Intelligent crack extraction and analysis for tunnel structures with terrestrial laser scanning measurement

Xu, Xiangyang; Yang, Hao

doi:10.1177/1687814019872650

Cited by 31 publications

(9 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, there are two common methods for surface flatness inspection that can be found in previous studies: (1) following quantitative indexes defined in relevant standards such as the F-numbers method [ 163 , 172 ]; or (2) setting up a reference plane and calculating the deviations between surface points and the reference plane [ 162 , 170 ]. On the other hand, the majority of papers on structural damage identification are focused on surface cracks [ 89 , 98 , 99 , 104 , 144 , 171 , 174 , 175 ], spalling [ 75 , 89 ], corrosion [ 161 ], water leakage [ 173 ], and concrete loss [ 160 , 166 ].…”

Section: Research Topics Related To Tls In the Aec Industrymentioning

confidence: 99%

Application of Terrestrial Laser Scanning (TLS) in the Architecture, Engineering and Construction (AEC) Industry

Yuan

Yang

et al. 2021

Sensors

View full text Add to dashboard Cite

As a revolutionary technology, terrestrial laser scanning (TLS) is attracting increasing interest in the fields of architecture, engineering and construction (AEC), with outstanding advantages, such as highly automated, non-contact operation and efficient large-scale sampling capability. TLS has extended a new approach to capturing extremely comprehensive data of the construction environment, providing detailed information for further analysis. This paper presents a systematic review based on scientometric and qualitative analysis to summarize the progress and the current status of the topic and to point out promising research efforts. To begin with, a brief understanding of TLS is provided. Following the selection of relevant papers through a literature search, a scientometric analysis of papers is carried out. Then, major applications are categorized and presented, including (1) 3D model reconstruction, (2) object recognition, (3) deformation measurement, (4) quality assessment, and (5) progress tracking. For widespread adoption and effective use of TLS, essential problems impacting working effects in application are summarized as follows: workflow, data quality, scan planning, and data processing. Finally, future research directions are suggested, including: (1) cost control of hardware and software, (2) improvement of data processing capability, (3) automatic scan planning, (4) integration of digital technologies, (5) adoption of artificial intelligence.

show abstract

Section: Research Topics Related To Tls In the Aec Industrymentioning

confidence: 99%

Application of Terrestrial Laser Scanning (TLS) in the Architecture, Engineering and Construction (AEC) Industry

Yuan

Yang

et al. 2021

Sensors

View full text Add to dashboard Cite

show abstract

“…These vision-based methods have shown promising results, but have been seen to struggle when applied to more challenging environments where the surface is unstructured [5]. 3D sensors have also been utilised for crack and defects detection, however, they have been applied on similar structural domains such as pavements [10], [11], concrete [12], [13], [14], timber [15] and aeroplane exterior [16].…”

Section: Related Workmentioning

confidence: 99%

PointCrack3D: Crack Detection in Unstructured Environments using a 3D-Point-Cloud-Based Deep Neural Network

Azhari¹,

Sennersten²,

Milford³

et al. 2021

Preprint

View full text Add to dashboard Cite

Surface cracks on buildings, natural walls and underground mine tunnels can indicate serious structural integrity issues that threaten the safety of the structure and people in the environment. Timely detection and monitoring of cracks is crucial to managing these risks, especially if the systems can be made highly automated through robots. Visionbased crack detection algorithms using deep neural networks have exhibited promise for structured surfaces such as walls or civil engineering tunnels, but little work has addressed highly unstructured environments such as rock cliffs and bare mining tunnels. To address this challenge, this paper presents PointCrack3D, a new 3D-point-cloud-based crack detection algorithm for unstructured surfaces. The method comprises three key components: an adaptive down-sampling method that maintains sufficient crack point density, a DNN that classifies each point as crack or non-crack, and a post-processing clustering method that groups crack points into crack instances.The method was validated experimentally on a new large natural rock dataset, comprising coloured LIDAR point clouds spanning more than 900 m 2 and 412 individual cracks. Results demonstrate a crack detection rate of 97% overall and 100% for cracks with a maximum width of more than 3 cm, significantly outperforming the state of the art. Furthermore, for crossvalidation, PointCrack3D was applied to an entirely new dataset acquired in different location and not used at all in training and shown to detect 100% of its crack instances. We also characterise the relationship between detection performance, crack width and number of points per crack, providing a foundation upon which to make decisions about both practical deployments and future research directions.

show abstract

“…in which A represents the activation function of feature extraction network [46]. As shown in Figure 2, the input of feature extraction network includes the global input image Therefore, according to the definition of the feature network, the global features and local features can be expressed as follows: Feature extraction from multibranch images.…”

Section: Network Structurementioning

confidence: 99%

“…in which A represents the activation function of feature extraction network f [46]. As shown in Figure 2, the input of feature extraction network f includes the global input image x g and the local input image x l , and the ith local input image is represented as x i l = m i x i g .…”

Section: Network Structurementioning

confidence: 99%

Fusion High-Resolution Network for Diagnosing ChestX-ray Images

Huang

Lin

et al. 2020

Electronics

View full text Add to dashboard Cite

The application of deep convolutional neural networks (CNN) in the field of medical image processing has attracted extensive attention and demonstrated remarkable progress. An increasing number of deep learning methods have been devoted to classifying ChestX-ray (CXR) images, and most of the existing deep learning methods are based on classic pretrained models, trained by global ChestX-ray images. In this paper, we are interested in diagnosing ChestX-ray images using our proposed Fusion High-Resolution Network (FHRNet). The FHRNet concatenates the global average pooling layers of the global and local feature extractors—it consists of three branch convolutional neural networks and is fine-tuned for thorax disease classification. Compared with the results of other available methods, our experimental results showed that the proposed model yields a better disease classification performance for the ChestX-ray 14 dataset, according to the receiver operating characteristic curve and area-under-the-curve score. An ablation study further confirmed the effectiveness of the global and local branch networks in improving the classification accuracy of thorax diseases.

show abstract

Intelligent crack extraction and analysis for tunnel structures with terrestrial laser scanning measurement

Cited by 31 publications

References 22 publications

Application of Terrestrial Laser Scanning (TLS) in the Architecture, Engineering and Construction (AEC) Industry

Application of Terrestrial Laser Scanning (TLS) in the Architecture, Engineering and Construction (AEC) Industry

PointCrack3D: Crack Detection in Unstructured Environments using a 3D-Point-Cloud-Based Deep Neural Network

Fusion High-Resolution Network for Diagnosing ChestX-ray Images

Contact Info

Product

Resources

About