Automatic Lane Marking Extraction From Point Cloud Into Polygon Map Layer
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62156489%3A43110%2F17%3A43911676" target="_blank" >RIV/62156489:43110/17:43911676 - isvavai.cz</a>
Nalezeny alternativní kódy
RIV/00216305:26210/17:PU124412
Výsledek na webu
<a href="http://symposium.earsel.org/37th-symposium-Prague/wp-content/uploads/2016/06/2017_EARSeL_abstract_book.pdf" target="_blank" >http://symposium.earsel.org/37th-symposium-Prague/wp-content/uploads/2016/06/2017_EARSeL_abstract_book.pdf</a>
DOI - Digital Object Identifier
—
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Automatic Lane Marking Extraction From Point Cloud Into Polygon Map Layer
Popis výsledku v původním jazyce
Optimization of road networks is a common concern worldwide, primarily for safety purposes. Because the extent of these networks is substantial, automation of their inventory is highly desirable. This paper concentrates on the road inventory process that is necessary for regular maintenance. The key part of our road marking detection and reconstruction is based on spanning tree usage. The spanning trees are obtained from alpha shapes of the detected road markings. Application of the spanning trees enables the reliable identification of the road markings and precise reconstruction of the of their contours even with noisy data. Our method processes the point cloud data obtained from LiDAR measurements, and provides a common vector layer with road line polygons. Such a vector layer is stored in a common file format ESRI Shapefile supported by the majority of geographical information systems, thus producing an output that can be conveniently used for decision-making based on the road inventory process. Our key advantage is the ability to reconstruct the precise shapes of the road lane markings. The reconstructed shapes can be used for the visualization as well as for analytic purposes. Our approach is very reliable as shown in the results. We used two different testing areas. The first tested area is located in the Brno city centre in the Czech Republic, particularly in the vicinity of the Mendel Square. It comprises common streets and squares. The roads contain multiple road lanes for cars as well as separate lanes for trams and trolleybuses. The second tested area is the country round near Semice town in the Czech Republic. The true positive rate of detection is in all cases above 92 %. Therefore, we are able to detect correctly vast majority of road lane markings.
Název v anglickém jazyce
Automatic Lane Marking Extraction From Point Cloud Into Polygon Map Layer
Popis výsledku anglicky
Optimization of road networks is a common concern worldwide, primarily for safety purposes. Because the extent of these networks is substantial, automation of their inventory is highly desirable. This paper concentrates on the road inventory process that is necessary for regular maintenance. The key part of our road marking detection and reconstruction is based on spanning tree usage. The spanning trees are obtained from alpha shapes of the detected road markings. Application of the spanning trees enables the reliable identification of the road markings and precise reconstruction of the of their contours even with noisy data. Our method processes the point cloud data obtained from LiDAR measurements, and provides a common vector layer with road line polygons. Such a vector layer is stored in a common file format ESRI Shapefile supported by the majority of geographical information systems, thus producing an output that can be conveniently used for decision-making based on the road inventory process. Our key advantage is the ability to reconstruct the precise shapes of the road lane markings. The reconstructed shapes can be used for the visualization as well as for analytic purposes. Our approach is very reliable as shown in the results. We used two different testing areas. The first tested area is located in the Brno city centre in the Czech Republic, particularly in the vicinity of the Mendel Square. It comprises common streets and squares. The roads contain multiple road lanes for cars as well as separate lanes for trams and trolleybuses. The second tested area is the country round near Semice town in the Czech Republic. The true positive rate of detection is in all cases above 92 %. Therefore, we are able to detect correctly vast majority of road lane markings.
Klasifikace
Druh
O - Ostatní výsledky
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
—
Návaznosti
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Ostatní
Rok uplatnění
2017
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů