4.7 Article

Semantic Segmentation of Terrestrial Laser Scanning Point Clouds Using Locally Enhanced Image-Based Geometric Representations

Related references

Note: Only part of the references are listed.
Review Construction & Building Technology

Semantic interpretation of architectural and archaeological geometries: Point cloud segmentation for HBIM parameterisation

Juan Moyano et al.

Summary: The creation of Cultural Heritage Digital Twins involves capturing geometric data, processing raw data, and converting them into BIM objects. Manual methods for BIM segmentation and modeling are labor-intensive, leading to research into automation especially in the field of cultural heritage. This study explores the application of the CANUPO algorithm for classifying architectural components of a 16th-century palace in Seville, Spain.

AUTOMATION IN CONSTRUCTION (2021)

Article Computer Science, Artificial Intelligence

Res2Net: A New Multi-Scale Backbone Architecture

Shang-Hua Gao et al.

Summary: This paper introduces a novel building block for CNNs, Res2Net, which represents multiscale features within one single residual block by constructing hierarchical residual-like connections. The Res2Net enhances the representation of multiscale features in various vision tasks and consistently outperforms baseline models in performance gains.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Article Geochemistry & Geophysics

Tunnel Reconstruction With Block Level Precision by Combining Data-Driven Segmentation and Model-Driven Assembly

Zhen Cao et al.

Summary: The study presents a method for creating high-fidelity geometric models of tunnel linings from Terrestrial Laser Scanning point clouds, using a two-stage algorithm and data-driven block segmentation combined with model-driven assembly techniques. Experimental results demonstrate that the proposed method performs well in geometric model fitting, making it applicable for monitoring and maintenance of metro tunnels.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2021)

Article Computer Science, Artificial Intelligence

Deep Learning for 3D Point Clouds: A Survey

Yulan Guo et al.

Summary: Recently, deep learning on point clouds has been gaining more attention, but it is still in its early stages due to the unique challenges faced in processing point clouds with deep neural networks.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Article Computer Science, Artificial Intelligence

Deep High-Resolution Representation Learning for Visual Recognition

Jingdong Wang et al.

Summary: The High-Resolution Network (HRNet) maintains high-resolution representations and exchanges information across resolutions, resulting in superior performance in various applications such as human pose estimation, semantic segmentation, and object detection.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Article Environmental Sciences

Global 3D Features of Error Variances of GPS Radio Occultation and Radiosonde Observations

Xu Xu et al.

Summary: This study estimated the error variances of global GPS RO and RS observations using the three-cornered hat method, analyzing the global distributions in terms of vertical and latitudinal variations. Results show that error variances of RO refractivity, bending angle, and RS specific humidity in the lower troposphere increase with decreasing latitude.

REMOTE SENSING (2021)

Article Geography, Physical

Automated street tree inventory using mobile LiDAR point clouds based on Hough transform and active contours

Amir Hossein Safaie et al.

Summary: The study proposes an efficient method for automated creation of road-side tree inventory using Mobile Terrestrial Lidar System point clouds, detecting and identifying tree trunks and canopies through Hough Transform and Voronoi Tessellation algorithms, and obtaining geometric characteristics of each tree using Active Contour models. Results show accurate extraction of all trees and promising accuracy of obtained geometric parameters when compared with manually observed measures.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2021)

Article Environmental Sciences

Selecting Optimal Combination of Data Channels for Semantic Segmentation in City Information Modelling (CIM)

Yuanzhi Cai et al.

Summary: Research has shown that combining multiple data channels can improve model accuracy, but may lead to high computation costs and processing time in large-scale datasets. This study proposed a framework to explore the impact of optimal data channel combinations on semantic segmentation and conducted a case study using a city-level benchmark dataset.

REMOTE SENSING (2021)

Article Environmental Sciences

An Efficient Approach to Automatic Construction of 3D Watertight Geometry of Buildings Using Point Clouds

Yuanzhi Cai et al.

Summary: The study presented an efficient reconstruction approach that successfully created accurate watertight building geometries with an average difference of 12 to 21 mm between the point cloud data and the geometric models, and a computation time of less than 5 minutes.

REMOTE SENSING (2021)

Article Construction & Building Technology

Effective Scanning Range Estimation for Using TLS in Construction Projects

Hong Huang et al.

Summary: The translation discusses the application of terrestrial laser scanner in construction, proposing a method to calculate effective scan range and conducting case studies. The results suggest that the method is feasible and reliable.

JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT (2021)

Article Environmental Sciences

An Efficient Filtering Approach for Removing Outdoor Point Cloud Data of Manhattan-World Buildings

Lei Fan et al.

Summary: This research explores an efficient image-based filtering approach to automatically remove unwanted data points beyond the indoor space of interest, with an average precision of 99.50% and computational efficiency of 0.53 seconds at most.

REMOTE SENSING (2021)

Proceedings Paper Computer Science, Artificial Intelligence

An Overview of Constructing Geometric Models of Buildings using Point Clouds

Yuanzhi Cai et al.

Summary: Building Information Modelling (BIM) and numerical simulations are valuable tools in building design, but their application in existing buildings is hindered by the lack of geometric models. Research focuses on automating the geometric modelling process to improve efficiency and quality of models.

2021 INTERNATIONAL CONFERENCE ON IMAGE, VIDEO PROCESSING, AND ARTIFICIAL INTELLIGENCE (2021)

Proceedings Paper Computer Science, Artificial Intelligence

InverseForm: A Loss Function for Structured Boundary-Aware Segmentation

Shubhankar Borse et al.

