3D Point Cloud Recognition Based on a Multi-View Convolutional Neural Network.
3D Point Cloud Recognition Based on a Multi-View Convolutional Neural Network.
复制标题
DOI：
10.3390/s18113681
复制
发表时间：
2018-10-29
期刊：
影响因子：
--
通讯作者：
Zheng Q
中科院分区：
文献类型：
--
作者：
Zhang L;Sun J;Zheng Q
三维（3D）激光雷达（光探测和测距）点云的识别是点云处理中的一个重要问题。传统的点云识别采用的是整个物体的三维点云。然而，激光雷达数据是激光雷达在一定视场角度内扫描物体获得的二维半（2.5D）点云（每个2.5D点云来自一个视图）的集合。为了解决这一问题，我们首先提出了一种用多视角的2.5D点云来表示3D点云的新方法，然后基于点云库（PCL）生成多视角的2.5D点云数据。随后，我们设计了一个基于多视图卷积神经网络的有效识别模型。该模型直接作用于来自所有视图的原始2.5D点云，并通过视图融合网络对来自所有视图的特征进行融合，学习得到全局特征描述符。实践证明，该方法在不需要对点云进行三维重建和预处理的情况下，可以获得较好的识别性能。综上所述，本文能够有效地解决激光雷达点云的识别问题，具有重要的实用价值。
The recognition of three-dimensional (3D) lidar (light detection and ranging) point clouds remains a significant issue in point cloud processing. Traditional point cloud recognition employs the 3D point clouds from the whole object. Nevertheless, the lidar data is a collection of two-and-a-half-dimensional (2.5D) point clouds (each 2.5D point cloud comes from a single view) obtained by scanning the object within a certain field angle by lidar. To deal with this problem, we initially propose a novel representation which expresses 3D point clouds using 2.5D point clouds from multiple views and then we generate multi-view 2.5D point cloud data based on the Point Cloud Library (PCL). Subsequently, we design an effective recognition model based on a multi-view convolutional neural network. The model directly acts on the raw 2.5D point clouds from all views and learns to get a global feature descriptor by fusing the features from all views by the view fusion network. It has been proved that our approach can achieve an excellent recognition performance without any requirement for three-dimensional reconstruction and the preprocessing of point clouds. In conclusion, this paper can effectively solve the recognition problem of lidar point clouds and provide vital practical value.
登录
查看更多内容
DOI：
10.3390/s150921931
发表时间：
2015-08-31
期刊：
Sensors (Basel, Switzerland)
影响因子：
--
作者：
Liu J;Liang H;Wang Z;Chen X
通讯作者：
Chen X
影响因子：
--
作者：
Prokhorov, Danil
通讯作者：
Prokhorov, Danil
影响因子：
3.9
作者：
Shi, Baoguang;Bai, Song;Bai, Xiang
通讯作者：
Bai, Xiang
影响因子：
14.9
作者：
Hinton, Geoffrey;Deng, Li;Kingsbury, Brian
通讯作者：
Kingsbury, Brian
影响因子：
2.5
作者：
Sfikas, Konstantinos;Pratikakis, Ioannis;Theoharis, Theoharis
通讯作者：
Theoharis, Theoharis