Multi-Scale Attentive Aggregation for LiDAR Point Cloud Segmentation
Open Access
- 14 February 2021
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 13 (4) , 691
Abstract
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.Keywords
Funding Information
- the national key Research and Development Program of China (2018YFB0505003)
This publication has 33 references indexed in Scilit:
- Exploring New Backbone and Attention Module for Semantic Segmentation in Street ScenesIEEE Access, 2018
- A scale robust convolutional neural network for automatic building extraction from aerial and satellite imageryInternational Journal of Remote Sensing, 2018
- 3DMV: Joint 3D-Multi-view Prediction for 3D Semantic Scene Segmentation2018
- Fully-Convolutional Point Networks for Large-Scale Point Clouds2018
- SnapNet: 3D point cloud semantic labeling with 2D deep segmentation networksComputers & Graphics, 2018
- Deep Projective 3D Semantic Segmentation2017
- SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning2017
- SEMANTIC3D.NET: A NEW LARGE-SCALE POINT CLOUD CLASSIFICATION BENCHMARKISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2017
- Deep learningNature, 2015
- SVM-Based Classification of Segmented Airborne LiDAR Point Clouds in Urban AreasRemote Sensing, 2013