Convolutional neural networks (CNNs) for 3-D data analyses require a large size of memory and fast computation power, making real-time applications difficult. This article proposes a novel OctreeNet (a sparse 3-D CNN) to analyze the sparse 3-D laser scanning data gathered from outdoor environments. It uses a collection of shallow octrees for 3-D scene representation to reduce the memory footprint of 3-D-CNNs and performs point cloud classification on every single octree. Furthermore, the smallest non-trivial and non-overlapped kernel (SNNK) implements convolution directly on the octree structure to reduce dense 3-D convolutions to matrix operations at sparse locations. The proposed neural network implements a depth-first search algorithm for real-time predictions. A conditional random field model is utilized for learning global semantic relationships and refining point cloud classification results. Two public data sets (Semantic3D.net and Oakland) are selected to test the classification performance in outdoor scenes with different spatial sparsity. The experiments and benchmark test results show that the proposed approach can be effectively used in real-time 3-D laser data analyses. Note to Practitioners-This article was motivated by the limitations of existing deep learning technologies for analyzing 3-D laser scanning data. This technology enables robots to infer what the surroundings are, which is closely linked to semantic mapping and navigation tasks. Previous deep neural networks have seldom been used in robotic systems since they require a large amount of memory and fast computation power to apply dense 3-D operations. This article presents a sparse 3-D-Convolutional neural network (CNN) for real-time point cloud classification by exploiting the sparsity of 3-D data. This framework requires no GPUs. The practicality of the proposed method is verified on data sets gathered from different platforms and sensors. The proposed network can be adopted for other clas...

中文翻译：

---

OctreeNet：一种用于实时 3D 室外场景分析的新型稀疏 3D 卷积神经网络


用于 3D 数据分析的卷积神经网络 (CNN) 需要大容量内存和快速计算能力，这使得实时应用变得困难。本文提出了一种新颖的 OctreeNet（稀疏 3-D CNN）来分析从室外环境收集的稀疏 3-D 激光扫描数据。它使用浅八叉树集合进行 3D 场景表示，以减少 3D-CNN 的内存占用，并对每个八叉树执行点云分类。此外，最小的非平凡非重叠内核（SNNK）直接在八叉树结构上实现卷积，以将密集的 3D 卷积减少为稀疏位置的矩阵运算。所提出的神经网络实现了用于实时预测的深度优先搜索算法。利用条件随机场模型来学习全局语义关系并细化点云分类结果。选择两个公共数据集（Semantic3D.net和Oakland）来测试不同空间稀疏度的室外场景中的分类性能。实验和基准测试结果表明，所提出的方法可以有效地用于实时3D激光数据分析。从业者注意事项 - 本文的动机是现有深度学习技术在分析 3D 激光扫描数据方面的局限性。这项技术使机器人能够推断周围环境，这与语义映射和导航任务密切相关。以前的深度神经网络很少用于机器人系统，因为它们需要大量内存和快速计算能力来应用密集的 3D 操作。 本文提出了一种稀疏 3D 卷积神经网络 (CNN)，利用 3D 数据的稀疏性进行实时点云分类。该框架不需要 GPU。该方法的实用性在从不同平台和传感器收集的数据集上得到了验证。所提出的网络可以用于其他类别...