Point cloud semantic segmentation in urban scenes plays a vital role in intelligent city modeling, autonomous driving, and urban planning. Point cloud semantic segmentation based on deep learning methods has achieved significant improvement. However, it is also challenging for accurate semantic segmentation in large scenes due to complex elements, variety of scene classes, occlusions, and noise. Besides, most methods need to split the original point cloud into multiple blocks before processing and cannot directly deal with the point clouds on a large scale. We propose a novel context-aware network (CAN) that can directly deal with large-scale point clouds. In the proposed network, a local feature aggregation module (LFAM) is designed to preserve rich geometric details in the raw point cloud and reduce the information loss during feature extraction. Then, in combination with a global context aggregation module (GCAM), capture long-range dependencies to enhance the network feature representation and suppress the noise. Finally, a context-aware upsampling module (CAUM) is embedded into the proposed network to capture the global perception from a broad perspective. The ensemble of low-level and high-level features facilitates the effectiveness and efficiency of 3-D point cloud feature refinement. Comprehensive experiments were carried out on three large-scale point cloud datasets in both outdoor and indoor environments to evaluate the performance of the proposed network. The results show that the proposed method outperformed the state-of-the-art representative semantic segmentation networks, and the overall accuracy (OA) of Tongji-3D, Semantic3D, and Stanford large-scale 3-D indoor spaces (S3DIS) is 96.01%, 95.0%, and 88.55%, respectively.

中文翻译：

---

用于城市环境中大规模点云语义分割的上下文感知网络


城市场景中的点云语义分割在智能城市建模、自动驾驶和城市规划中发挥着至关重要的作用。基于深度学习方法的点云语义分割取得了显着的改进。然而，由于元素复杂、场景类别多样、遮挡和噪声，大场景中准确的语义分割也面临挑战。此外，大多数方法在处理前需要将原始点云分割成多个块，无法直接大规模处理点云。我们提出了一种新颖的上下文感知网络（CAN），可以直接处理大规模点云。在所提出的网络中，设计了局部特征聚合模块（LFAM）来保留原始点云中丰富的几何细节，并减少特征提取过程中的信息丢失。然后，结合全局上下文聚合模块（GCAM），捕获远程依赖性以增强网络特征表示并抑制噪声。最后，将上下文感知上采样模块（CAUM）嵌入到所提出的网络中，以从广泛的角度捕获全局感知。低级和高级特征的集成有助于提高 3D 点云特征细化的有效性和效率。在室外和室内环境下的三个大型点云数据集上进行了综合实验，以评估所提出的网络的性能。结果表明，所提出的方法优于最先进的代表性语义分割网络，Tongji-3D、Semantic3D 和斯坦福大型 3D 室内空间 (S3DIS) 的总体精度 (OA) 为 96.01分别为 %、95.0% 和 88.55%。