Background-Aware 3-D Point Cloud Segmentation With Dynamic Point Feature Aggregation
With the proliferation of LiDAR sensors and 3-D vision cameras, 3-D point cloud analysis has attracted significant attention in recent years. In this article, we propose a novel 3-D point cloud learning network, referred to as dynamic point feature aggregation network (DPFA-Net), by selectively performing the neighborhood feature aggregation (FA) with dynamic pooling and an attention mechanism. DPFA-Net has two variants for semantic segmentation and classification of 3-D point clouds. As the core module of the DPFA-Net, we propose an FA layer, in which features of the dynamic neighborhood of each point are aggregated via a self-attention mechanism. In contrast to other segmentation models, which aggregate features from fixed neighborhoods, our approach can aggregate features from different neighbors in different layers providing a more selective and broader view to the query points and focusing more on the relevant features in a local neighborhood. In addition, to further improve the performance of semantic segmentation, we exploit the background–foreground (BF) information and present two novel approaches, namely, two-stage BF-Net and BF regularization. Experimental results show that the proposed DPFA-Net achieves the state-of-the-art overall accuracy score of 89.22% for semantic segmentation on the Stanford large-scale 3-D Indoor Spaces (S3DIS) dataset and provides consistently satisfactory performance across different tasks of semantic segmentation, part segmentation, and 3-D object classification. Furthermore, our model achieves 93.1% accuracy on the ModelNet40 dataset and provides a mean shape intersection-over-union (IoU) value of 85.5% for part segmentation on the ShapeNet-Part dataset. It is a also computationally more efficient compared to other methods.
- Research Organization:
- Syracuse Univ., NY (United States)
- Sponsoring Organization:
- USDOE
- Grant/Contract Number:
- AR0000940
- OSTI ID:
- 1884976
- Journal Information:
- IEEE Transactions on Geoscience and Remote Sensing, Journal Name: IEEE Transactions on Geoscience and Remote Sensing Vol. 60; ISSN 0196-2892
- Publisher:
- IEEECopyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
Concentric Spherical GNN for 3D Representation Learning
PANTHER. Pattern ANalytics To support High-performance Exploitation and Reasoning.