ues
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XXXV, Part B3. Istanbul 2004
(b) Connection (black) between extrac- (c) Extracted car (incl. substructures)
ted lanes (white) as region of interest. within region of interest.
Figure 8: Extraction of cars in optical imagery.
Since vehicles appear only as small, elliptical, dark or bright
“blobs” in these images (resolution about 1m), many other ob-
jects in urban areas exhibit a very similar appearance. Thus, a
reasonable good system for vehicle detection from thermal im-
agery must make use of additional information. Knowledge about
the appearance of cars as repetitive patterns in dense traffic situ-
ations or in filled parking lots provides such additional informa-
tion. This kind of knowledge is used in the example shown in
Fig. 9 (Details regarding the methodology of the approach can be
found in (Hinz, 2004a)).
However, as can be also seen from Fig. 9, each car that is too far
away from another car has been rejected during generating ve-
hicle queues from the individual car hypotheses. To detect also
isolated cars with high confidence, information about the road —
or even better: the lane a car is driving on—needs to be included.
Unfortunately, this information is almost impossible to extract
from thermal imagery itself, since road sides are rarely visible
therein (see Fig. 9). But clearly, road data from an external source
are appropriate means to deliver the necessary information, and
the road extraction system described above is able to serve as
such a source. What is more, since it extracts not only road axes
but also lanes, even the current state of the system will poten-
tially be better suited for this particular application than common
map data. Further developments and tests will show whether this
expectation will be met.
REFERENCES
Agouris, P. and Stefanidis, A. (eds), 1999. Integrated Spatial Databases -
Digital Images and GIS. Springer-Verlag, Berlin.
Baltsavias, E., Grün, A. and van Gool, L. (eds), 2001. Automatic Extrac-
tion of Man-Made Objects from Aerial and Space Images (III). Balkema
Publishers, Lisse, The Netherlands.
Baumgartner, A., Steger, C., Mayer, H., Eckstein, W. and Ebner, H., 1999.
Automatic Road Extraction Based on Multi-Scale, Grouping, and Con-
text. Photogrammetric Engineering and Remote Sensing 65(7), pp. 777—
785.
Clément, V., Giraudon, G., Houzelle, S. and Sandakly, E., 1993. Inter-
pretation of Remotely Sensed Images in a Context of Multisensor Fusion
Using a Multispecialist Architecture. IEEE Transactions on Geoscience
and Remote Sensing 31(4), pp. 779—791.
Fischler, M. and Heller, A., 1998. Automated Techniques for Road Net-
work Modeling. In: Image Understanding Workshop '98, Morgan Kauf-
mann Publishers, San Francisco, CA, pp. 501—516.
Figure 9: Extraction of cars in thermal imagery: Detected car hy-
potheses/"blobs" (white), hypotheses linked into queues (black).
Fuchs, C., Gülch, E. and Fórstner, W., 1998. OEEPE Survey on 3D-City
Models. OEEPE Official Publication 35, pp. 9-123.
Grün, A., Baltsavias, E. and Henricsson, O. (eds), 1997. Automatic
Extraction of Man-Made Objects from Aerial and Space Images (Il).
Birkhäuser Verlag, Basel.
Grün, A., Kuebler, O. and Agouris, P. (eds), 1995. Automatic Extraction
of Man-Made Objects from Aerial and Space Images. Birkháuser Verlag,
Basel.
Hinz, S., 2003. Automatische Extraktion urbaner Straffennetze aus Luft-
bildern. Dissertation, Technische Universität München.
Hinz, S., 2004a. Car Detection in Aerial Thermal Imagery by Local
and Global Evidence Accumulation. Technischer Bericht, PF-2004-
01, Lehrstuhl für Methodik er Fernerkundung, Technische Universität
München.
Hinz, S., 2004b. Detection of Vehicles and Vehicle Queues in High Res-
olution Aerial Images. Photogrammetrie — Fernerkundung — Geoinfor-
mation (PFG) 3, pp. 203-215.
Hinz, S. and Baumgartner, A., 2002. Urban Road Net Extraction Integrat-
ing Internal Evaluation Models. In: International Archives of Photogram-
metry, Remote Sensing and Spatial Information Sciences, Vol. 34(3A),
pp. 163-168.
Hinz, S., Baumgartner, A., Mayer, H., Wiedemann, C. and Ebner, H.,
2001. Road extraction focussing on urban areas. In: (Baltsavias et al.,
2001), pp. 255-265.
Mayer, H. and Steger, C., 1998. Scale-Space Events and Their Link to
Abstraction for Road Extraction. ISPRS Journal of Photogrammetry and
Remote Sensing 53(2), pp. 62-75.
Price, K., 2000. Urban Street Grid Description and Verification. In: 5th
IEEE Workshop on Applications of Computer Vision, pp. 148-154.
Ruskoné, R., 1996. Road Network Automatic Extraction by Local Con-
text Interpretation: application to the production of cartographic data.
PhD thesis, Université Marne-La-Valleé.
Schlosser, C., Reitberger, J. and Hinz, S., 2003. Automatic Car Detection
in High Resolution Urban Scenes Based on an Adaptive 3D Model. In:
IEEE/ISPRS joint Workshop on Remote Sensing and Data Fusion over
Urban Areas.
Strat, T. and Fischler, M., 1995. The Role of Context in Computer Vision.
In: IBEE Workshop on Context-based Vision, pp. 2-12.
Tónjes, R., Growe, S., Bückner, J. and Liedke, C.-E., 1999. Knowledge-
Based Interpretation of Remote Sensing Images Using Semantic Nets.
Photogrammetric Engineering and Remote Sensing 65(7), pp. 811—821.
Tupin, F., Bloch, I. and Maitre, H., 1999. A First Step Toward Automatic
Interpretaion of SAR Images Using Evidential Fusion of Several Struc-
ture Detectors. IEEE Transactions on Geoscience and Remote Sensing
37(3), pp. 1327-1343.
Wiedemann, C., 2003. External Evaluation of Road Networks. In: Inter-
national Archives of Photogrammetry, Remote Sensing and Spatial Infor-
mation Sciences, Vol. 34(3W/8), pp. 93-98.
Wiedemann, C. and Ebner, H., 2000. Automatic Completion and Evalu-
ation of Road Networks. In: International Archives of Photogrammetry
and Remote Sensing, Vol. 33(B3/2), pp. 979—986.
THR
KEY V
ABSTI
In the
framew
Waiting
regions
groupir
on forv
moving
images.
from tl
observ:
Traffic
vehicle
effectiv
Sensing
distribu
ground:
sensing
distribu
Fi
Recent
imagin;
system:
mounte
reducti
resoluti
backwa
By sea
