Planar Projection of Mobile Laser Scanning Data in Tunnels

Gonçalves, José Alberto; Mendes, Renato; Araújo, Emanuel; Oliveira, Adriano Q. de; Boavida, João

doi:10.5194/isprsarchives-xxxix-b3-109-2012

Cited by 5 publications

(8 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They recommended employing LiDAR sensors since they provide fast data acquisition and full surface characterization and they do not need geo-referencing. Goncalves et al [ 16 ] inspected the cross sectional deformation of a subway tunnel from MLS data by employing image processing techniques. Once the cross sections are extracted, they are converted into 2D images, which are further analyzed by image processing techniques.…”

Section: Literature Reviewmentioning

confidence: 99%

Automated As-Built Model Generation of Subway Tunnels from Mobile LiDAR Data

Arastounia

2016

Sensors

View full text Add to dashboard Cite

This study proposes fully-automated methods for as-built model generation of subway tunnels employing mobile Light Detection and Ranging (LiDAR) data. The employed dataset is acquired by a Velodyne HDL 32E and covers 155 m of a subway tunnel containing six million points. First, the tunnel’s main axis and cross sections are extracted. Next, a preliminary model is created by fitting an ellipse to each extracted cross section. The model is refined by employing residual analysis and Baarda’s data snooping method to eliminate outliers. The final model is then generated by applying least squares adjustment to outlier-free data. The obtained results indicate that the tunnel’s main axis and 1551 cross sections at 0.1 m intervals are successfully extracted. Cross sections have an average semi-major axis of 7.8508 m with a standard deviation of 0.2 mm and semi-minor axis of 7.7509 m with a standard deviation of 0.1 mm. The average normal distance of points from the constructed model (average absolute error) is also 0.012 m. The developed algorithm is applicable to tunnels with any horizontal orientation and degree of curvature since it makes no assumptions, nor does it use any a priori knowledge regarding the tunnel’s curvature and horizontal orientation.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Automated As-Built Model Generation of Subway Tunnels from Mobile LiDAR Data

Arastounia

2016

Sensors

View full text Add to dashboard Cite

show abstract

“…For local referencing, tunnel geometry serves as a nominal constraint for adjusting the navigation trajectory and the mapping data [23]. Since the INS usually maintains short-term precision (depending on the IMU's quality), the relative precision within a segment of point cloud data is sufficient to describe the mapped object.…”

Section: Localized Tunnel Projectionmentioning

confidence: 99%

Conceptual Issues Regarding the Development of Underground Railway Laser Scanning Systems

Hung

King

Chen

2015

IJGI

View full text Add to dashboard Cite

Mobile Laser Scanning (MLS) systems are widely applied for spatial data collection and support applications in many aspects. In recent years, MLS technology had been introduced to railway applications and greatly enhanced the spatial detail and efficiency when compared to traditional approaches. However, the advance of MLS technology is not completely applied to railway environment. Typical MLS systems rely on integrated navigation through the use of Inertial Navigation Systems (INS) and Global Navigation Satellite Systems (GNSS) for geo-referencing, while operation under long-term GNSS outages or even GNSS-free environments, such as underground railway or long tunnels, remains a challenging issue due to the degraded operation of standalone inertial navigation. Commercial MLS systems usually employ high performance inertial measurement units (IMU) and various strategies to manage GNSS outages, but GNSS components are still necessary prior to and after experiencing the loss of GNSS signals. To tackle the problem of permanent GNSS outages, alternative methods are introduced to replace the GNSS and so allow the use of MLS systems in GNSS-free underground railway environments. Such approaches encourage the MLS systems to be developed into the Underground Railway Laser Scanning (URLS) systems, which may provide several alternative operational functions for the management of underground railway operation.

show abstract

“…Zhou et al [15] extracted the track line based on 3D linear fitting for the rail tunnel point cloud after slicing, to obtain the central line of the tunnel based on the track line. The segmented projection method proposed by Gonçalves et al [16] was sensitive to discrete points, and manual adjustment of outliers was required. The tunnel sections can be used to detect the profile of the tunnel section, but it is not enough to complete more flexible 3D feature recognition.…”

Section: Introductionmentioning

confidence: 99%

“…Related research focuses on the volume calculation of the overbreak and the blasting characteristics of the rock surface [2,18,19]. The research about tunnel feature detection focus on the underground surface monitoring and the deformed cross-section of the completed tunnel [11,15,16]. For the treatment of disordered, rough, and multiple types of point clouds, researchers usually visualize and store them for post-processing by interactive software [16,20,21,22], which is not suitable for automated construction scenarios.…”

Section: Introductionmentioning

confidence: 99%

“…The research about tunnel feature detection focus on the underground surface monitoring and the deformed cross-section of the completed tunnel [11,15,16]. For the treatment of disordered, rough, and multiple types of point clouds, researchers usually visualize and store them for post-processing by interactive software [16,20,21,22], which is not suitable for automated construction scenarios. Lai et al [21] proposed a new method for building an index of a point cloud of multiple tubular types of curved surfaces similar to a tunnel.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Tunnel Steel Arches Extraction Algorithm Based on 3D LiDAR Point Cloud

Zhang

Qiu

Song

et al. 2019

Sensors

View full text Add to dashboard Cite

Automation is an inevitable trend in the development of tunnel shotcrete machinery. Tunnel environmental perception based on 3D LiDAR point cloud has become a research hotspot. Current researches about the detection of tunnel point clouds focus on the completed tunnel with a smooth surface. However, few people have researched the automatic detection method for steel arches installed on a complex rock surface. This paper presents a novel algorithm to extract tunnel steel arches. Firstly, we propose a refined function for calibrating the tunnel axis by minimizing the density variance of the projected point cloud. Secondly, we segment the rock surface from the tunnel point cloud by using the region-growing method with the parameters obtained by analyzing the tunnel section sequence. Finally, a Directed Edge Growing (DEG) method is proposed to detect steel arches on the rock surface in the tunnel. Our experiment in the highway tunnels under construction in Changsha (China) shows that the proposed algorithm can effectively extract the points of the edge of steel arches from 3D LiDAR point cloud of the tunnel without manual assistance. The results demonstrated that the proposed algorithm achieved 92.1% of precision, 89.1% of recall, and 90.6% of the F-score.

show abstract

Planar Projection of Mobile Laser Scanning Data in Tunnels

Cited by 5 publications

References 2 publications

Automated As-Built Model Generation of Subway Tunnels from Mobile LiDAR Data

Automated As-Built Model Generation of Subway Tunnels from Mobile LiDAR Data

Conceptual Issues Regarding the Development of Underground Railway Laser Scanning Systems

Automatic Tunnel Steel Arches Extraction Algorithm Based on 3D LiDAR Point Cloud

Contact Info

Product

Resources

About