ABSTRACT

CONTENTS 10.1 Introduction ............................................................................................. 180 10.2 Road Extraction from Remote Sensing Data...................................... 180

10.2.1 Modeling of Roads ................................................................... 180 10.2.2 Related Work on Road Extraction ......................................... 184 10.2.3 TUM-LOREX ............................................................................. 185

10.2.3.1 Model ......................................................................... 185 10.2.3.2 Extraction Strategy................................................... 186

10.3 Road Extraction from SAR Images ...................................................... 190 10.3.1 Model for Roads in SAR Images............................................ 191 10.3.2 Example: TUM-LOREX Applied to SAR Images ................ 192

10.3.2.1 Correction of the Near-Far Range Intensity Loss............................................................ 193

10.3.2.2 Speckle Reduction.................................................... 194 10.3.2.3 Data Scaling .............................................................. 194 10.3.2.4 Focus on Rural Areas .............................................. 194 10.3.2.5 Line Extraction with Steger’s Algorithm ............. 195 10.3.2.6 Evaluation of Linear Primitives ............................ 196

10.4 Extended Concepts for Road Extraction from SAR.......................... 197 10.4.1 Integration of Context .............................................................. 198

10.4.1.1 Local Context for Road Extraction from SAR Images............................................................... 198

10.4.1.2 Global Context for Road Extraction from SAR Images..................................................... 199

10.4.2 Integration of Road-Class-Specific Modeling: Example ‘‘Highways’’ .............................................................. 200 10.4.2.1 Model for Highways ............................................... 201 10.4.2.2 Extraction of Highways .......................................... 201

10.4.3 Multiaspect Fusion of SAR Images........................................ 202 10.4.3.1 Bayesian Fusion Approach .................................... 204 10.4.3.2 Examples ................................................................... 206

10.5 Discussion and Conclusion ................................................................... 210 Acknowledgment............................................................................................... 211 References ........................................................................................................... 212

Road extraction from remote sensing data has been of considerable interest in recent years due to the rapid progress of geographic information systems (GIS) and the increasing importance of roads in our daily life. Detailed and up-to-date road information is an important issue for numerous applications. Logistics, tourism, car navigation systems are just a few fields of interest. Yet, to accommodate for the needs of these applications, digital road information requires frequent updates, whereby the main source for road data collection is digital aerial and satellite imagery. Despite numerous technological advances, the process of data acquisition still needs a lot of manual interaction of a human operator, which is of course both timeconsuming and expensive. Consequently, much effort has been put into automatic road extraction approaches in recent years (Stilla et al., 2005).