Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/162039
Title: FPS-Net: a convolutional fusion network for large-scale LiDAR point cloud segmentation
Authors: Xiao, Aoran
Yang, Xiaofei
Lu, Shijian
Guan, Dayan
Huang, Jiaxing
Keywords: Engineering::Computer science and engineering
Issue Date: 2021
Source: Xiao, A., Yang, X., Lu, S., Guan, D. & Huang, J. (2021). FPS-Net: a convolutional fusion network for large-scale LiDAR point cloud segmentation. ISPRS Journal of Photogrammetry and Remote Sensing, 176, 237-249. https://dx.doi.org/10.1016/j.isprsjprs.2021.04.011
Journal: ISPRS Journal of Photogrammetry and Remote Sensing
Abstract: Scene understanding based on LiDAR point cloud is an essential task for autonomous cars to drive safely, which often employs spherical projection to map 3D point cloud into multi-channel 2D images for semantic segmentation. Most existing methods simply stack different point attributes/modalities (e.g. coordinates, intensity, depth, etc.) as image channels to increase information capacity, but ignore distinct characteristics of point attributes in different image channels. We design FPS-Net, a convolutional fusion network that exploits the uniqueness and discrepancy among the projected image channels for optimal point cloud segmentation. FPS-Net adopts an encoder-decoder structure. Instead of simply stacking multiple channel images as a single input, we group them into different modalities to first learn modality-specific features separately and then map the learned features into a common high-dimensional feature space for pixel-level fusion and learning. Specifically, we design a residual dense block with multiple receptive fields as a building block in the encoder which preserves detailed information in each modality and learns hierarchical modality-specific and fused features effectively. In the FPS-Net decoder, we use a recurrent convolution block likewise to hierarchically decode fused features into output space for pixel-level classification. Extensive experiments conducted on two widely adopted point cloud datasets show that FPS-Net achieves superior semantic segmentation as compared with state-of-the-art projection-based methods. In addition, the proposed modality fusion idea is compatible with typical projection-based methods and can be incorporated into them with consistent performance improvements.
URI: https://hdl.handle.net/10356/162039
ISSN: 0924-2716
DOI: 10.1016/j.isprsjprs.2021.04.011
Rights: © 2021 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:SCSE Journal Articles

SCOPUSTM   
Citations 20

11
Updated on Nov 25, 2022

Web of ScienceTM
Citations 20

8
Updated on Nov 19, 2022

Page view(s)

30
Updated on Nov 26, 2022

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.