Small Abstraction Large
Scale — Scale
oA eani
| Road segment
— ——— Specialization relation
—— > Part-of relation
—— ——- Concrete relation
----= General relation of objects
Pavement Marking es en Car
; |
Solid | Dashed Real World
marking | | marking
Mostly straight Elongated, flat Long colored Short colored Painted Geometry
concrete or 9?" concrete or line line metal or | ang Material
asphalt line asphalt area glass box
| | |
Mostly straight ».| Elongated Long bright Short bright Dark
bright line bright area line line blob | Image
\
Substructure
Figure 8: Model for road segment (concepts are depicted in boxes)
REFERENCES Lindeberg, T., 1994. Scale-Space Theory in Computer Vision.
Airault, S., Ruskoné, R. and Jamet, O., 1994. Road detection from
aerial images: a cooperation between local and global methods.
in J. Desachy (ed.), Image and Signal Processing for Remote
Sensing, Proc. SPIE 2315, pp. 508-518.
Brachman, R. J., 1979. On the epistomological status of semantic
networks. in Findler (ed.), Associative Networks, Academic Press,
New York, USA, pp. 191-215.
Brachman, R. J., 1983. What is-a is and isn’t: an analysis of
taxonomic links in semantic networks. Computer IEEE 16(10),
pp. 30-36.
Clément, V., Giraudon, G., Houzelle, S. and Sandakly, F., 1993.
Interpretation of remotely sensedimages in a context of multi sen-
sor fusion. IEEE Transactions on Geoscience and Remote Sensing
31(4), pp. 779-791.
Encyclopedia Britannica, 1985. Encyclopædia Britannica, Inc.
Encyclopedia of Artificial Intelligence, 1985. Wiley & sons, Inc.
Gruen, A., Agouris, P. and Li, H., 1995. Linear feature extraction
with dynamic programming and globally enforced least squares
matching. in Gruen et al. (eds), Automatic Extraction of Man-
Made Objects from Aerial and Space Images, Birkháuser, Basel,
Switzerland, pp. 83-94.
Haralick, R. M. and Shapiro, L. G., 1992. Computer and Robot
Vision. Vol. 1, Addison-Wesley Publishing Company, Reading,
MA, USA.
Jedynak, B. and Rozé, J.-P., 1995. Tracking roads in satellite im-
ages by playing twenty questions. in Gruen et al. (eds), Automatic
Extraction of Man-Made Objects from Aerial and Space Images,
Birkháuser, Basel, Switzerland, pp. 243-253.
Koenderink, J. J., 1984. The structure of images, Biological Cy-
bernetics 50, pp. 363-370.
Kosslyn, S., 1994. Image and Brain. MIT Press, Cambridge, MA,
USA.
528
International Archives of Photogrammetry and Remote Sensing. Vol. XXXI, Part B3. Vienna 1996
Kluwer Academic Publishers, Boston, MA, USA.
Marr, D., 1982. Vision. Freeman and Company, New York, USA.
Mayer, H., 1994. Automatic knowledege based extraction of ob-
jects of the real world from scanned maps. International Archives
of Photogrammetry and Remote Sensing 30(3/2), pp. 547—554.
McKeown, D. M., 1991. Information fusion in cartographic fea-
ture extraction from aerial imagery. in Ebner et al. (eds), Digital
Photogrammiric Systems, pp. 103—110.
McKeown Jr., D. M. and Denlinger, J. L., 1988. Cooperative
methods for road tracking in aerial imagery. Computer Vision and
Pattern Recognition, IEEE Computer Society Press, pp. 662-672.
Niemann, H., Sagerer, G. F., Schrôder, S. and Kummert, F., 1990.
ERNEST: A semantic network system for pattern understanding.
IEEE Transactions on Pattern Analysis and Machine Intelligence
12(9), pp. 883-905.
Rapp, F., 1995. Modell und Realität. Zeitschrift für Photogram-
metrie and Fernerkundung 6/95, pp. 220-223.
Sester, M., 1990. Multi-scale representation of knowledge based
recognition and tracking of objects in image sequences. Interna-
tional Archives of Photogrammetry and Remote Sensing 28(3/2),
pp. 868-888.
Sowa, J. F. (ed.), 1995. Principles of Semantic Networks - Explo-
rations in the Representation of Knowledge. Morgan Kaufmann
Publishers, San Mateo, CA, USA.
Steger, C., Glock, C., Eckstein, W., Mayer, H. and Radig, B.,
1995. Model-based road extraction from images, in Gruen et al.
(eds), Automatic Extraction of Man-Made Objects from Aerial
and Space Images. Birkhäuser, Basel, Switzerland, pp. 275-284.
Strat, T. M., 1995. Using context to control computer vision al-
gorithms. in Gruen et al. (eds), Automatic Extraction of Man-
Made Objects from Aerial and Space Images, Birkhäuser, Basel,
Switzerland, pp. 3-12.
KEY '
ABST
This p
assum
geome
among
statist
constr
Our gt
of acc
ages.
[Hsieh
1994a
hypotl
hypotl
descri
metho
geome
1993]
Methc
erful,
proper
outsid
utilize
bundk
and w
While
ment
have I
tation
tend t
to pro
match
The d
metric
tion o
image
space.
pothe:
lines,
specif
ject S|
but m
The v
ing of
snoop