Al Eq. 6 
the scale parameter is 
ve with respect to the 
iS to directly introduce it 
matching observation 
tives of gray values as 
the Jacobian matrix) 
ENTS 
hing procedure presented 
d in several experiments 
ges. Synthetic data were 
with substantial local 
lings etc.), assigning 
cting back to fictitious 
cale space inclinations, 
g conjugate features were 
the performance of the 
range in scale differences 
tained matching results. 
Fig. 2) it was found that, 
ns typical least squares 
rences exceeded 20-30%. 
variations in the local 
ve described method we 
ramp which differed by 
entification of sufficient 
tures was the only limit. 
rivial as scale differences 
re significantly different 
dings, we were even able 
ag them as such. In terms 
lts were comparable to 
ilts (on the order of 0.1 
] quite successful when 
accuracies refer to cases 
failed to produce any 
»fanidis, 1993] for a more 
of experiments. 
NTS 
the problem of matching 
variations. The technique 
ng into account such 
rming precise matching. 
ntial of matching, this 
1 module within a general 
matching results in areas 
failed. Of course it can 
ry module, but it would be 
perform a detailed scale 
atch to be matched. The 
space images opens a new 
Not only do these images 
allowing an operator to 
ve the great advantage of 
enna 1996 
  
being, by design, compatible with digital image processing 
and analysis algorithms and software. This makes their 
complete integration in an existing general matching 
strategy very easy. They can be effectively combined with 
edge detection for automated, fast, and reliable scale space 
feature tracking, showing great promise for use towards 
image understanding. 
REFERENCES 
O Agouris P. & A. Stefanidis (1996) Integration of 
Photogrammetric and Geographic Databases, International 
Archives of Photogrammetry & Remote Sensing, Vol. 
XXXI, Part B4 (in print). 
C] Alvertos N., D. Brzakovic & R.C. Gonzalez (1989) 
Camera Geometries for Image Matching in 3-D Machine 
Vision, IEEE Transactions on Pattern Analysis and Machine 
Intelligence, Vol. 11, No. 9, pp. 897-915. 
L] Babaud J. A. Witkin, M. Baudin & R.O. Duda (1986) 
Uniqueness of the Gaussian Kernel for Scale-Space Filtering, 
IEEE Transactions on Pattern Analysis and Machine 
Intelligence, Vol. 8, No. 1, pp. 26-33. 
LJ Bergholm F. (1987) Edge Focusing, IEEE Transactions on 
Pattern Analysis and Machine Intelligence, Vol. 9, No. 6, 
pp. 726-74]. 
O Burt P.J. (1981) Fast Filter Transforms for Image 
Processing, Computer Graphics Image Processing, Vol. 16, 
pp. 20-51. 
Q Burt P.J. (1984) The Pyramid as a Structure for Efficient 
Computation, in ^Multiresolution Image Processing and 
Analysis’ (A. Rosenfeld ed.), Springer-Verlag, New York, 
NY, pp. 6-35. 
Q Chin F., A. Choi & Y. Luo (1992) Optimal Generating 
Kernels for Image Pyramids by Piecewise Fitting, IEEE 
Transactions on Pattern Analysis and Machine Intelligence, 
Vol. 14, No. 12, pp. 1190-1198. 
O Gruen A, O. Kuebler & P. Agouris (eds.) (1995) 
Automatic Extraction of Man-Made Objects from Aerial and 
Space Images, Birkhaeuser Verlag, Basel, Switzerland. 
O Hahn M. (1990) Estimation of the Width of the Point 
Spread Function within Image Matching, International 
Archives of Photogrammetry & Remote Sensing, Vol. 28- 
3/2, pp. 246-267. 
C) Horn B.K.P. (1986) Robot Vision, MIT Press, 
Cambridge, MA. 
C) Lindeberg T. (1990) Scale-Space for Discrete Signals, 
IEEE Transactions on Pattern Analysis and Machine 
Intelligence, Vol. 12, No. 3, pp. 234-254. 
Q Lindeberg T. (1994) Scale-Space Theory: A Basic Tool for 
Analyzing Structures at Different Scales, Journal of Applied 
Statistics, Vol. 21, No. 2, pp. 224-270. 
Q Lindeberg T. (1994) Scale-Space Theory in Computer 
Vision, Kluwer Academic Publishers, Dordrecht, 
Netherlands. 
International Archives of Photogrammetry and Remote Sensing. Vol. XXXI, Part B3. Vienna 1996 
C] Lu Y. & R.C. Jain (1992) Reasoning about Edges in Scale 
Space, IEEE Transactions on Pattern Analysis and Machine 
Intelligence, Vol. 14, No. 4, pp. 450-468. 
C] Meer P., E. Baugher & A. Rosenfeld (1987) Frequency 
Domain Analysis of Image Pyramid Generating Kernels, 
IEEE Transactions on Pattern Analysis and Machine 
Intelligence, Vol. 9, No. 4, pp. 512-522. 
LJ) Schneider P. & M. Hahn (1992) Matching Images of 
Different Geometric Scale, International Archives of 
Photogrammetry & Remote Sensing, Vol. XXIX, Part B3, 
pp. 295-302. 
Q Stefanidis A. (1993) Using Scale Space Techniques to 
Eliminate ^ Scale Differences Across Images, Ph.D. 
Dissertation, Dept. of Geodetic Science & Surveying, The 
Ohio State University. 
CJ Tanimoto S. & T. Pavlidis (1975) A Hierarchical Structure 
for Picture Processing, Computer Vision, Graphics and 
Image Processing, Vol. 4, No. 2, pp. 104-119. 
Q Witkin AP. (1983) Scale Space Filtering, Proceedings 
7th International Conference on Artificial Intelligence, 
Karlsruhe, pp. 1019-1022. 
Q Witkin A.P. (1986) Scale Space Filtering, in “From Pixels 
to Predicates’ (A.P. Pentland ed.), Ablex Publishing Co. 
Norwood, NJ. pp. 5-19. 
OQ Wrobel B.P. (1991) The Evolution of Digital 
Photogrammetry from Analytical = Photogrammetry, 
Photogrammetric Record, Vol. 13, No. 77, pp. 765-776. 
13