Center for Machine Learning and Intelligent Systems
About  Citation Policy  Donate a Data Set  Contact

Repository Web            Google
View ALL Data Sets

× Check out the beta version of the new UCI Machine Learning Repository we are currently testing! Contact us if you have any issues, questions, or concerns. Click here to try out the new site.

3D Road Network (North Jutland, Denmark) Data Set
Download: Data Folder, Data Set Description

Abstract: 3D road network with highly accurate elevation information (+-20cm) from Denmark used in eco-routing and fuel/Co2-estimation routing algorithms.

Data Set Characteristics:  

Sequential, Text

Number of Instances:




Attribute Characteristics:


Number of Attributes:


Date Donated


Associated Tasks:

Regression, Clustering

Missing Values?


Number of Web Hits:



Manohar Kaul, Department of Computer Science, Aarhus University, Denmark (mkaul '@'

Data Set Information:

This dataset was constructed by adding elevation information to a 2D road network in North Jutland, Denmark (covering a region of 185 x 135 km^2). Elevation values where extracted from a publicly available massive Laser Scan Point Cloud for Denmark (available at : [Web Link] (Bottom-most dataset)). This 3D road network was eventually used for benchmarking various fuel and CO2 estimation algorithms. This dataset can be used by any applications that require to know very
accurate elevation information of a road network to perform more accurate routing for eco-routing, cyclist routes etc. For the data mining and machine learning community, this dataset can be used as 'ground-truth' validation in spatial mining techniques and satellite image processing. It has no class labels, but can be used in unsupervised learning and regression to guess some missing elevation information for some points on the road.
The work was supported by the Reduction project that is funded by the European Comission as FP7-ICT-2011-7 STREP project number 288254.

Attribute Information:

1. OSM_ID: OpenStreetMap ID for each road segment or edge in the graph.
2. LONGITUDE: Web Mercaptor (Google format) longitude
3. LATITUDE: Web Mercaptor (Google format) latitude
4. ALTITUDE: Height in meters.

Note: OSM_ID is the ID assigned by OpenStreetMaps ([Web Link]) to the road segments. Each (long,lat,altitude) point on a road segment (with unique OSM ID) is sorted in the same order as they appear on the road. So a 3D-polyline can be drawn by joining points of each row for each OSM_ID road segment.

Relevant Papers:

[1] Chenjuan Guo, Yu Ma, Bin Yang, Christian S. Jensen, Manohar Kaul: EcoMark: evaluating models of vehicular environmental impact. SIGSPATIAL/GIS 2012: 269-278

Citation Request:

Use of this dataset in publications must be acknowledged by referencing the following publication:

Building Accurate 3D Spatial Networks to Enable Next Generation Intelligent Transportation Systems (Accepted and to be published in June)
Proceedings of International Conference on Mobile Data Management (IEEE MDM), June 3-6 2013, Milan, Italy

Supported By:

 In Collaboration With:

About  ||  Citation Policy  ||  Donation Policy  ||  Contact  ||  CML