LFT-Net: Local Feature Transformer Network for Point Clouds Analysis

6G network enables the rapid connection of autonomous vehicles, the generated internet of vehicles establishes a large-scale point cloud, which requires automatic point cloud analysis to build an intelligent transportation system in terms of the 3D object detection and segmentation. Recently, a great variety of deep convolution networks have been proposed for 3D data analysis, making significant progress in the application of deep learning in 3D computer vision. Inspired by the application of transformer network in 2D computer visual tasks, and in order to increase the expression ability of local fine-grained features, we propose an effective local feature transformer network to learn local feature information and correlations between point clouds. Our network is adaptive to the arrangement of set elements through transformer module, so it is suitable for the feature extraction of local point clouds. In addition, experimental results demonstrate that our LFT-network outperforms the state-of-the-art in 3D model classification tasks on ModelNet40 dataset and segmentation tasks on S3DIS dataset.

Automated summary

The 6G network enables fast connection of autonomous vehicles and generates a large-scale internet of vehicles. The analysis of point cloud data is essential for building an intelligent transportation system with 3D object detection and segmentation. Recent advancements in deep learning for 3D computer vision have introduced various deep convolution networks. Inspired by the application of transformer networks in 2D computer visual tasks, this study proposes an effective local feature transformer network for learning local feature information and correlations between point clouds.