The reliability of RANSAC method when estimating geometric object parameters

Urbančič, Tilen; Vrečko, Anja; Kregar, Klemen

doi:10.15292/geodetski-vestnik.2016.01.69-97

Cited by 8 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…RANSAC is a semi-automatic method for segmenting planes with specific given user parameters such as maximum distance to the plane, surface normal deviation, and minimum points of primitive geometry, and then the road surface can be estimated. The basic principle of the RANSAC algorithm is the estimation of the plane that defines the mathematical model covering the maximum points for the calculation of optimum parameters with minimum error ( 48 ). After the plane model is determined by the highest number of ground points, the distances to the plane should be calculated to remove the points outside the road surface.…”

Section: Methodsmentioning

confidence: 99%

Extraction of Road Lane Markings from Mobile LiDAR Data

Zeybek

2021

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

This study presents a method for automatic extraction of road lane markings from mobile light detection and ranging (LiDAR) data. Road lanes and traffic signs on the road surface provide safe driving for drivers and aid traffic flow movement along the highway and street. Mobile LiDAR systems acquire massive datasets very quickly in a short time. To simplify the data structure and feature extraction, it is essential for traffic management personnel to apply the right methods. Road lanes must be visible and are a major factor in road safety for drivers. In this study, a methodology is devised and implemented for the extraction of features such as dashed lines, continuous lanes, and direction arrows on the pavement from point clouds. Point cloud data was collected from the Riegl VMX-450 mobile LiDAR system. The alpha shape algorithm is implemented on a point cloud and compared with the widespread use of edge detection techniques applied for intensity-based raster images. The proposed methodology directly extracts three-dimensional and two-dimensional road features to control the quality of road markings and spatial positions with the obtained marking boundaries. State-of-the-art results are obtained and compared with manually digitized reference markings. The standard deviations were evaluated and acquired for intensity image-based and direct point cloud-based extractions, at 1.2 cm and 1.7 cm, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Extraction of Road Lane Markings from Mobile LiDAR Data

Zeybek

2021

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

show abstract

“…The coordinates of the reference target points of all volume targets, both spheres and the cone, were defined with the least squares method, which is described in Reference [74]. The parameters of the geometric forms were obtained by solving the mathematical model.…”

Section: Methodsmentioning

confidence: 99%

New Target for Accurate Terrestrial Laser Scanning and Unmanned Aerial Vehicle Point Cloud Registration

Urbančič

Roškar²,

Fras

et al. 2019

Sensors

Self Cite

View full text Add to dashboard Cite

The main goal of our research was to design and implement an innovative target that would be suitable for accurately registering point clouds produced from unmanned aerial vehicle (UAV) images and terrestrial laser scans. Our new target is composed of three perpendicular planes that combine the properties of plane and volume targets. The new target enables the precise determination of reference target points in aerial and terrestrial point clouds. Different types of commonly used plane and volume targets as well as the new target were placed in an established test area in order to evaluate their performance. The targets were scanned from multiple scanner stations and surveyed with an unmanned aerial vehicle DJI Phantom 4 PRO at three different altitudes (20, 40, and 75 m). The reference data were measured with a Leica Nova MS50 MultiStation. Several registrations were performed, each time with a different target. The quality of these registrations was assessed on the check points. The results showed that the new target yielded the best results in all cases, which confirmed our initial expectations. The proposed new target is innovative and not difficult to create and use.

show abstract

“…In the third step ( Figure 10 ) we used the RANSAC algorithm [ 21 , 22 ]. We used this algorithm to fine filter and eliminate the roughly misplaced points that could not be defined as points in the vicinity of the rails during the manual filtering process.…”

Section: Measurement Methods and Computationsmentioning

confidence: 99%

Control Measurements of Crane Rails Performed by Terrestrial Laser Scanning

Kregar

Možina²,

Ambrožič

et al. 2017

Sensors

Self Cite

View full text Add to dashboard Cite

This article presents a method for measuring the geometry of crane rails with terrestrial laser scanning (TLS). Two sets of crane rails were divided into segments, their planes were adjusted, and the characteristic rail lines were defined. We used their profiles to define the positional and altitude deviations of the rails, the span and height difference between the two rails, and we also verified that they complied with the Eurocode 3 standard. We tested the method on crane rails at the hydroelectric power plant in Krško and the thermal power plant in Brestanica. We used two scanning techniques: “pure” TLS (Riegel VZ-400) and “hybrid” TLS (Leica MS50) scanning. This article’s original contribution lies in the detailed presentation of the computations used to define the characteristic lines of the rails without using the numeric procedures from existing software packages. We also analysed the influence of segment length and point density on the rail geometry results, and compared the two laser scanning techniques. We also compared the results obtained by terrestrial laser scanning with the results obtained from the classic polar method, which served as a reference point for its precision.

show abstract

The reliability of RANSAC method when estimating geometric object parameters

Cited by 8 publications

References 14 publications

Extraction of Road Lane Markings from Mobile LiDAR Data

Extraction of Road Lane Markings from Mobile LiDAR Data

New Target for Accurate Terrestrial Laser Scanning and Unmanned Aerial Vehicle Point Cloud Registration

Control Measurements of Crane Rails Performed by Terrestrial Laser Scanning

Contact Info

Product

Resources

About