Next Article in Journal
Boundary-Aware Refined Network for Automatic Building Extraction in Very High-Resolution Urban Aerial Images
Previous Article in Journal
Aerosol—Cloud Interaction with Summer Precipitation over Major Cities in Eritrea
Open AccessTechnical Note

Multi-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation

1
School of Remote Sensing and Information Engineering, Wuhan University, 129 Luoyu Road, Wuhan 430079, China
2
Department of Physical Geography, Faculty of Geoscience, Utrecht University, Princetonlaan 8, 3584 CB Utrecht, The Netherlands
*
Author to whom correspondence should be addressed.
Academic Editor: Sander Oude Elberink
Remote Sens. 2021, 13(4), 691; https://doi.org/10.3390/rs13040691
Received: 29 December 2020 / Revised: 29 January 2021 / Accepted: 8 February 2021 / Published: 14 February 2021
Semantic segmentation of LiDAR point clouds has implications in self-driving, robots, and augmented reality, among others. In this paper, we propose a Multi-Scale Attentive Aggregation Network (MSAAN) to achieve the global consistency of point cloud feature representation and super segmentation performance. First, upon a baseline encoder-decoder architecture for point cloud segmentation, namely, RandLA-Net, an attentive skip connection was proposed to replace the commonly used concatenation to balance the encoder and decoder features of the same scales. Second, a channel attentive enhancement module was introduced to the local attention enhancement module to boost the local feature discriminability and aggregate the local channel structure information. Third, we developed a multi-scale feature aggregation method to capture the global structure of a point cloud from both the encoder and the decoder. The experimental results reported that our MSAAN significantly outperformed state-of-the-art methods, i.e., at least 15.3% mIoU improvement for scene-2 of CSPC dataset, 5.2% for scene-5 of CSPC dataset, and 6.6% for Toronto3D dataset. View Full-Text
Keywords: LiDAR point cloud segmentation; attentive skip connection; channel attentive enhancement; multi-scale aggregation; deep learning LiDAR point cloud segmentation; attentive skip connection; channel attentive enhancement; multi-scale aggregation; deep learning
Show Figures

Figure 1

MDPI and ACS Style

Geng, X.; Ji, S.; Lu, M.; Zhao, L. Multi-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation. Remote Sens. 2021, 13, 691. https://doi.org/10.3390/rs13040691

AMA Style

Geng X, Ji S, Lu M, Zhao L. Multi-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation. Remote Sensing. 2021; 13(4):691. https://doi.org/10.3390/rs13040691

Chicago/Turabian Style

Geng, Xiaoxiao; Ji, Shunping; Lu, Meng; Zhao, Lingli. 2021. "Multi-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation" Remote Sens. 13, no. 4: 691. https://doi.org/10.3390/rs13040691

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop