基于深度学习的机载点云屋顶平面提取算法

李婕; 李青清; 李礼; 刘钊; 沈阳; 涂静敏; 李婕; 李青清; 李礼; 刘钊; 沈阳; 涂静敏

doi:10.7510/jgjs.issn.1001-3806.2024.05.003

[1]

杨必胜, 梁福逊, 黄荣刚. 3维激光扫描点云数据处理研究进展、挑战与趋势[J]. 测绘学报, 2017, 46(10): 1509-1516.YANG B Sh, LIANG F X, HUANG R G. Progress, challenges and trends in 3D laser scanning point cloud data processing research[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(10): 1509-1516(in Chinese).

[2]

董保根. 机载LiDAR点云与遥感影像融合的地物分类技术研究[D]. 郑州: 解放军信息工程大学, 2013.DONG B G. Research on feature classification technology by fusion of airborne LiDAR point cloud and remote sensing images[D]. Zhengzhou: Information Engineering University, 2013(in Chinese).

[3]

史建青. 机载LiDAR在省级基础测绘中若干关键技术研究[D]. 武汉: 武汉大学, 2014.SHI J Q. Research on several key technologies of airborne LiDAR in provincial basic surveying and mapping[D]. Wuhan: Wuhan University, 2014(in Chinese).

[4]

何正斌. 机载LiDAR技术用于数字地面的应用研究[D]. 西安: 长安大学, 2008.HE Zh B. An applied study of airborne LiDAR technology for digital terrestrial applications[D]. Xi'an: Chang'an University, 2008(in Chinese).

[5]

赵传, 张保明, 陈小卫, 等. 一种基于LiDAR点云的建筑物提取方法[J]. 测绘通报, 2017(2): 35-39.ZHAO Ch, ZHANG B M, CHEN X W, et al. A building extraction method based on LiDAR point cloud[J]. Bulletin of Surveying and Mapping, 2017(2): 35-39(in Chinese).

[6]

陈焱明. 基于机载与车载LiDAR数据的建筑物模型多视3维重建研究[D]. 南京: 南京大学, 2015.CHEN Y M. Multi-view 3D reconstruction of building models based on airborne and vehicle-mounted LiDAR data[D]. Nanjing: Nanjing University, 2015(in Chinese).

[7]

曾齐红. 机载激光雷达点云数据处理与建筑物3维重建[D]. 上海: 上海大学, 2009.ZENG Q H. Airborne LiDAR point cloud data processing and 3D reconstruction of buildings[D]. Shanghai: Shanghai University, 2009(in Chinese).

[8]

李峰, 吴燕雄, 卫爱霞, 等. 机载激光雷达3维建筑物模型重建的研究进展[J]. 激光技术, 2015, 39(1): 23-27.LI F, WU Y X, WEI A X, et al. Research progress in airborne LiDAR 3D building model reconstruction[J]. Laser Technology, 2015, 39(1): 23-27(in Chinese).

[9]

卢维欣, 万幼川, 何培培, 等. 大场景内建筑物点云提取及平面分割算法[J]. 中国激光, 2015, 42(9): 0914004.LU W X, WAN Y Ch, HE P P, et al. Point cloud extraction and planar segmentation algorithm for buildings in large scenes[J]. Chinese Journal of Lasers, 2015, 42(9): 0914004(in Chinese).

[10]

XU Y, TONG X, STILLA U. Voxel-based representation of 3D point clouds: Methods, applications, and its potential use in the construction industry[J]. Automation in Construction, 2021, 126(6): 1-26.

[11]

王雯, 任小玲, 陈逍遥. 一种改进的区域增长彩色3D点云分割算法[J]. 国外电子测量技术, 2018, 37(11): 10-14.WANG W, REN X L, CHEN X Y. An improved algorithm for segmentation of region-growing color 3D point clouds[J]. Foreign Electronic Measurement Technology, 2018, 37(11): 10-14(in Chinese).

[12]

朱军桃, 王雷, 赵传, 等. 基于区域生长算法的复杂建筑物屋顶点云分割[J]. 国土资源遥感, 2019, 31(4): 20-25.ZHU J T, WANG L, ZHAO Ch, et al. Complex building roof point cloud segmentation based on region growing algorithm[J]. Remote Sensing for Land & Resources, 2019, 31(4): 20-25(in Chinese).

[13]

BALLARD D H. Generalizing the Hough transform to detect arbitrary shape[J]. Pattern Recognition, 1981, 13(2): 111-122.

[14]

FISHLER M A, BOLLES R C. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6): 381-395.

[15]

XU L, OJA E. Randomized Hough transform (RHT): Basic mechanisms, algorithms, and computational complexities[J]. CVGIP: Image Understanding, 1993, 57(2): 131-154.

[16]

KIRYATI N, ELDAR Y, BRUCKSTEIN A M. A probabilistic Hough transform[J]. Pattern Recognition, 1991, 24(4): 303-316.

[17]

YLA-JAASKI A, KIRYATI N. Adaptive termination of voting in the probabilistic circular Hough transform[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1994, 16(9): 911-915.

