Pole-Like Road Object Detection From Mobile Lidar System Using a Coarse-to-Fine Approach

Teo, Tee-Ann; Chiu, Chi-Min

doi:10.1109/jstars.2015.2467160

Cited by 50 publications

(26 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The detection rate for the three data sets tested were 83%, 91% and 83% by the method of El-Halawany and Lichti [8], respectively. The detection rate was about 90% by the method of Teo and Chiu [36]. The method of Rodríguez-Cuenca, et al [24] detected rates in the two datasets at 94.3% and 95.7%.…”

Section: Comparison With Previous Methodsmentioning

confidence: 84%

“…These ground points include a large number of redundant points. If the ground points are effectively removed, the efficiency of subsequent detection and extraction of the PLOs is improved [36,37]. In order to filter ground points, Zhang, et al [38] used progressive window algorithm based on the mathematical morphology ground filtering method.…”

Section: Ground Points Filteringmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Recognition of Pole-Like Objects from Mobile Laser Scanning Point Clouds

et al. 2018

View full text Add to dashboard Cite

Mobile Laser Scanning (MLS) point cloud data contains rich three-dimensional (3D) information on road ancillary facilities such as street lamps, traffic signs and utility poles. Automatically recognizing such information from point cloud would provide benefits for road safety inspection, ancillary facilities management and so on, and can also provide basic information support for the construction of an information city. This paper presents a method for extracting and classifying pole-like objects (PLOs) from unstructured MLS point cloud data. Firstly, point cloud is preprocessed to remove outliers, downsample and filter ground points. Then, the PLOs are extracted from the point cloud by spatial independence analysis and cylindrical or linear feature detection. Finally, the PLOs are automatically classified by 3D shape matching. The method was tested based on two point clouds with different road environments. The completeness, correctness and overall accuracy were 92.7%, 97.4% and 92.3% respectively in Data I. For Data II, that provided by International Society for Photogrammetry and Remote Sensing Working Group (ISPRS WG) III/5 was also used to test the performance of the method, and the completeness, correctness and overall accuracy were 90.5%, 97.1% and 91.3%, respectively. Experimental results illustrate that the proposed method can effectively extract and classify PLOs accurately and effectively, which also shows great potential for further applications of MLS point cloud data.

show abstract

Section: Comparison With Previous Methodsmentioning

confidence: 84%

Section: Ground Points Filteringmentioning

confidence: 99%

Automatic Recognition of Pole-Like Objects from Mobile Laser Scanning Point Clouds

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The process involves identifying required parameters to shape segmented point clouds into parametric or polyhedral model components describing individual building elements (Teo and Chiu, 2015) , and then connecting all components using CSG (Constructive Solid Geometry) or similar algorithms to form a barebones model representing the skeleton structure of the target. If necessary, additional levels of detail of the bare-bones model can be achieved using procedural (Koehl and Roussel, 2015) or projected generalization algorithms.…”

Section: Proposed Methodologymentioning

confidence: 99%

Combining 3d Volume and Mesh Models for Representing Complicated Heritage Buildings

Tsai

Chang

Lin

2017

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:This study developed a simple but effective strategy to combine 3D volume and mesh models for representing complicated heritage buildings and structures. The idea is to seamlessly integrate 3D parametric or polyhedral models and mesh-based digital surfaces to generate a hybrid 3D model that can take advantages of both modeling methods. The proposed hybrid model generation framework is separated into three phases. Firstly, after acquiring or generating 3D point clouds of the target, these 3D points are partitioned into different groups. Secondly, a parametric or polyhedral model of each group is generated based on plane and surface fitting algorithms to represent the basic structure of that region. A "bare-bones" model of the target can subsequently be constructed by connecting all 3D volume element models. In the third phase, the constructed bare-bones model is used as a mask to remove points enclosed by the bare-bones model from the original point clouds. The remaining points are then connected to form 3D surface mesh patches. The boundary points of each surface patch are identified and these boundary points are projected onto the surfaces of the bare-bones model. Finally, new meshes are created to connect the projected points and original mesh boundaries to integrate the mesh surfaces with the 3D volume model. The proposed method was applied to an open-source point cloud data set and point clouds of a local historical structure. Preliminary results indicated that the reconstructed hybrid models using the proposed method can retain both fundamental 3D volume characteristics and accurate geometric appearance with fine details. The reconstructed hybrid models can also be used to represent targets in different levels of detail according to user and system requirements in different applications.

show abstract

“…Although the results of these methods are often effective in using the data from a practical perspective, the fact remains that there can still be a significant loss of information from the ignored data. Without removing the points during the partition procedure, other methods divide the data into sections or tiles, such that each section can be processed separately to reduce the computation complexity (e.g., Chen, et al [6], Holgado-Barco, et al [8], Wu, et al [10], Soilán, et al [16], Jung, et al [17], Teo and Chiu [19], Pu, et al [23]). Furthermore, depending on the desired analysis, the refinement of the data partition can be achieved by merging multiple profiles to generate a series of overlapping tiles (e.g., Zai, et al [11], Wang, et al [20]), or by dividing a profile based on some other constraints, such as the slope of the roadway (e.g., Wang, et al [9]).…”

Section: Introductionmentioning

confidence: 99%

“…They also consider the scan angle in bounding that estimate. Similarly, Teo and Chiu [19] first estimate the elevation of the road, using the height of the trajectory, and then based on the normal vector and horizontal range to the road centerlines generated from the trajectory, the road surface is segmented. Holgado-Barco, et al [8] also extract the ground points by considering scan angles within a given range threshold.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Framework for Mobile Lidar Trajectory Reconstruction and Mo-norvana Segmentation

Che

Olsen

2019

Remote Sensing

View full text Add to dashboard Cite

Mobile laser scanning (MLS, or mobile lidar) is a 3-D data acquisition technique that has been widely used in a variety of applications in recent years due to its high accuracy and efficiency. However, given the large data volume and complexity of the point clouds, processing MLS data can be still challenging with respect to effectiveness, efficiency, and versatility. This paper proposes an efficient MLS data processing framework for general purposes consisting of three main steps: trajectory reconstruction, scan pattern grid generation, and Mo-norvana (Mobile Normal Variation Analysis) segmentation. We present a novel approach to reconstructing the scanner trajectory, which can then be used to structure the point cloud data into a scan pattern grid. By exploiting the scan pattern grid, point cloud segmentation can be performed using Mo-norvana, which is developed based on our previous work for processing Terrestrial Laser Scanning (TLS) data, normal variation analysis (Norvana). In this work, with an unorganized MLS point cloud as input, the proposed framework can complete various tasks that may be desired in many applications including trajectory reconstruction, data structuring, data visualization, edge detection, feature extraction, normal estimation, and segmentation. The performance of the proposed procedures are experimentally evaluated both qualitatively and quantitatively using multiple MLS datasets via the results of trajectory reconstruction, visualization, and segmentation. The efficiency of the proposed method is demonstrated to be able to handle a large dataset stably with a fast computation speed (about 1 million pts/sec. with 8 threads) by taking advantage of parallel programming.

show abstract

Pole-Like Road Object Detection From Mobile Lidar System Using a Coarse-to-Fine Approach

Cited by 50 publications

References 23 publications

Automatic Recognition of Pole-Like Objects from Mobile Laser Scanning Point Clouds

Automatic Recognition of Pole-Like Objects from Mobile Laser Scanning Point Clouds

Combining 3d Volume and Mesh Models for Representing Complicated Heritage Buildings

An Efficient Framework for Mobile Lidar Trajectory Reconstruction and Mo-norvana Segmentation

Contact Info

Product

Resources

About