3-D Point Cloud Object Detection Based on Supervoxel Neighborhood With Hough Forest Framework
3-D Point Cloud Object Detection Based on Supervoxel Neighborhood With Hough Forest Framework
复制标题
基于超体素邻域和霍夫森林框架的 3-D 点云目标检测
DOI：
10.1109/jstars.2015.2394803
复制
发表时间：
2015-04-01
影响因子：
5.5
通讯作者：
Li, Jonathan
中科院分区：
文献类型：
--
作者：
Wang, Hanyun;Wang, Cheng;Li, Jonathan
复杂城市环境下三维激光扫描点云目标检测是一个具有挑战性的问题。现有的方法是有限的，他们的鲁棒性复杂的情况下，如闭塞，重叠，旋转或其计算效率。本文提出了一种高计算效率的方法，结合超体素和Hough森林框架，从三维激光扫描点云检测目标。首先，将点云过度分割为空间一致的超体素。每个超体素连同其一阶邻域被分组为一个局部块。所有的局部补丁描述的结构和反射率的功能，然后在训练阶段用于学习一个随机森林分类器，以及检测阶段投票的对象中心的可能位置。其次，引入局部参考系和循环投票策略，实现了目标方位角旋转的不变性。最后，在3-D Hough投票空间的峰值点处检测目标。我们所提出的方法的性能进行评估，对现实世界的点云数据收集的最新的移动的激光扫描系统。实验结果表明，我们提出的方法优于国家的最先进的3-D目标检测方法具有较高的计算效率。
Object detection in three-dimensional (3-D) laser scanning point clouds of complex urban environment is a challenging problem. Existing methods are limited by their robustness to complex situations such as occlusion, overlap, and rotation or by their computational efficiency. This paper proposes a high computationally efficient method integrating supervoxel with Hough forest framework for detecting objects from 3-D laser scanning point clouds. First, a point cloud is over-segmented into spatially consistent supervoxels. Each supervoxel together with its first-order neighborhood is grouped into one local patch. All the local patches are described by both structure and reflectance features, and then used in the training stage for learning a random forest classifier as well as the detection stage to vote for the possible location of the object center. Second, local reference frame and circular voting strategies are introduced to achieve the invariance to the azimuth rotation of objects. Finally, objects are detected at the peak points in 3-D Hough voting space. The performance of our proposed method is evaluated on real-world point cloud data collected by the up-to-date mobile laser scanning system. Experimental results demonstrate that our proposed method outperforms state-of-the-art 3-D object detection methods with high computational efficiency.