A Dual Attention Neural Network for Airborne LiDAR Point Cloud Semantic Segmentation
Open Access
- 26 August 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 60 (01962892) , 1-17
Abstract
With the development of airborne light detection and ranging (LiDAR) technology, it has become a common and efficient way to collect large-scale 3-D spatial information. However, efficient and automatic semantic segmentation of LiDAR data, in the form of 3-D point clouds, remains a persistent challenge. To address this, a dual attention neural network (DA-Net) is proposed, consisting of two different blocks, namely, augmented edge representation (AER) and elevation attentive pooling (EAP). First, the AER can adaptively represent local orientation and position, thereby effectively enhancing geometric information. Second, the captured local features of centroid points are utilized to further encode discriminative features using the EAP with the learned attention scores. Finally, a location homogeneity (LH) module is devised to explore the long-range relationship in an encoder–decoder network. Benefiting from the dual attention module, geometric information hidden in unorganized point clouds can be effectively propagated. Besides, the LH forces the network to pay attention to the semantic consistency of elevated objects, which facilitates both point- and object-level point cloud semantic segmentation for scene understanding. A benchmark dataset is used to assess the proposed method, which achieves an overall accuracy of 85.98% and an average F1 score of 72.31%. In addition, comparisons with other latest deep learning methods on the 2019 Data Fusion Contest dataset further demonstrate the robustness and generalization ability of the proposed method.Keywords
Funding Information
- National Natural Science Foundation of China (42271342, 42071301)
- Natural Science Foundation of Jiangsu Province (BK20201372)
- Open Fund of Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources (KF-2019-04-003)
- National Key Research and Development Plan of China (2017YFB0503500, 2017YFB0503504)
- Priority Academic Program Development of Jiangsu Higher Education Institutions (164320H116)
This publication has 70 references indexed in Scilit:
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiersISPRS Journal of Photogrammetry and Remote Sensing, 2015
- Extraction of road traffic sign information based on a vehicle‐borne mobile photogrammetric systemThe Photogrammetric Record, 2015
- Fully-Automated Power Line Extraction from Airborne Laser Scanning Point Clouds in Forest AreasRemote Sensing, 2014
- Contextual classification of lidar data and building object detection in urban areasISPRS Journal of Photogrammetry and Remote Sensing, 2014
- SVM-Based Classification of Segmented Airborne LiDAR Point Clouds in Urban AreasRemote Sensing, 2013
- CONDITIONAL RANDOM FIELDS FOR THE CLASSIFICATION OF LIDAR POINT CLOUDSThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012
- RANDOM FORESTS BASED MULTIPLE CLASSIFIER SYSTEM FOR POWER-LINE SCENE CLASSIFICATIONThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2012
- Unique Signatures of Histograms for Local Surface Description2010
- Using spin images for efficient object recognition in cluttered 3D scenesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999