☆ 4.7 Article

Attention-enhanced sampling point cloud network (ASPCNet) for efficient 3D tunnel semantic segmentation

AUTOMATION IN CONSTRUCTION (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Construction & Building Technology

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

Ankang Ji et al.

Summary: 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. The method achieves excellent performance through optimized data processing, feature extraction, and model training, and it has great practical potential.

AUTOMATION IN CONSTRUCTION (2022)

添加到收藏夹

Article Construction & Building Technology

Sewer defect detection from 3D point clouds using a transformer-based deep learning model

Yunxiang Zhou et al.

Summary: This research develops a deep learning method called TransPCNet for 3D point cloud defect classification. TransPCNet achieves more accurate and effective results by enhancing feature extraction and learning capability, and introducing a novel loss function to address data imbalance issues.

AUTOMATION IN CONSTRUCTION (2022)

添加到收藏夹

Article Construction & Building Technology

Multi-objective optimization for improved project management: Current status and future directions

Kai Guo et al.

Summary: This paper presents a systematic review on the application of multi-objective optimization (MOO) in project improvement in the construction industry. The study reveals an increasing number of MOO-related papers in recent years, with wide applications in project planning, construction automation, and structural health monitoring. However, challenges such as incompatibility with dynamic features, ambiguity of input-output relationship, and low interaction still exist for the adoption of MOO in project management.

AUTOMATION IN CONSTRUCTION (2022)

添加到收藏夹

Article Construction & Building Technology

UnrollingNet: An attention-based deep learning approach for the segmentation of large-scale point clouds of tunnels

Zhaoxiang Zhang et al.

Summary: This study develops a novel projection-based learning method named UnrollingNet for multi-label segmentation of 3D point clouds. The approach involves collecting raw point clouds using 3D laser scanning, creating 2D representations through an unrolling projection technique, and employing a U-net-based segmentation algorithm for pixel-level tunnel classification. To address class imbalance issues and enhance segmentation performance, a pixel-weight cross-entropy loss and a dual attention module are proposed. A case study of a real cross-river tunnel section in China demonstrates the high performance of the established model in point cloud projection and multi-class segmentation compared to other deep-learning-based point cloud segmentation models.

AUTOMATION IN CONSTRUCTION (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Automatic defect detection of metro tunnel surfaces using a vision-based inspection system

Dawei Li et al.

Summary: Damage to metro tunnel surfaces often leads to accidents due to lack of maintenance. An automatic Metro Tunnel Surface Inspection System (MTSIS) is designed for efficient and accurate defect detection, with hardware and software components covering data collection and image processing for defect recognition. High precision defect detection methods have shown promising performance in practical experiments and successful application on multiple metro lines.

ADVANCED ENGINEERING INFORMATICS (2021)

添加到收藏夹

Article Construction & Building Technology

A deep learning-based approach for refined crack evaluation from shield tunnel lining images

Shuai Zhao et al.

Summary: This paper presents a deep learning-based approach that extends the PANet model by adding a semantic branch to refine crack evaluation and reduce inaccuracies associated with crack discontinuities and image skeletonization. Experimental results show that the proposed approach outperforms other methods, demonstrating its superiority in mitigating crack disjoint problems and skeletonization error. The evaluation metrics indicate that the proposed model is an alternative approach for crack segmentation and quantification in the field.

AUTOMATION IN CONSTRUCTION (2021)

添加到收藏夹

Article Construction & Building Technology

Automated semantic segmentation of industrial point clouds using ResPointNet plus

Chao Yin et al.

Summary: This paper proposes a novel deep learning-based approach, ResPointNet++, for automatic creation of as-built BIM models from point clouds, with higher segmentation accuracy and mIoU demonstrated in experiments. The study first constructs an expert-labeled industrial LiDAR dataset, contributing to automated 3D scene interpretation of industrial point clouds.

AUTOMATION IN CONSTRUCTION (2021)

添加到收藏夹

Article Construction & Building Technology

Semantic segmentation of bridge components based on hierarchical point cloud model

Jun S. Lee et al.

Summary: A graph-based hierarchical DGCNN (HGCNN) model is proposed in this study for improved representation of tall components like electric poles in railway bridges. The model obtains detailed local features by incrementally considering neighboring points, resulting in improved recall and IoU rate for electric poles.

AUTOMATION IN CONSTRUCTION (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

PointVGG: Graph convolutional network with progressive aggregating features on point clouds

Rongkang Li et al.

