneberger O, Fischer P, Brox T. U-Net:Convolutional networks for biomedical image segmentation[C]// International Conference on Medical Image Computing and Computer-Assisted Intervention.Springer,Cham, 2015:234-241.
[14] Ren S, He K, Girshick R, et al. Faster R-CNN:Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(6):1137-1149.
doi: 10.1109/TPAMI.2016.2577031 url: http://ieeexplore.ieee.org/document/7485869/
[15] Lin T Y, Dollár P, Girshick R, et al. Feature pyramid networks for object detection[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017:2117-2125.
[16] 谢奇芳, 姚国清, 张猛. 基于Faster R-CNN的高分辨率图像目标检测技术[J]. 国土资源遥感, 2019, 31(2):38-43.doi:10.6046/gtzyyg.2019.02.06.
doi: 10.6046/gtzyyg.2019.02.06
[16] Xie Q F, Yao G Q, Zhang M. Research on high resolution image object detection technology based on Faster R-CNN[J]. Remote Sensing for Land and Resources, 2019, 31(2):38-43.doi:10.6046/gtzyyg.2019.02.06.
doi: 10.6046/gtzyyg.2019.02.06
[17] 武宇, 张俊, 李屹旭, 等. 基于改进U-Net的建筑物集群识别研究[J]. 国土资源遥感, 2021, 33(2):48-54.doi:10.6046/gtzyyg.2020278.
doi: 10.6046/gtzyyg.2020278
[17] Wu Y, Zhang J, Li Y X, et al. Research on building cluster identification based on improved U-Net[J]. Remote Sensing for Land and Resources, 2021, 33(2):48-54.doi:10.6046/gtzyyg.2020278.
doi: 10.6046/gtzyyg.2020278
[18] 卢麒, 秦军, 姚雪东, 等. 基于多层次感知网络的GF-2遥感影像建筑物提取[J]. 国土资源遥感, 2021, 33(2):75-84.doi:10.6046/gtzyyg.2020289.
doi: 10.6046/gtzyyg.2020289
[18] Lu Q, Qin J, Yao X D, et al. Buildings extraction of GF-2 remote sensing image based on multi-layer perception network[J]. Remote Sensing for Land and Resources, 2021, 33(2):75-84.doi:10.6046/gtzyyg.2020289.
doi: 10.6046/gtzyyg.2020289
[19] 刘文雅, 岳安志, 季钰, 等. 基于DeepLabv3+语义分割模型的GF-2影像城市绿地提取[J]. 国土资源遥感, 2020, 32(2):120-129.doi:10.6046/gtzyyg.2020.02.16.
doi: 10.6046/gtzyyg.2020.02.16
[19] Liu W Y, Yue A Z, Ji Y, et al. Urban green space extraction from GF-2 remote sensing image based on DeepLabv3+ semantic segmentation model[J]. Remote Sensing for Land and Resources, 2020, 32(2):120-129.doi:10.6046/gtzyyg.2020.02.16.
doi: 10.6046/gtzyyg.2020.02.16
[20] 安健健, 孟庆岩, 胡蝶, 等. 基于Faster R-CNN的火电厂冷却塔检测及工作状态判定[J]. 国土资源遥感, 2021, 33(2):93-99.doi:10.6046/gtzyyg.2020184.
doi: 10.6046/gtzyyg.2020184
[20] An J J, Meng Q Y, Hu D, et al. The detection and determination of the working state of cooling tower in the thermal power plant based on Faster R-CNN[J]. Remote Sensing for Land and Resources, 2021, 33(2):93-99.doi:10.6046/gtzyyg.2020184.
doi: 10.6046/gtzyyg.2020184
[21] Guo Y, Wang H, Hu Q, et al. Deep learning for 3D point clouds:A survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 43(12):4338-4364.
doi: 10.1109/TPAMI.2020.3005434 url: https://ieeexplore.ieee.org/document/9127813/
[22] Qi C R, Su H, Mo K, et al. Pointnet:Deep learning on point sets for 3D classification and segmentation[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017:652-660.
[23] Wu B, Wan A, Yue X, et al. Squeezeseg:Convolutional neural nets with recurrent CRF for real-time road-object segmentation from 3D LiDAR point cloud[C]// 2018 IEEE International Conference on Robotics and Automation (ICRA), 2018:1887-1893.
[24] Thomas H, Qi C R, Deschaud J E, et al. Kpconv:Flexible and deformable convolution for point clouds[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019:6411-6420.
[25] Hu Q, Yang B, Xie L, et al. RandLA-Net:Efficient semantic segmentation of large-scale point clouds[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020:11108-11117.