[18]

康传利, 兰猗令, 王宁, 等. 一种结合SIFT与3D Hough变换的建筑物屋顶点云分割方法[J]. 遥感信息, 2022, 37(5): 31-37.KANG Ch L, LAN Y L, WANG N, et al. A combined SIFT and 3D Hough transform for segmentation of building roof point clouds[J]. Remote Sensing Information, 2022, 37(5): 31-37(in Chinese).

[19]

夏金泽, 孙浩铭, 胡盛辉, 等. 基于图像信息约束的3维激光点云聚类方法[J]. 光电工程, 2023, 50(2): 220148.XIA J Z, SUN H M, HU Sh H, et al. 3D laser point cloud clustering method based on image information constraints[J]. Opto-Electronic Engineering, 2023, 50(2): 220148(in Chinese).

[20]

XU B, JIANG W Sh, SHAN J, et al. Investigation on the weighted RANSAC approaches for building roof plane segmentation from LiDAR point clouds[J]. Remote Sensing, 2015, 8(1): 01005.

[21]

LI Z, SHAN J. RANSAC-based multi primitive building reconstruction from 3D point clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 185(3): 247-260.

[22]

巩育江, 庞亚军, 王汞, 等。基于几何特征的点云分割算法研究进展[J]. 激光技术, 2022, 46(3): 326-336.GONG Y J, PANG Y J, WANG G, et al. Research progress on point cloud segmentation algorithm based on geometric features[J]. Laser Technology, 2022, 46(3): 326-336(in Chinese).

[23]

赵传, 张保明, 陈小卫, 等. 一种利用点云邻域信息的建筑物屋顶面高精度自动提取方法[J]. 测绘学报, 2017, 46(9): 1123-1134.ZHAO Ch, ZHANG B M, CHEN X W, et al. A high-precision automatic extraction method of building roof surface using point cloud neighborhood information[J]. Acta Geodaetica et Cartographica Sinica, 2017, 46(9): 1123-1134(in Chinese).

[24]

CHEN H, LIANG M, LIU W, et al. An approach to boundary detection for 3D point clouds based on DBSCAN clustering[J]. Pattern Recognition, 2022, 124(4): 108431.

[25]

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. Honolulu, USA: IEEE, 2017: 652-660.

[26]

QI C R, YI L, SU H, et al. PointNet + +: Deep hierarchical feature learning on point sets in a metric space[J]. Advances in Neural Information Processing Systems, 2017, 30(12): 5105-5114.

[27]

WU W, QI Z, FUXIN L. Pointconv: Deep convolutional networks on 3d point clouds[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019: 9621-9630.

[28]

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. Seattle, WA, USA: IEEE, 2020: 11108-11117.

[29]

YI L, ZHAO W, WANG H, et al. Gspn: Generative shape proposal network for 3D instance segmentation in point cloud[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019: 3947-3956.

[30]

WANG X, LIU S, SHEN X, et al. Associatively segmenting instances and semantics in point clouds[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019: 4096- 4105.

[31]

PHAM Q H, NGUYEN T, HUA B S, et al. JSIS3D: Joint semantic-instance segmentation of 3D point clouds with multi-task pointwise networks and multi-value conditional random fields[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019: 8827-8836.

[32]

JIANG L, ZHAO H, SHI S, et al. Pointgroup: Dual-set point grouping for 3D instance segmentation[C]// Proceedings of the IEEE/CVF conference on computer vision and Pattern recognition. Seattle, USA: IEEE, 2020: 4867- 4876.

[33]

MAHMUD J, PRICE T, BAPAT A, et al. Boundary-aware 3D building reconstruction from a single overhead image[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, USA: IEEE, 2020: 441- 451.

[34]

ZHANG C Q, FAN H C. An improved multi-task pointwise network for segmentation of building roofs in airborne laser scanning point clouds[J]. The Photogrammetric Record, 2022, 37(179): 260-284.

[35]

WICHMANN A, AGOUB A, KADA M. RoofN3D: Deep learning training data for 3D building reconstruction[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2018, 42(5): 1191-1198.

[36]

LI L, SONG N, SUN F, et al. Point2Roof: End-to-end 3D building roof modeling from airborne LiDAR point clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 193(11): 17-28.

[37]

REN M, ZEMEL R S. End-to-end instance segmentation with recurrent attention[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017: 6656-6664.

[38]

LIU S, JIA J, FIDLER S, et al. SGN: Sequential grouping networks for instance segmentation[C]// Proceedings of the IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017: 3496-3504.

[39]

ZHUO W, SALZMANN M, HE X, et al. Indoor scene parsing with instance segmentation, semantic labeling and support relationship inference[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE, 2017: 5429-5437.

[40]

de BRABANDERE B, NEVEN D, van GOOL L. Semantic instance segmentation with a discriminative loss function[J/OL]. (2017-08-08)[2023-08-16]. https://arxiv.org/abs/1708.02551.

[41]

SCHNABEL R, WAHL R, KLEIN R. Efficient RANSAC for point cloud shape detection[C]// Computer Graphics Forum. Oxford, UK: Blackwell Publishing Ltd, 2007: 214-226.

[42]

LAFARGE F, MALLET C. Creating large-scale city models from 3D-point clouds: A robust approach with hybrid representation[J]. International Journal of Computer Vision, 2012, 99(2): 69-85.