Summary: This paper introduces the usage of point convolution and point pooling on irregular point cloud data for learning high-level features. By applying these techniques, accurate shape information and geometric representation of point clouds can be achieved, leading to outstanding results in tasks like object classification and part segmentation.

NEUROCOMPUTING (2021)

添加到收藏夹

Article Computer Science, Hardware & Architecture

A Heuristic Sampling Method for Maintaining the Probability Distribution

Jiao-Yun Yang et al.

Summary: This paper proposes a heuristic sampling algorithm based on Bayesian networks and chi-square tests, which generates data subsets that pass distribution tests while maintaining probability distributions. Experimental results show that the algorithm significantly outperforms random sampling in terms of distribution accuracy.

JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY (2021)

添加到收藏夹

Article Computer Science, Software Engineering

PCT: Point cloud transformer

Meng-Hao Guo et al.

Summary: This paper introduces a novel framework named Point Cloud Transformer (PCT) for point cloud learning, based on Transformer and enhanced by farthest point sampling and nearest neighbor search for better capturing local context. Extensive experiments demonstrate that the PCT achieves state-of-the-art performance on shape classification, part segmentation, semantic segmentation, and normal estimation tasks.

COMPUTATIONAL VISUAL MEDIA (2021)

添加到收藏夹

Article Construction & Building Technology

Image-based concrete crack detection in tunnels using deep fully convolutional networks

Yupeng Ren et al.

CONSTRUCTION AND BUILDING MATERIALS (2020)

添加到收藏夹

Article Construction & Building Technology

Deep learning-based image instance segmentation for moisture marks of shield tunnel lining

Shuai Zhao et al.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2020)

添加到收藏夹

Article Environmental Sciences

Point Cloud Semantic Segmentation Using a Deep Learning Framework for Cultural Heritage

Roberto Pierdicca et al.

REMOTE SENSING (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Point attention network for semantic segmentation of 3D point clouds

Mingtao Feng et al.

PATTERN RECOGNITION (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Feature fusion network based on attention mechanism for 3D semantic segmentation of point clouds

Heng Zhou et al.

PATTERN RECOGNITION LETTERS (2020)

添加到收藏夹

Article Computer Science, Software Engineering

Attention-based relation and context modeling for point cloud semantic segmentation

Zhiyu Hu et al.

COMPUTERS & GRAPHICS-UK (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Multi-view semantic learning network for point cloud based 3D object detection

Yongguang Yang et al.

NEUROCOMPUTING (2020)

添加到收藏夹

Article Computer Science, Software Engineering

Point cloud semantic scene segmentation based on coordinate convolution

Zhaoxuan Zhang et al.

COMPUTER ANIMATION AND VIRTUAL WORLDS (2020)

添加到收藏夹

Article Construction & Building Technology

Factors in the development of urban underground space surrounding metro stations: A case study of Osaka, Japan

Jian Peng et al.

TUNNELLING AND UNDERGROUND SPACE TECHNOLOGY (2019)

添加到收藏夹

Article Computer Science, Information Systems

A Review of Deep Learning-Based Semantic Segmentation for Point Cloud

Jiaying Zhang et al.

IEEE ACCESS (2019)

添加到收藏夹

Proceedings Paper Computer Science, Software Engineering

JUSTLOOKUP: ONE MILLISECOND DEEP FEATURE EXTRACTION FOR POINT CLOUDS BY LOOKUP TABLES

Hongxin Lin et al.

2019 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO (ICME) (2019)

添加到收藏夹

Article Construction & Building Technology

Damage detection and quantitative analysis of shield tunnel structure

Zhen Huang et al.

AUTOMATION IN CONSTRUCTION (2018)

添加到收藏夹

Article Construction & Building Technology

Sensitivity analysis of structural health risk in operational tunnels

Wenli Liu et al.

AUTOMATION IN CONSTRUCTION (2018)

添加到收藏夹

Proceedings Paper Automation & Control Systems

Weighted Focal Loss: An Effective Loss Function to Overcome Unbalance Problem of Chest X-ray14

Ruoxi Qin et al.

3RD INTERNATIONAL CONFERENCE ON AUTOMATION, CONTROL AND ROBOTICS ENGINEERING (CACRE 2018) (2018)

添加到收藏夹

Article Economics

Transportation infrastructure impacts on firm location: the effect of a new metro line in the suburbs of Madrid

Lucia Mejia-Dorantes et al.

JOURNAL OF TRANSPORT GEOGRAPHY (2012)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.