Summary: This study introduces a novel boundary-aware loss term for semantic segmentation, which efficiently learns the degree of parametric transformations between estimated and target boundaries, resulting in consistent and significant performance improvements.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Lite-HRNet: A Lightweight High-Resolution Network

Changqian Yu et al.

Summary: Lite-HRNet is an efficient high-resolution network that outperforms popular lightweight networks by introducing conditional channel weighting unit to replace costly pointwise convolutions. It demonstrates superior results on human pose estimation and can easily be applied to semantic segmentation task in a lightweight manner.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning

Jingyu Gong et al.

Summary: This paper introduces a method of omni-scale supervision through gradual reasoning from coarse to fine to infer Receptive Field Component Codes, ultimately obtaining semantic labels. Additionally, the proposed Feature Densification method is able to enhance the potential of the omni-supervision approach.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Article Computer Science, Artificial Intelligence

Focal Loss for Dense Object Detection

Tsung-Yi Lin et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2020)

Article Computer Science, Software Engineering

ConvPoint: Continuous convolutions for point cloud processing

Alexandre Boulch

COMPUTERS & GRAPHICS-UK (2020)

Article Automation & Control Systems

OctreeNet: A Novel Sparse 3-D Convolutional Neural Network for Real-Time 3-D Outdoor Scene Analysis

Fei Wang et al.

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING (2020)

Article Computer Science, Artificial Intelligence

Squeeze-and-Excitation Networks

Jie Hu et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2020)

Proceedings Paper Automation & Control Systems

PointAtrousGraph: Deep Hierarchical Encoder-Decoder with Point Atrous Convolution for Unorganized 3D Points

Liang Pan et al.

2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) (2020)

Proceedings Paper Automation & Control Systems

Dilated Point Convolutions: On the Receptive Field Size of Point Convolutions on 3D Point Clouds

Francis Engelmann et al.

2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) (2020)

Article Geochemistry & Geophysics

CoinNet: Copy Initialization Network for Multispectral Imagery Semantic Segmentation

Bin Pan et al.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2019)

Article Computer Science, Software Engineering

Dynamic Graph CNN for Learning on Point Clouds

Yue Wang et al.

ACM TRANSACTIONS ON GRAPHICS (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Know What Your Neighbors Do: 3D Semantic Segmentation of Point Clouds

Francis Engelmann et al.

COMPUTER VISION - ECCV 2018 WORKSHOPS, PT III (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Graph Attention Convolution for Point Cloud Semantic Segmentation

Lei Wang et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Point Cloud Oversegmentation with Graph-Structured Deep Metric Learning

Loic Landrieu et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Self-Supervised Learning via Conditional Motion Propagation

Xiaohang Zhan et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Article Computer Science, Software Engineering

SnapNet: 3D point cloud semantic labeling with 2D deep segmentation networks

Alexandre Boulch et al.

COMPUTERS & GRAPHICS-UK (2018)

Article Computer Science, Artificial Intelligence

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

Liang-Chieh Chen et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2018)

Article Geography, Physical

Fusion of images and point clouds for the semantic segmentation of large-scale 3D scenes based on deep learning

Rui Zhang et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2018)

Proceedings Paper Computer Science, Artificial Intelligence

Semantic Classification of 3D Point Clouds with Multiscale Spherical Neighborhoods

Hugues Thomas et al.

2018 INTERNATIONAL CONFERENCE ON 3D VISION (3DV) (2018)

Proceedings Paper Energy & Fuels

Space Charge Analysis of Polyethylene with Chemical Defects Based on Density Function Theory

Tao Lin et al.

2018 IEEE INTERNATIONAL CONFERENCE ON HIGH VOLTAGE ENGINEERING AND APPLICATION (ICHVE) (2018)

Article Geography, Physical

Computing multiple aggregation levels and contextual features for road facilities recognition using mobile laser scanning data

Bisheng Yang et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2017)

Article Geography, Physical

Contextual segment-based classification of airborne laser scanner data

George Vosselman et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Exploring Spatial Context for 3D Semantic Segmentation of Point Clouds

Francis Engelmann et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW 2017) (2017)

Proceedings Paper Computer Science, Theory & Methods

Deep Projective 3D Semantic Segmentation

Felix Jaremo Lawin et al.

COMPUTER ANALYSIS OF IMAGES AND PATTERNS (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Xception: Deep Learning with Depthwise Separable Convolutions

Francois Chollet

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Article Geography, Physical

Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers

Martin Weinmann et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2015)

Article Computer Science, Artificial Intelligence

Transfer Learning for Visual Categorization: A Survey

Ling Shao et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2015)

Article Geography, Physical

The effect of short ground vegetation on terrestrial laser scans at a local scale

Lei Fan et al.

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING (2014)

Proceedings Paper Engineering, Electrical & Electronic

COMBINED USE OF GROUND-BASED SYSTEMS FOR CULTURAL HERITAGE CONSERVATION MONITORING

A. Montuori et al.

2014 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS) (2014)

Article Robotics

Vision meets robotics: The KITTI dataset

A. Geiger et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2013)

Article Biochemical Research Methods

Digital Image Processing, Third Edition

Rafael C. Gonzalez et al.

JOURNAL OF BIOMEDICAL OPTICS (2009)