An encoder-decoder deep learning method for multi-class object segmentation from 3D tunnel point clouds

Discovering seepage is widely thought to be critical for maintaining the healthy conditions of the tunnel. Unfortunately, most of the seepage surveys are still manual with tedious, time-consuming, and inefficient as well as work-related physical injuries. To address this problem, this research propo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Automation in construction Jg. 137; S. 104187
Hauptverfasser: Ji, Ankang, Chew, Alvin Wei Ze, Xue, Xiaolong, Zhang, Limao
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Amsterdam Elsevier B.V 01.05.2022
Elsevier BV
Schlagworte:
3D tunnel point-clouds
Coders
Data processing
Deep learning
Encoder-decoder
Encoders-Decoders
Feature extraction
Image segmentation
Machine learning
Multi-class object segmentation
Seepage
Segmentation
Teaching methods
Three dimensional models
Tunnels
Deep learning
3D tunnel point-clouds
Multi-class object segmentation
Segmentation
Encoder-decoder
ISSN:0926-5805, 1872-7891
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Discovering seepage is widely thought to be critical for maintaining the healthy conditions of the tunnel. Unfortunately, most of the seepage surveys are still manual with tedious, time-consuming, and inefficient as well as work-related physical injuries. To address this problem, this research proposes an encoder-decoder deep learning method combined with point cloud techniques for multi-class object segmentation, including seepage, from 3D tunnel point clouds. This method develops data processing and feature extraction techniques to perform normalization of 3D point clouds with full consideration of point features, followed by constructing voxels as input to the proposed encoder-decoder architecture for learning. In the training process, an optimal model is selected with a learning rate of 0.0001, a batch size of 256, and a voxel boundary of 8. Subsequently, the optimal well-trained model is applied to the testing set, achieving excellent performance. Comparisons with other state-of-the-art methods and four data processing strategies are conducted, demonstrating that the proposed method outperforms in segmenting large-scale 3D point clouds. Overall, the proposed method performs excellently, beneficially contributing to the multi-class object segmentation from 3D tunnel point clouds with great practical potential. •An encoder-decoder deep learning model is developed for 3D point cloud segmentation.•Data processing and feature extraction techniques are developed for processing 3D point cloud.•The effectiveness of the method is validated by evaluation metrics in practical tunnels.•Conducting comparisons examining the segmentation performance of the method.•The method perform excellently with great efficiency and high reliability.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0926-5805
1872-7891
DOI:10.1016/j.autcon.2022.104187