Method of building extraction from UAV oblique photography point cloud based on cloth simulation

doi:10.13474/j.cnki.11-2246.2020.0327

Abstract

Abstract: Inspired by the idea of cloth simulation filtering, this paper presents a new method of building extraction from dense matching point cloud based on UAV oblique photography. The method introduces cloth simulation to identify the top of the building as the first step. By simulating the falling process of cloth, the function between cloth and corresponding dense matching point cloud is analyzed, and the position where cloth stays after gravity falling is determined as the building top. And then buildings are distinguished by the density clustering algorithm so as to realize the monomer extraction of the building top surface. The experimental results show that the method can achieve better results and provide a new idea for building extraction from dense matching point cloud based on UAV oblique photography.

Key words: UAV based oblique photography, dense matching point cloud, cloth simulation, density clustering, building extraction

CLC Number:

WANG Guo, WANG Qiang, LIU Shaotang, YANG Fuqin, ZHAO Guangxing, YANG Bin. Method of building extraction from UAV oblique photography point cloud based on cloth simulation[J]. Bulletin of Surveying and Mapping, 2020, 0(10): 97-100.

References

[1] 桑文刚,李娜,韩峰,等.小区域消费级无人机倾斜摄影像控点布设及建模精度研究[J].测绘通报,2019(10):93-96.
[2] 王果,蒋瑞波,肖海红,等.基于无人机倾斜摄影的露天矿边坡三维重建[J].中国矿业,2017,26(4):158-161.
[3] 杨必胜,董震.点云智能研究进展与趋势[J].测绘学报,2019,48(12):1575-1585.
[4] 任诚,高利敏,冯耀楼,等.基于无人机倾斜摄影的建筑物三维建模尝试[J].测绘通报,2019(2):161-164.
[5] DAHLKE D,LINKIEWICZ M.Comparison between two generic 3D building reconstruction algorithms:point cloud based vs. image processing based[C]//International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Prague:International Society of Photogrammetry and Remote Sensing,2016.
[6] 冯帅.影像匹配点云与机载激光点云的比较[J].地理空间信息,2014,12(6):82-83.
[7] MALTEZOS E,KYRKOU A,IOANNIDIS C.LiDAR vs dense image matching point clouds in complex urban scenes[C]//Fourth International Conference on Remote Sensing and Geoinformation of the Environment. Paphos:Cyprus Remote Sensing Society,2016.
[8] 闫利,魏峰.利用密集匹配点云的建筑单体提取算法研究[J].中国激光,2018,45(7):270-277.
[9] AWRANGJEB M,LU G,FRASER C. Automatic building extraction from LiDAR data covering complex urban scenes[C]//International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Zurich:International Society of Photogrammetry and Remote Sensing,2014.
[10] NOVACHEVA A. Building roof reconstruction from LiDAR data and aerial images through plane extraction and color edge detection[C]//International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Beijing:International Society of Photogrammetry and Remote Sensing,2008.
[11] 程效军,程小龙,胡敏捷,等.融合航空影像和LiDAR点云的建筑物探测及轮廓提取[J].中国激光,2016,43(5):253-261.
[12] 赵宗泽,张永军.基于植被指数限制分水岭算法的机载激光点云建筑物提取[J].光学学报,2016,36(10):503-511.
[13] LI M L, NAN L L, SMITH N, et al. Reconstructing building mass models from UAV images[J]. Computers & Graphics, 2016, 54(2):84-93.
[14] ZHANG W M, QI J B, WAN P, et al. An easy-to-use airborne LiDAR data filtering method based on cloth simulation[J]. Remote Sensing, 2016, 8(6):501.
[15] 曲金博,王岩,赵琪.DBSCAN聚类和改进的双边滤波算法在点云去噪中的应用[J].测绘通报,2019(11):89-92.
[16] 袁德宝,王炳灵,闫瑜,等.室内位置轨迹的聚类与可视化[J].测绘通报,2019(5):21-24.
[17] 王果,谢瑞,肖海红,等. 无人机倾斜摄影技术支持下的校园三维模型构建[J].河南工程学院学报(自然科学版), 2017, 29(1):44-47.
[18] LIN Zongjian, XIE Feifei, SU Guozhong. Accuracy analysis of low altitude photogrammetry with wide-angle camera[J]. Journal of Geodesy and Geoinformation Science, 2018, 1(1):30-38.