Polylidar3D-Fast Polygon Extraction from 3D Data.

Polylidar3D-Fast Polygon Extraction from 3D Data.
复制标题

DOI:
10.3390/s20174819
复制
发表时间:
2020-08-26
期刊:
Sensors (Basel, Switzerland)
影响因子:
--
通讯作者:
Atkins E
Atkins E
中科院分区:
其他
文献类型:
--
作者:
Castagno J;Atkins E

文献摘要

参考文献

被引文献

相似文献

3D 点云捕获的平坦表面通常用于定位、绘图和建模。密集点云处理具有较高的计算和内存成本,因此需要平面(例如多边形)的低维表示。我们提出了 Polylidar3D,一种非凸多边形提取算法,它采用无组织的 3D 点云(例如 LiDAR 数据)、有组织的点云(例如范围图像)或用户提供的网格作为输入。非凸多边形表示环境中的平坦表面,内部切口表示障碍物或孔洞。 Polylidar3D 前端将输入数据转换为半边三角形网格。这种表示形式为后续后端处理提供了通用的抽象级别。 Polylidar3D后端由四个核心算法组成:网格平滑、主平面法线估计、平面段提取以及最后的多边形提取。 Polylidar3D 的速度相当快,在可用时利用了 CPU 多线程和 GPU 加速。我们通过真实数据集展示了 Polylidar3D 的多功能性和速度,包括用于屋顶测绘的航空 LiDAR 点云、用于路面检测的自动驾驶 LiDAR 点云以及用于室内地板/墙壁检测的 RGBD 摄像机。我们还在具有挑战性的平面分割基准数据集上评估 Polylidar3D。结果始终显示出出色的速度和准确性。
Flat surfaces captured by 3D point clouds are often used for localization, mapping, and modeling. Dense point cloud processing has high computation and memory costs making low-dimensional representations of flat surfaces such as polygons desirable. We present Polylidar3D, a non-convex polygon extraction algorithm which takes as input unorganized 3D point clouds (e.g., LiDAR data), organized point clouds (e.g., range images), or user-provided meshes. Non-convex polygons represent flat surfaces in an environment with interior cutouts representing obstacles or holes. The Polylidar3D front-end transforms input data into a half-edge triangular mesh. This representation provides a common level of abstraction for subsequent back-end processing. The Polylidar3D back-end is composed of four core algorithms: mesh smoothing, dominant plane normal estimation, planar segment extraction, and finally polygon extraction. Polylidar3D is shown to be quite fast, making use of CPU multi-threading and GPU acceleration when available. We demonstrate Polylidar3D’s versatility and speed with real-world datasets including aerial LiDAR point clouds for rooftop mapping, autonomous driving LiDAR point clouds for road surface detection, and RGBD cameras for indoor floor/wall detection. We also evaluate Polylidar3D on a challenging planar segmentation benchmark dataset. Results consistently show excellent speed and accuracy.
DOI: 10.1109/tit.1983.1056714
发表时间: 1983-01-01
影响因子: 2.5
作者:
EDELSBRUNNER, H;KIRKPATRICK, DG;SEIDEL, R
通讯作者: SEIDEL, R
DOI: 10.1080/01431161.2017.1302112
发表时间: 2017-01-01
影响因子: 3.4
作者:
Cao, Rujun;Zhang, Yongjun;Zhao, Zongze
通讯作者: Zhao, Zongze
DOI: 10.1109/lra.2020.3002212
发表时间: 2020-07-01
影响因子: 5.2
作者:
Castagno, Jeremy;Atkins, Ella
通讯作者: Atkins, Ella
DOI: 10.1109/99.660313
发表时间: 1998-01-01
期刊: IEEE COMPUTATIONAL SCIENCE & ENGINEERING
影响因子: --
作者:
Dagum, L;Menon, R
通讯作者: Menon, R
DOI: 10.1109/2945.817351
发表时间: 1999-10-01
影响因子: 5.2
作者:
Bernardini, F;Mittleman, J;Taubin, G
通讯作者: Taubin, G