ISPRS Commission III, Vol.34, Part 3A „Photogrammetric Computer Vision‘, Graz, 2002
IMPROVING CARTOGRAPHIC ROAD DATABASES BY IMAGE ANALYSIS
Chunsun Zhang, Emmanuel Baltsavias
Institute of Geodesy and Photogrammetry, Swiss Federal Institute of Technology Zurich, ETH Hoenggerberg, CH-8093 Zurich,
Switzerland — (chunsun, manos)@baug.geod.ethz.ch
Commission III, WG III/4
KEY WORDS: 3D Road reconstruction, Context, Knowledge base, Spatial reasoning
ABSTRACT:
The extraction of road networks from aerial images is one of the current challenges in digital photogrammetry and computer vision.
In this paper, we present our system for 3D road network reconstruction from aerial images using knowledge-based image analysis.
In contrast to other approaches, the developed system integrates processing of color image data and information from digital spatial
databases, extracts and fuses multiple object cues, takes into account context information, employs existing knowledge, rules and
models, and treats each road subclass accordingly. The key of the system is the use of knowledge as much as possible to increase
success rate and reliability of the results, working in 2D images and 3D object space, and use of 2D and 3D interaction when needed.
Another advantage of the developed system is that it can correctly and reliably handle problematic areas caused by shadows and
occlusions. This work is part of a project to improve and update the 1:25,000 vector maps of Switzerland. The system has been
implemented as a standalone software package. We tested the system on a number of images in different landscapes. In this paper we
present the results of our system in recent benchmark tests conducted independently by our project partner in Switzerland, and test
results with black and white images in a test site in Belgium.
1. INTRODUCTION
The extraction of roads from digital images has drawn
considerable attention lately. The existing approaches cover a
wide variety of strategies, using different resolution aerial or
satellite images. Overviews can be found in Gruen et al. (1995,
1997), Foerstner and Pluemer (1997) and Baltsavias et al.
(2001). Semi-automatic schemes require human interaction to
provide interactively some information to control the extraction.
Roads are then extracted by profile matching (Airault et al.,
1996; Vosselman and de Gunst, 1997), cooperative algorithms
(McKeown et al., 1988), and dynamic programming or LSB-
Snakes (Gruen and Li, 1997). Automatic methods usually
extract reliable hypotheses for road segments through edge and
line detection and then establish connections between road
segments to form road networks (Wang and Trinder, 2000).
Contextual information is taken into account to guide the
extraction of roads (Ruskone, 1996). Roads can be detected in
multi resolution images (Baumgartner and Hinz, 2000). The use
of existing road data for road updating is reported in Agouris et
al. (2001). The existing approaches show individually that the
use of road models and varying strategies for different types of
scenes are promising. However, most methods are based on
relatively simplistic road models, and make only insufficient use
of a priori information, thus they are very sensitive to
disturbances like cars, shadows or occlusions, and do not
always provide good quality results. Furthermore, most
approaches work in single 2D images, thus neglecting valuable
information inherent in 3D processing.
In this paper, we present a knowledge-based system for
automatic extraction of 3D roads from stereo aerial images
which integrates processing of colour image data and existing
digital spatial databases. The system has been developed within
the project ATOMI (Automated reconstruction of Topographic
Objects from aerial images using vectorized Map Information),
in cooperation with the Swiss Federal Office of Topography
(L*T), with aims to improve road centerlines from digitized
1:25,000 topographic maps by fitting them to the real
landscape, improving the planimetric accuracy to 1m and
providing height information with 1-2m accuracy. The details of
ATOMI can be found in Eidenbenz et al. (2000). We currently
use 1:16,000 scale color imagery, with 30cm focal length, and
6099/2096 forward/side overlap, scanned with 14 microns at a
Zeiss SCAL. The other input data include: a nationwide DTM
with 25m grid spacing and accuracy of 2-3/5-7m in
lowland/Alps, the vectorized 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. 5-7.5m and a maximum one of ca.
12.5m, including generalization effects. They are topologically
correct, but due to their partly automated extraction from maps,
some errors exist. In addition, DSM data in the working area
was generated from stereo images using MATCH-T of Inpho
with 2m grid spacing.
2. GENERAL STRATEGY
Our road network reconstruction 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. We give a brief description of our
strategy in this section, for more details, we refer to Zhang and
Baltsavias (2000).
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, land cover 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 segment. This model provides the initial 2D location of a
road in the scene, as well as road attributes, such as road class,
presence of road marks, and possible geometry (width, length,
A - 400
