3DmFV: Three-Dimensional Point Cloud Classification in Real-Time Using Convolutional Neural Networks
3DmFV: Three-Dimensional Point Cloud Classification in Real-Time Using Convolutional Neural Networks
复制标题
DOI：
10.1109/lra.2018.2850061
复制
发表时间：
2018-10-01
影响因子：
5.2
通讯作者：
Fischer, Anath
中科院分区：
文献类型：
--
作者：
Ben-Shabat, Yizhak;Lindenbaum, Michael;Fischer, Anath
现代机器人系统通常配备直接三维（3-D）数据采集设备，例如激光雷达，它提供了丰富的3-D点云表示周围环境。这种表示通常用于避障和映射。在这里，我们提出了一种新的方法，将点云用于另一种关键的机器人能力，即对环境的语义理解（即对象分类）。卷积神经网络（cnn）在二维图像的目标分类中表现非常好，但不容易扩展到三维点云分析。由于点云的不规则格式和不同数量的点，这不是直截了当的。将点云数据转换为3-D体素网格的常见解决方案需要解决严重的准确性与内存大小之间的权衡。在这封信中，我们提出了一种新颖的，直观可解释的3-D点云表示，称为3-D修改费雪向量。我们的表示是混合的，因为它结合了粗糙的离散网格结构和连续的广义费雪向量。使用网格使我们能够设计一种新的CNN架构，用于实时点云分类。在一系列性能分析实验中，我们展示了在具有挑战性的基准数据集上具有竞争力的结果，甚至比最先进的结果更好，同时保持了对各种数据损坏的鲁棒性。
Modern robotic systems are often equipped with a direct three-dimensional (3-D) data acquisition device, e.g., LiDAR, which provides a rich 3-D point cloud representation of the surroundings. This representation is commonly used for obstacle avoidance and mapping. Here, we propose a new approach for using point clouds for another critical robotic capability, semantic understanding of the environment (i.e., object classification). Convolutional neural networks (CNNs), that perform extremely well for object classification in 2-D images, are not easily extendible to 3-D point clouds analysis. It is not straightforward due to point clouds' irregular format and a varying number of points. The common solution of transforming the point cloud data into a 3-D voxel grid needs to address severe accuracy versus memory size tradeoffs. In this letter, we propose a novel, intuitively interpretable, 3-D point cloud representation called 3-D modified Fisher vectors. Our representation is hybrid as it combines a coarse discrete grid structure with continuous generalized Fisher vectors. Using the grid enables us to design a new CNN architecture for real-time point cloud classification. In a series of performance analysis experiments, we demonstrate competitive results or even better than state of the art on challenging benchmark datasets while maintaining robustness to various data corruptions.