Grant: Engage Grants Program
York University
$24,850.00
Road sign extraction from mobile lidar and camera data
EF 2012-13
Résumé
Applications such as road infrastructure management, accurate 3D modeling and road navigation require
detailed and accurate road asset inventory consisting of location, geometry and attribute characteristics of road
features. Commercial mobile mapping systems are often used to locate and catalogue road and road side
features such as signs, poles, lane markings, curbs, and pavement extents. Traditionally this has been done
interactively through the manual location and classification of a feature by having an operator manipulate then
place the feature in the digital data set. This is a laborious, tedious and time consuming task.
The objective of this project is the development of algorithms to automatically detect, locate identify and
classify high reflectance roadside and overhead signs from high volumes of accurately 3D point cloud data and
captured road features using Optech's Lynx mobile mapper. It collects terrain features with unprecedented
detail using lidar sensors with multiple perspective lidar imaging, 4 onboard imaging cameras, and a
navigation system . The size of the data (millions of points) makes it almost prohibited to interactively detect
and extracting road signs. The goal is to automatically identify signs, categorize their type and place a CAD
feature on the appropriate geographical layer. Two main algorithms will be developed: a) the sign localization
algorithm to detect and localize the signs from the 3D point clouds and determine its location on the optimum
image frame the sign appears, and b) the sign classification algorithm to identify and classify the detected road
signs.
Programme
Engage Grants Program
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data
Tel que publié
Application id
434818-2012
Name nom
Armenakis, (Constadinos)Costas
Department département
Earth and Space Science and Engineering
Organization id
38
Institution établissement
York University
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2012
Competition year année de concours
2012
Award amount
24850
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1553
Committee name en
Ontario Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Ontario
Area of application code
1206
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Engineering
Area of application fr
Génie
Research subject code
2700
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Information technology
Research subject fr
Technologie de l'information
Partie
1
Nb partie
1
Application title
Road sign extraction from mobile lidar and camera data
Keyword
NSERC
Application summary
Applications such as road infrastructure management, accurate 3D modeling and road navigation require
detailed and accurate road asset inventory consisting of location, geometry and attribute characteristics of road
features. Commercial mobile mapping systems are often used to locate and catalogue road and road side
features such as signs, poles, lane markings, curbs, and pavement extents. Traditionally this has been done
interactively through the manual location and classification of a feature by having an operator manipulate then
place the feature in the digital data set. This is a laborious, tedious and time consuming task.
The objective of this project is the development of algorithms to automatically detect, locate identify and
classify high reflectance roadside and overhead signs from high volumes of accurately 3D point cloud data and
captured road features using Optech's Lynx mobile mapper. It collects terrain features with unprecedented
detail using lidar sensors with multiple perspective lidar imaging, 4 onboard imaging cameras, and a
navigation system . The size of the data (millions of points) makes it almost prohibited to interactively detect
and extracting road signs. The goal is to automatically identify signs, categorize their type and place a CAD
feature on the appropriate geographical layer. Two main algorithms will be developed: a) the sign localization
algorithm to detect and localize the signs from the 3D point clouds and determine its location on the optimum
image frame the sign appears, and b) the sign classification algorithm to identify and classify the detected road
signs.