@misc{benito_automatic_nodate,
	title = {Automatic {3D} modelling of train  rails in a lidar point cloud},
	abstract = {Rail track irregularities have a large effect on rail
way safety and operation. To ensure a good maintenance 
of the rails, frequent measurements are needed, which are costly and require specific tools for different 
aspects of the rails geometry. Laser scanning offers 
the advantage of acquiring accurate 3D measurements 
of all the objects present in the railway environment in a short operational time. While some work has 
been done to detect the presence of rails and other objects in the point cloud, the modelling of those 
objects has received little attention. Such models not 
only enable all sorts of measurements about the rail 
geometry, but also facilitate simulations in train re
search. The purpose of this thesis is to develop a 
method to automatically build a 3D model of train 
rails from a point cloud where the rails have been 
already detected. First of all, the rail point cloud is se
ctioned into pieces of equal length. The points laying 
in each of the planes of the head of the rail are th
en identified. A non-linear least squares adjustment is 
used to find the parameters of the model pieces that best fit into the point cloud by minimizing the 
distance from the points to their corresponding planes. Finally, the model pieces are adjusted globally 
using a 6 dimensional non-rational Bezier curve, which yiel
ds a set of rail profiles that can be connected to 
build the final model representing the curved shape of
 the rail. The final model is validated by computing 
the distance from each point in the point cloud to 
the end model. The results showed that 90\% of the 
points were at less than 1 cm distance to the recons
tructed model, while the mean distance is 0.5 cm and 
95\% of the points were at less than 1.4 cm. Althou
gh the results are dependent on the accuracy of 
acquisition and detection methods, the overall performance of the method demonstrates that it is possible 
to model the train rails accurately by surface fitting and curvature adjustment.},
	author = {Benito, Daniel Diaz},
}

{"_id":"8EqymgpBxZDb8fGgi","bibbaseid":"benito-automatic3dmodellingoftrainrailsinalidarpointcloud","author_short":["Benito, D. D."],"bibdata":{"bibtype":"misc","type":"misc","title":"Automatic 3D modelling of train rails in a lidar point cloud","abstract":"Rail track irregularities have a large effect on rail way safety and operation. To ensure a good maintenance of the rails, frequent measurements are needed, which are costly and require specific tools for different aspects of the rails geometry. Laser scanning offers the advantage of acquiring accurate 3D measurements of all the objects present in the railway environment in a short operational time. While some work has been done to detect the presence of rails and other objects in the point cloud, the modelling of those objects has received little attention. Such models not only enable all sorts of measurements about the rail geometry, but also facilitate simulations in train re search. The purpose of this thesis is to develop a method to automatically build a 3D model of train rails from a point cloud where the rails have been already detected. First of all, the rail point cloud is se ctioned into pieces of equal length. The points laying in each of the planes of the head of the rail are th en identified. A non-linear least squares adjustment is used to find the parameters of the model pieces that best fit into the point cloud by minimizing the distance from the points to their corresponding planes. Finally, the model pieces are adjusted globally using a 6 dimensional non-rational Bezier curve, which yiel ds a set of rail profiles that can be connected to build the final model representing the curved shape of the rail. The final model is validated by computing the distance from each point in the point cloud to the end model. The results showed that 90% of the points were at less than 1 cm distance to the recons tructed model, while the mean distance is 0.5 cm and 95% of the points were at less than 1.4 cm. Althou gh the results are dependent on the accuracy of acquisition and detection methods, the overall performance of the method demonstrates that it is possible to model the train rails accurately by surface fitting and curvature adjustment.","author":[{"propositions":[],"lastnames":["Benito"],"firstnames":["Daniel","Diaz"],"suffixes":[]}],"bibtex":"@misc{benito_automatic_nodate,\n\ttitle = {Automatic {3D} modelling of train rails in a lidar point cloud},\n\tabstract = {Rail track irregularities have a large effect on rail\nway safety and operation. To ensure a good maintenance \nof the rails, frequent measurements are needed, which are costly and require specific tools for different \naspects of the rails geometry. Laser scanning offers \nthe advantage of acquiring accurate 3D measurements \nof all the objects present in the railway environment in a short operational time. While some work has \nbeen done to detect the presence of rails and other objects in the point cloud, the modelling of those \nobjects has received little attention. Such models not \nonly enable all sorts of measurements about the rail \ngeometry, but also facilitate simulations in train re\nsearch. The purpose of this thesis is to develop a \nmethod to automatically build a 3D model of train \nrails from a point cloud where the rails have been \nalready detected. First of all, the rail point cloud is se\nctioned into pieces of equal length. The points laying \nin each of the planes of the head of the rail are th\nen identified. A non-linear least squares adjustment is \nused to find the parameters of the model pieces that best fit into the point cloud by minimizing the \ndistance from the points to their corresponding planes. Finally, the model pieces are adjusted globally \nusing a 6 dimensional non-rational Bezier curve, which yiel\nds a set of rail profiles that can be connected to \nbuild the final model representing the curved shape of\n the rail. The final model is validated by computing \nthe distance from each point in the point cloud to \nthe end model. The results showed that 90\\% of the \npoints were at less than 1 cm distance to the recons\ntructed model, while the mean distance is 0.5 cm and \n95\\% of the points were at less than 1.4 cm. Althou\ngh the results are dependent on the accuracy of \nacquisition and detection methods, the overall performance of the method demonstrates that it is possible \nto model the train rails accurately by surface fitting and curvature adjustment.},\n\tauthor = {Benito, Daniel Diaz},\n}\n\n","author_short":["Benito, D. D."],"key":"benito_automatic_nodate","id":"benito_automatic_nodate","bibbaseid":"benito-automatic3dmodellingoftrainrailsinalidarpointcloud","role":"author","urls":{},"metadata":{"authorlinks":{}},"html":""},"bibtype":"misc","biburl":"https://bibbase.org/zotero/sede","dataSources":["pQYee5oovEhJF75n6"],"keywords":[],"search_terms":["automatic","modelling","train","rails","lidar","point","cloud","benito"],"title":"Automatic 3D modelling of train rails in a lidar point cloud","year":null}