Effective and efficient semantic segmentation of 3D point cloud data is important for many tasks. Many methods for point cloud semantic segmentation rely on computationally expensive sampling and grouping layers to process irregular points, while others convert irregular points into regular volumetric grids and process them with a 3D U-Netbased semantic segmentation network. However, most of these methods suffer from high computational costs and cannot be applied to the real-time processing of large-scale point clouds. To address these issues, we propose a computationally efficient point-voxel-based network architecture named Sparse Point-Voxel Aggregation Network (SPVAN) for point cloud semantic segmentation. It consists of an encoding layer that consists of sparse convolution and MLP layers and a new decoding layer called Point Feature Aggregation Layer (PFAL) that is only composed of feature interpolation and MLP layers. Compared with recent popular point-voxel-based methods with the U-Net-based network, our method does not need 3D convolution networks in the decoding layer and thus achieves a higher speed. Experimental results on the large-scale SemanticKITTI dataset show that our method gets a good balance between the efficiency and the performance. Moreover, our method achieves on-par or better performance than previous methods for semantic segmentation on the challenging S3DIS dataset.

This paper presents a real-time and multi-sensor-based landing area recognition system for UAVs, which aims to enable UAVs to land safely on open and flat terrain and is suitable for comprehensive unmanned autonomous operation. The landing area recognition system for UAVs is built on the combination of a camera and a 3D LiDAR. The problem is how to fuse the image and point cloud information and realize the landing area recognition to guide the UAV landing autonomously and safely. To solve this problem, firstly, we use a deep learning method to realize the landing area recognition and tracking from images. After that, we project 3D LiDAR point cloud data into camera coordinates to obtain the semantic label of each point. Finally, we use the 3D LiDAR point cloud data with the semantic label to build the 3D environment map and calculate the most suitable area for UAV landing. Experiments show that the proposed method can achieve accurate and robust recognition of landing area for UAVs.