Point Cloud Semantic Segmentation Network Based on Multi-Scale Feature Fusion

Sensors

Yundong Wu¹  Shangfeng Huang¹  Zuning Jiang¹  Guorong Cai¹  Zongyue Wang¹  Jinhe Su¹  Jing Du¹  Songjian Su² 

[1] Computer Engineering College, Jimei University, Xiamen 361021, China;Ropeok Technology Group co., LTD., Xiamen 361021, China;

关键词: LIDAR point cloud;    semantic segmentation;    feature fusion;    deep learning;    computer vision;   

DOI  :  10.3390/s21051625

来源: DOAJ

【 摘 要 】

The semantic segmentation of small objects in point clouds is currently one of the most demanding tasks in photogrammetry and remote sensing applications. Multi-resolution feature extraction and fusion can significantly enhance the ability of object classification and segmentation, so it is widely used in the image field. For this motivation, we propose a point cloud semantic segmentation network based on multi-scale feature fusion (MSSCN) to aggregate the feature of a point cloud with different densities and improve the performance of semantic segmentation. In our method, random downsampling is first applied to obtain point clouds of different densities. A Spatial Aggregation Net (SAN) is then employed as the backbone network to extract local features from these point clouds, followed by concatenation of the extracted feature descriptors at different scales. Finally, a loss function is used to combine the different semantic information from point clouds of different densities for network optimization. Experiments were conducted on the S3DIS and ScanNet datasets, and our MSSCN achieved accuracies of 89.80% and 86.3%, respectively, on these datasets. Our method showed better performance than the recent methods PointNet, PointNet++, PointCNN, PointSIFT, and SAN.

【 授权许可】

Unknown