[26] Hackel T, Savinov N, Ladicky L, et al. Semantic3d.net:A new large-scale point cloud classification benchmark[J/OL]. arXiv, 2017(2017-04-12)[2022-10/15]. https://arxiv.org/abs/1704.03847 .
url: https://arxiv.org/abs/1704.03847
[1] WANG Liying, MA Xuwei, YOU Ze, WANG Shichao, CAMARA Mahamadou. Spatial-spectral joint classification of airborne multispectral LiDAR point clouds based on the multivariate GMM[J]. Remote Sensing for Natural Resources, 2023, 35(3): 88-96.
[2] CUI Ziwei, XU Wenxue, LIU Yanxiong, GUO Yadong, MENG Xiangqian, JIANG Zhengkun. Current status of the acquisition and processing of airborne laser sounding data[J]. Remote Sensing for Natural Resources, 2023, 35(3): 1-9.
[3] DONG Ting, FU Weiqi, SHAO Pan, GAO Lipeng, WU Changdong. Detection of changes in SAR images based on an improved fully-connected conditional random field[J]. Remote Sensing for Natural Resources, 2023, 35(3): 134-144.
[4] ZHANG Tian, ZHOU Zhongfa, WANG Lingyu, ZHAO Xin, ZHANG Wenhui, ZHANG Shu, WANG Yu. A method for soil roughness measurement based on UAV point cloud data[J]. Remote Sensing for Natural Resources, 2023, 35(1): 115-122.
[5] QIN Le, HE Peng, MA Yuzhong, LIU Jianqiang, YANG Bin. Change detection of satellite time series images based on spatial-temporal-spectral features[J]. Remote Sensing for Natural Resources, 2022, 34(4): 105-112.
[6] HE Peng, YAN Yuyan, WEN Yan, MA Zhigang, JIAO Qisong, GUO Zhaocheng, MO You. Application of the airborne LiDAR technology in the identification of flat landslides and their crack grooves[J]. Remote Sensing for Natural Resources, 2022, 34(4): 307-316.
[7] WU Fang, LI Yu, JIN Dingjian, LI Tianqi, GUO Hua, ZHANG Qijie. Application of 3D information extraction technology of ground obstacles in the flight trajectory planning of UAV airborne geophysical exploration[J]. Remote Sensing for Natural Resources, 2022, 34(1): 286-292.
[8] XUE Bai, WANG Yizhe, LIU Shuhan, YUE Mingyu, WANG Yiying, ZHAO Shihu. Change detection of high-resolution remote sensing images based on Siamese network[J]. Remote Sensing for Natural Resources, 2022, 34(1): 61-66.
[9] PAN Jianping, XU Yongjie, LI Mingming, HU Yong, WANG Chunxiao. Research and development of automatic detection technologies for changes in vegetation regions based on correlation coefficients and feature analysis[J]. Remote Sensing for Natural Resources, 2022, 34(1): 67-75.
[10] LI Yikun, YANG Yang, YANG Shuwen, WANG Zihao. A change vector analysis in posterior probability space combined with fuzzy C-means clustering and a Bayesian network[J]. Remote Sensing for Natural Resources, 2021, 33(4): 82-88.
[11] WANG Yiuzhu, HUANG Liang, CHEN Pengdi, LI Wenguo, YU Xiaona. Change detection of remote sensing images based on the fusion of co-saliency difference images[J]. Remote Sensing for Natural Resources, 2021, 33(3): 89-96.
[12] XU Rui, YU Xiaoyu, ZHANG Chi, YANG Jin, HUANG Yu, PAN Jun. Building change detection method combining Unet and IR-MAD[J]. Remote Sensing for Land & Resources, 2020, 32(4): 90-96.
[13] DIAO Mingguang, LIU Wenjing, LI Jing, LIU Fang, WANG Yanzuo. Dynamic change detection method of vector result data in mine remote sensing monitoring[J]. Remote Sensing for Land & Resources, 2020, 32(3): 240-246.
[14] Peiting LI, Qingzhan ZHAO, Wenzhong TIAN, Yongjian MA. Point cloud simplification method combining K-means++ clustering with UAV LiDAR point cloud normal vectors[J]. Remote Sensing for Land & Resources, 2020, 32(2): 103-110.
[15] Chunsen ZHANG, Rongrong WU, Guojun LI, Weihong CUI, Chenyi FENG. High resolution remote sensing image object change detection based on box-plot method[J]. Remote Sensing for Land & Resources, 2020, 32(2): 19-25.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech