Feature Graph Convolution Network With Attentive Fusion for Large-Scale Point Clouds Semantic Segmentation | IEEE Journals & Magazine | IEEE Xplore

Feature Graph Convolution Network With Attentive Fusion for Large-Scale Point Clouds Semantic Segmentation


Abstract:

Unstructured nature of 3-D point clouds in large scenes is a challenging problem to effectively learn local geometric structures for point cloud semantic segmentation. To...Show More

Abstract:

Unstructured nature of 3-D point clouds in large scenes is a challenging problem to effectively learn local geometric structures for point cloud semantic segmentation. To address this issue, we proposed a Feature Graph Convolution Network with Attentive Fusion (FGC-AFNet) in this letter. Our method takes large point clouds as input and uses the Feature Graph Convolution (FGC) module to construct a graph of the central point with its neighboring points to extract local features. Then, we reduced the number of points using random sampling (RS) to expand the receptive field gradually to obtain multilevel features. The network also employs a dual Attentive Fusion (AF) mechanism for efficient feature aggregation. One is at different levels for semantic feature fusion, another is for narrowing the semantic feature gap between the encoder and decoder. Compared to state-of-the-art methods on the S3DIS and Toronto3D datasets, our method obtained competitive results, with an overall accuracy of 88.6% and 96.58%, and a mean intersection over a union of 71.2% and 81.92% on S3DIS and Toronto3D, respectively.
Published in: IEEE Geoscience and Remote Sensing Letters ( Volume: 20)
Article Sequence Number: 6501405
Date of Publication: 14 August 2023

ISSN Information:

Funding Agency:


References

References is not available for this document.