International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XXXV, Part B1. Istanbul 2004
FIG. 3. The peak and valley points of histogram.
Therefor, the peak and valley points are detected by using
these rules. Each peak point and two neighboring points, the left
and right valley points of the peak point, corresponds an object
(objects i, and j in Fig. 3). The Mean and SD of each object are
calculated and used as the values of real variables.
FIG. 4. The segmented image.
Mean and SD of each object are determined and used as input
into the fuzzy mode. Fig. 4 shows the result of the
segmentation.
CONCLUSIONS
In this study, we used fuzzy logic system for
segmentation of spot images. The results showed that if the
range of SD and mean of gray levels were varied from 36-38
and 226-228 for objects such as roads and 38-40 and 20-190 for
non-roads respectively. Then, the optimum width and SD of
Gaussian kernel function would be 3 and 0.4 respectively. The
skeleton of segmented image could be extracted by
mathematical morphology and vectorized to put directly in to
GIS. At the end, this approach can be proposed in large scale
imagemap for segmentation.
ACKNOWLEDGMENT
The author would like to thank Faculty of engineering,
University of Tehran for supporting this project.
REFERENCES
AMINI, J. and SARADJIAN M.R., 2000. Imagemap simplification by
using mathematical morphology. International Archives of
Photogrammetry and Remote Sensing, xxxiii(B3): 36-47.
BARZOHAR, M. and COOPER, D.B., 1993. Automatic finding of main
roads in aerial images by using geometric-stochastic models and
estimation. Proceeding of the IEEE Computer Vision and Pattern
Recognition, July 1993, 459-464.
BAUMGARTNER, A., STEGER, C., MAYER, H., ECKSTEIN, W.
and EBNER, H., 1999. Automatic road extraction based on multi
scale grouping and content. Photogrammetric Engineering &
Remote Sensing, 65(7): 777-785.
COULOIGNER, I. and RONCHIN, T., 2000. A multiresolution
modeling approach for semi-automatic extraction of streets.
Photogrammetric Engineering & Remote Sensing, 66(7): 867-
874.
GERLACH, F., 2000. Characteristics of Space Imaging one meter
Resolution Satellite imagery Products. International Archives of
Photogrammetry and Remote Sensing, xxxiii(B1).
GRUEN, A. and LI, H., 1997. Semiautomatic Linear Feature Extraction
by Dynamic Programming and LSB_Snakes. Photogrammetric
Engineering & Remote Sensing, 63(8): 985-995.
KRISHNA, M., BABA MADHAVAN, B. and DAS GUPTA, U.M.,
2000. Integration IRS-1A L2 data by fuzzy logic approaches for
landuse classification. International journal of remote sensing,
21(8): 1709-1723.
LI, R., 1998. Potential of high resolution satellite imagery for national
mapping products, Photogrammetric Engineering & Remote
Sensing, 64(12): 1165-1170.
MOON, W. M. and AN, P., 1991. Integration of geophysical, geological
and remote sensing data using fuzzy set theory. Geoinformatic, 2:
171-176.
SOWMYA, A. and TRINDER, J., 2000. Modeling and representation
issues in automated feature extraction from aerial and satellite
images, ISPRS journal of photogrammetry and remote sensing,
55(1): 34-47.
WANG, F., 1989. A fuzzy expert system for remote sensing image
analysis. Proceedings of IEEE Geoscience and Remote Sensing,
848-851.
KEY WOR
ABSTRAC
The laser sc
considered.
has to be fo
a trajectory
produced w
in this cas
continuousl
Suggested 1
distance to
velocity is :
vehicle owr
The laser
continuous
of aircraft
sensing of
image of o
velocity ha:
azimuthal «
distance m:
compressio
dispersive :
Meyzonnet
In the syste
all laser c
(AOM) wh
of change o
optics and :
not modula
it mixes up
mixing opt
out, and lir
presence o
signal is in
velocity ca
to [Stephar
on frequer
Further the
(DADL) w
product of
An output
frequency |
laser. The
measures a
clock pulse
