Stefan Hinz 
  
Whereas the fine scale gives detailed 
information, the coarse scale adds 
global information. Because of the 
abstraction in coarse scale, additional 
correct hypotheses for roads can be 
found and sometimes also false ones 
can be eliminated based on topological 
criteria, while details, like exact width 
and position of the lanes and markings, Fine scale 
from fine scale are integrated. In this M + 
way the extraction benefits from both : 
scales. 
Figure 2: Road model 
Road network 
connects 
Road link J = === === === === 
Simple 
       
— ——- Part-of relation 
         
   
— Specialization 
— Concrete relation 
  
Road Te Complex junction ===# General relation between objects 
y 1 
     
  
    
  
    
   
Coarse scale 
“is parallel 
      
     
  
      
  
   
  
Line-shaped 
marking 
3.3 Context Model 
  
  
       
  
     
   
   
  
      
  
  
' Real world 
The road model presented above com- — ---1----——1--—-—-—--———[ilií—-i eeeeB—————- 
. . . É c ' 
prises knowledge about radiometric, Fendt | Com HIE Geometry and 
. 5 concrete or concrete or | | : 
geometric, and topological character- colored line) colored ne} | symbols J | asphalt region | (asphatt region] : Material 
istics of roads. This model is ex- ed idis | hegesenente | iioii rupem un deseo stein 0700-7202: rion 
tended by knowledge about context: Long Short Bag) |. Frongated _) {Compact} Y [ Snape Image 
bright line bright line symbols bright region bright region : bright line 
So-called context objects, i.e. back- 
ground objects like buildings, trees, or 
vehicles, can support road extraction, but they can also interfere (see the discussion of Sect. 3.1). Also, external GIS data 
can be regarded as context object. Experience has shown that modeling this interaction between road objects and context 
objects on a local level as well as a global level is an aid for guiding the extraction since the interpretation problem is split 
into smaller sub-problems which can be solved more efficiently by using specific models and extraction strategies. 
  
In order to capture the varying appearance of roads globally, we distinguish between the context regions urban, forest, 
and rural (cf. (Baumgartner et al., 1997)). Furthermore, we model the local context with so-called context relations, i.e., 
certain relations between a small number of road and context objects. For typical context relations in the rural context 
region, we refer the reader to (Baumgartner et al., 1997). In the following we turn our focus on context relations in the 
urban context region (see Fig. 3). 
33 1* . . : (vehicle ) Beten) Iding GIS road axis Context objec 
Almost every building in the real world is connected with the = aro ries EN 
road network. The denser the settlement is, the closer the build- .......... RU MA 
: is approximately : 
ings move to the road, and the more parallel is their outline with {astsshadowoni : occludes : 
arallel to 
the road sides . Therefore, this context relation gets moreuseful — "r7 ^r 077 ^ EC RPG Mic i 
for the extraction in downtown areas, where, in some extreme E n Rosas 
cases, roads and junctions are purely defined by the building —— |. ^ w |  ..— E 
outlines. Vice-versa, buildings or other high objects standing "US nin t aif 
close to the road potentially occlude larger parts of it or cast ber. eui Lens 
shadows on it. Hence, a context relation "occlusion", gives rise Te Suesmicturs 
to select another image providing a better view on that particular 
part of the scene, whereas a context relation "shadow" can tell Figure 3: Context relations for urban areas 
an extraction algorithm to choose modified parameter settings. 
Both context relations imply that roads lie beneath the surrounding objects. Consequently, there is no need to search for 
roads on locally high objects. 
For some settlements, road axes might be available digitally. Such kind of information can be integrated in a very con- 
sistent way by using a context relation that models parallelism and closeness between an extracted piece of road and the 
mapped road axis. With such a context relation, cues are provided where a road might be present. Nevertheless, the 
extraction has to prove independently if the road truly exists. 
Vehicles are related with a road, or more specifically, with a lane segment by means of occluding the lane's pavement. 
However, since vehicles drive or stand collinear with the a lane (at least in most cases), we can directly use a detected 
vehicle or vehicle convoy for road extraction — in particular, we treat a detected vehicle as lane segment. By doing so, we 
need not to take care of moving vehicles if we want to fuse extraction results achieved from images taken at a different 
time. 
In addition to relations between road and context objects, we also consider relations between the object and its sub- 
structures. This is best exemplified with orthogonal markings at the end of a lane. In most cases, they define the end of a 
lane and relate it to a junction. Fig. 3 summarizes the relations between road objects, context objects, and sub-structures 
by using the concepts "Lane segment" and "Junction" as the basic entities of a road network. 
Note, however, that the use of knowledge about local context and the verification of specific relations between local objects 
  
408 International Archives of Photogrammetry and Remote Sensing. Vol. XXXIII, Part B3. Amsterdam 2000.