On Constructing a Base Map for Collaborative Map

On Constructing a Base Map for Collaborative Map Generation and its Application in Urban Mobility Planning Maik Drodzynski, Stefan Edelkamp, Andreas Gaubatz, Shahid Jabbar, and Miguel Liebe Chair for Programming Systems, University of Dortmund, Germany Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe

Motivation n Problem: q q n Computer assisted urban mobility planning requires good vector maps. Good vector maps are not always available, especially for many third world countries. Solution: q q Web 2. 0 Collaborative map generation n GPS-Tracks, Wikimapia, Open Street Map, etc. Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe 2

Challenges and Solutions n Combining the GPS traces collected by people. q Through Computational Geometry algorithms n n n q AI clustering methods to combine these traces in order to infer road geometry n n n [Shahid Jabbar, Master’s Thesis, University of Freiburg, Germany, 2003] [Edelkamp, Jabbar, Willhalm, ITSC 2003] [Edelkamp, Jabbar, Willhalm, IEEE Transactions on ITS vol. 6 no. 1 (2005)] [Brüntrup, Edelkamp, Jabbar, Scholz, ITSC’ 05] A reliable integration of traces require a good base mapthat can act as the template. This paper discusses our approach to generate such a vector base map. q Borrows several techniques from Digital Image Processing and Computational Geometry. q Extracts calibrated road topology from raster maps. q Integrated with SUMO (by German Aerospace Agency, DLR ) Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe 3

Raster Maps • Can be collected easily from city authorities or through scanning paper maps. • A 2 D arrangement of pixels. • Raster Maps from Dortmund, Germany. • Collected from the City authority of Dortmund. Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe 4

Extraction of Road Surfaces § Streets’ extraction by color values. § Problem: Railway tracks and street names are also black! Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe 5

Erosion § Street names and railway tracks are eliminated. 3 x 3 Mask Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe 6

Dilatation § Street lines might become distorted by erosion Made thicker again. § Small holes due to street names are filled Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe 7

Other Filters n n n Morphological Opening and Closing Gap closing Fragment Elimination Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe §Smoothening of contours 8

Road Skeleton Computation § • Extraction Skeletonof ofthe a Pixel Map: A set of thin curves denoting the centerlines of the black surfaces. center lines of the surfaces. §thick. Medial Axis Transformation Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe 9

Graph Construction § Sweep-line paradigm : process pixels in columns § For each crossing, start a traversal in all possible directions! § Need a hash table to avoid duplicate work Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe 10

Graph Simplification n n Several thousands of nodes are generated! Not all are required or – more precisely – “interesting”. Employ a similar algorithm as Douglas-Peucker simplification. ε (epsilon) Co-linearity test Constructing a Base Map for Collaborative Map Generation (x 2, y 2) as the accuracy parameter (x 1, y 1) If d = 0, (x 2, y 2) can be deleted! (x 3, y 3) Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe 11

SUMO – Simulation for Urban Mobility (by DLR) n n A start-of-the-art tool for traffic simulation Used during FIFA-06 and Catholic Youth day, along with a Zeppelin to give real-time guidance to the traffic authority. Raster Maps Nodes + Edges in XML Raster to Vector Transformation Simulation Results SUMO Routes Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe 12

Integration with SUMO Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe 13

Summary n n n Urban mobility planning require a good vector map. Collaborative map generation needs a base map to correct the inaccuracies that can be added by people. Raster maps are inexpensive and widely available. Good quality maps can be obtained from the city authority. We propose: q q n Extract a vector map from a raster map. Digital Image Processing techniques can be helpful. Integrated with SUMO – a state-of-the-art tool for traffic simulation. Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe 14

Future extensions n Better image processing for Bridges – 3 D. Integration with lane information. Traffic Signals etc. n Special Thanks to: Daniel Krajzewicz at German Aerospace Agency (DLR) n n Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe 15

Thank You! Questions ? Constructing a Base Map for Collaborative Map Generation Drodzynski, Edelkamp, Gaubatz, Jabbar & Liebe