International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XXXV, Part B2. Istanbul 2004
to the real landscape, improve their planimetric accuracy to Im
and derive road centerline heights with an accuracy of 1| to 2 m.
The topology and the attributes of the existing datasets should
be maintained. This update should be achieved by using the
image analysis techniques developed at the Institute of Geodesy
and Photogrammetry, ETH Zurich (IGP). The whole procedure
should be implemented as a standalone software package,
should be operational, fast, and most importantly reliable. We
do not aim at full automation (ca. 8094 completeness is a
plausible target), but the "correct" results should be really
correct to avoid checking manually the whole dataset. After
some initial work, the aims of ATOMI were restricted to
improvement of the VEC25 (i.e. no extraction of new roads)
with the first target being the open rural areas. More details of
ATOMI can be found in Eidenbenz et al. (2000).
The standard input data used includes 1:16,000 scale colour
imagery, with 30-cm focal length, and 60%/20% forward/side
overlap, scanned with 14 microns at a Zeiss SCAI, a nationwide
DTM (DHM25) with 25-m grid spacing and accuracy of 1-3/5-
8 m in lowlands/Alps, the vectorised map data (VEC25) of
1:25,000 scale, and the raster map with its 6 different layers.
The VEC25 data have a RMS error of ca. 5-7.5 m and a
maximum error of ca. 12.5 m, including generalisation effects.
They are topologically correct, but due to their partly automated
extraction from maps, some errors exist. In some cases, DSM
data in the working area was generated using matching (without
subsequent editing) on commercial digital photogrammetric
workstations with 2-m grid spacing. In the meantime, a much
better DTM and DSM (with 2-m spacing and 0.5-m and 1.5-m
accuracy in nonforest and forest areas) produced by airborne
laser scanning exists for large areas and will be soon finished
for all Swiss regions up to 2000 m height, but has not been used
up to now.
2.2 The Road Reconstruction System
Our developed system makes full use of available information
about the scene and contains a set of image analysis tools. The
management of different information and the selection of image
analysis tools are controlled by a knowledge-based system. In
this section, a brief description of our strategy is given. We
refer to Zhang (2003a) for more details. The initial knowledge
base is established by the information extracted from the
existing spatial data and road design rules. This information is
formed in object-oriented multiple object layers, i.e. roads are
divided into various subclasses according to road type,
landcover and terrain relief. It provides a global description of
road network topology, and the local geometry for a road
subclass. Therefore, we avoid developing a general road model;
instead a specific model can be assigned to each road subclass.
This model provides the initial 2D location of a road in the
scene, as well as road attributes, such as road class, presence of
roadmarks, and possible geometry. A road is processed with an
appropriate method corresponding to its model, certain features
and cues are extracted from images, and roads are derived by a
proper combination of cues. The knowledge base is then
automatically updated and refined using information gained
from previous extraction of roads. The processing proceeds
from the easiest subclasses to the most difficult ones. Since
neither 2D nor 3D procedures alone are sufficient to solve the
problem of road extraction, we make the transition from 2D
image space to 3D object space as early as possible, and extract
the road network with the mutual interaction between features
of these spaces.
The system can extract roads with a minimum width of ca. 3
pixels. It focuses on extraction of roads in open rural areas, by
excluding roads in forest and urban areas using the existing
information about the borders of these landcover classes. The
existing road database information is used not only for giving
an approximate position but also (a) to bridge and fill-in gaps in
the extracted roads, and (b) to copy this information in
nonprocessed areas (forest, urban) and connect it to the
extracted road network in open rural areas. The aim of these
two usages is to provide as final result a complete network
(even if partially incorrect) avoiding results which consist of a
set of broken and unconnected road segments. The system has
been modified to work also with orthoimages, whereby the 3D
information is extracted by overlaying the 2D information on
the DSM or DTM. Although orthoimages have certain
disadvantages compared to 2 or more images, the main being
the inaccuracies introduced by the DTM/DSM during their
generation, they are much easier to handle, are sensor
independent and most importantly lead to reduced input data
and much faster processing, a crucial factor for operational
production.
Our system includes tools for external evaluation of the
extracted results, by comparing the extracted results with
precise reference data. The quality measures used in this work
aim at assessing completeness and correctness as well as
geometric accuracy. Completeness measures the percentage of
the reference data that lies within the buffer of the extracted
roads, while correctness is the percentage of the extracted roads
within the buffer of the reference data (Heipke et al., 1998). The
buffer distance is defined using the required accuracy of the
project ATOMI, i.e. | m. The geometric accuracy is assessed by
the mean and RMS of the distances between the extracted roads
and the reference data. The detailed description for the
computation of the external evaluation measures is presented in
Zhang (2003a).
The developed system has been implemented as a stand-alone
package initially on SGI platforms for stereo and orthoimages
and has been ported to Windows XP only for orthoimage
processing, with the same user interface. The system imports
imagery, the existing road database and other input data (e.g.
DSM/DTM). The extracted road network as well as the
computed road attributes including length and width are saved
in 3D Arc/Info Shapefile format that is readily imported into
existing GIS software. For the technical details of the system,
we refer to Zhang (2003a, 2003b). The Windows XP version for
orthoimages is termed ATOMIRO (with R standing for roads
and O for orthoimages). All current and further improvements
of the system and the tests reported here refer to ATOMIRO,
while the SGI versions have been frozen.
3. TEST SITES AND DATA DESCRIPTION
Results from two test sites in Switzerland will be presented
here, one in Thun and the other one close to the city of Geneva.
The selection is mainly based on the consideration that the test
sites should cover as many types of typical landcover in
Switzerland as possible. Another considcration is the
availability of images from multiple sensors. Both sites are in
open rural arcas but with different landcover. All road types in
Switzerland can be found in the areas. The description of the
test sites and the available imagery are listed in Table 1. Fig. 1
shows aerial images of the two test sites. Much larger and
different regions have been used for tests hy swisstopo with a
total road length of about 9.000 km.
Internati
In Thun,
from aeri
cm orthc
(produce
planimet
60 cm w
1998. A
using the
control [
ADS40 1
and the 2
comparis
the discri
differenc
orthoima
the real :
than the
datasets
orientatic
| Area (st
Height i
Landsc:
Imagen
(orthoin
pixel si
Tabl
Fig
The Ger
containin
differenc
and large
are obser