Recurrent Residual Dual Attention Network for Airborne Laser Scanning Point Cloud Semantic Segmentation

Kernel point convolution (KPConv) can effectively represent the point features of point cloud data. However, KPConv-based methods just consider the local information of each point, which is very difficult to characterize the intrinsic properties of airborne laser scanning (ALS) point clouds for comp...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on geoscience and remote sensing Jg. 61; S. 1 - 14
Hauptverfasser: Zeng, Tao, Luo, Fulin, Guo, Tan, Gong, Xiuwen, Xue, Jingyun, Li, Hanshan
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Aggregation
Airborne lasers
Attention mechanism
Coders
Convolution
Decoding
Design
Distribution
encoder-decoder structure
Feature extraction
Image segmentation
Kernel
kernel point convolution (KPConv)
Kernels
Laser applications
Lasers
Methods
Modules
Normal distribution
Point cloud compression
point cloud semantic segmentation
recurrent residual structure
Scaling
Scaling factors
Scanning
Semantic segmentation
Semantics
Three-dimensional displays
ISSN:0196-2892, 1558-0644
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Kernel point convolution (KPConv) can effectively represent the point features of point cloud data. However, KPConv-based methods just consider the local information of each point, which is very difficult to characterize the intrinsic properties of airborne laser scanning (ALS) point clouds for complex laser scanning conditions. Therefore, we rethink KPConv and propose a recurrent residual dual attention network (RRDAN) based on the encoder-decoder structure for the semantic segmentation of ALS point cloud data. In the encoder stage, we design an attention KPConv (AKPConv) block by using a scaling factor of batch normalization to highlight the significant channel information. Then, we use the AKPConv block to develop a recurrent residual kernel attention (RRKA) module to iteratively aggregate the local neighborhood features. In the decoder stage, we design a global and local channel attention (GLCA) module with global connection and local 1-D convolution to interact the global and local information after fusing the upsampled high-level representations and the skip-connected low-level features. In addition, to reduce the influence of the long-tailed distribution of reflection intensity, we apply gamma transformation to correct the data as a normal distribution. The proposed RRDAN can achieve diversified feature aggregation to implement the refined semantic segmentation of ALS point clouds. We evaluate our method on three ALS datasets (i.e., ISPRS, DCF2019, and LASDU) to demonstrate its performance compared to a few advanced methods. The code is available at https://github.com/SC-shendazt/RRDAN .
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2023.3285207