There appears to be no need to include the image parame-
ters in the calculation, although this should be verified with
further tests.
Our work will continue on applying these techniques to
more complicated geometric objects such as buildings, and
on incorporating them into our existing site modeling sys-
tems, such as SiteCity [Hsieh, 1996; Hsieh, 1995], MultiView
[Roux and McKeown, 1994a; Roux et a/., 1995], and PIVOT
[Shufelt, 19962].
6 ACKNOWLEDGEMENTS
| would like to thank my colleagues in the Digital Mapping
Laboratory for their support and interaction.
Digital Mapping Laboratory publications are available at
http:/ /www.cs.cmu.edu/^ MAPSLab
The research reported in this paper was supported by the
Advanced Research Projects Agency (ARPA/ISO) and
the U.S. Army Topographic Engineering Center under con-
tracts DACA76-91-c-0014, DACAT6-92-c-0036, and
DACAT6-95-c-0009. The views and conclusions con-
tained in this document are those of the authors and should
not be interpreted as representing the official policies, either
expressed or implied, of the U.S. Army Topographic Engi-
neering Center, the Advanced Research Projects Agency, or
of the United States government.
REFERENCES
[Fôrstner, 1985] W. Fôrstner. The reliability of block trian-
gulation. Photogrammetric Engineering and Remote Sens-
ing, 51(8):1137-1149, 1985.
[Forstner, 1987] W. Fórstner. Reliability analysis of param-
eter estimation in linear models with applications to men-
suration problems in computer vision. Computer Vision,
Graphics, and Image Processing, 40:273-310, 1987.
[Forstner, 1994] W. Fôrstner. Diagnostics and performance
evaluation in computer vision. In Proceedings, NSF/ARPA
Workshop on Performance versus Methodology in Com-
puter Vision, pages 11-25, 1994.
[Gee and Newman, 1993] S. Gee and A. Newman. RADIUS:
Automating image analysis through model-supported ex-
ploitation. In Proceedings of the DARPA Image Under-
standing Workshop, pages 185-196, Washington, D. C.,
April 19-21 1993. Morgan Kaufmann Publishers, Inc.
[Hsieh, 1995] Y. Hsieh. Design and evaluation of a semi-
automated site modeling system. Technical Report CMU-
C$-95-195, School of Computer Science, Carnegie Mel-
lon University, Pittsburgh, Pennsylvania 15213, November
1995.
[Hsieh, 1996] Y. Hsieh. Design and evaluation of a semi-
automated site modeling system. In Proceedings of the
ARPA Image Understanding Workshop, Palm Springs,
California, February 1996. Advanced Research Projects
Agency, Morgan Kaufmann Publishers, Inc.
[McGlone and Mikhail, 1982] Chris McGlone and Edward M.
Mikhail. Geometric constraints in multispectral scanner
data. In Proceedings of the 48th Annual Meeting, Ameri-
can Society of Photogrammetry, pages 563-572. American
Society of Photogrammetry, March 1982.
[McGlone and Shufelt, 1993] J. C. McGlone and J. A.
Shufelt. Incorporating vanishing point geometry into a
534
International Archives of Photogrammetry and Remote Sensing. Vol. XXXI, Part B3. Vienna 1996
building extraction system. In Proceedings of the DARPA
Image Understanding Workshop, pages 437-448, Washing-
ton, D. C., April 19-21 1993. Defense Advanced Research
Projects Agency, Morgan Kaufmann Publishers, Inc.
[McGlone, 1995] Chris McGlone. Bundle adjustment with
object space constraints for site modeling. In Proceedings
of the SPIE: Integrating Photogrammetric Techniques with
Scene Analysis and Machine Vision, volume 2486, pages
25-36, April 1995.
[Mikhail, 1970] Edward M. Mikhail. Relative control for ex-
traterrestrial work. Photogrammetric Engineering, 36(4),
April 1970.
[Mikhail, 1980] Edward M. Mikhail. Observations and Least
Squares. Harper and Row, New York, 1980.
[Roux and McKeown, 1994a] M. Roux and D. M. McKeown,
Jr. Feature matching for building extraction from multiple
views. In Proceedings of the ARPA Image Understanding
Workshop, pages 331-349, Monterey, California, Novem-
ber 13-16 1994. Advanced Research Projects Agency, Mor-
gan Kaufmann Publishers, Inc.
[Roux and McKeown, 1994b] M. Roux and D. M. McKeown,
Jr. Feature matching for building extraction from multiple
views. In Proceedings of IEEE Conference on Computer Vi-
sion and Pattern Recognition, pages 46-53, Seattle, Wash-
ington, June 19-23 1994.
[Roux et a/., 1995] M. Roux, Y. C. Hsieh, and D. M. McK-
eown, Jr. Performance analysis of object space matching
for building extraction using several images. In Proceed-
ings of the SPIE: Integrating Photogrammetric Techniques
with Scene Analysis and Machine Vision Il, volume 2486,
pages 277—297, 1995.
[Shufelt and McKeown, 1993] J. A. Shufelt and D. M. McK-
eown. Fusion of monocular cues to detect man-made struc-
tures in aerial imagery. Computer Vision, Graphics, and
Image Processing, 57(3):307-330, May 1993.
[Shufelt, 1996a] J. Shufelt. Exploiting photogrammetric
methods for building extraction in aerial images. In Interna-
tional Archives of Photogrammetry and Remote Sensing,
volume XXXI, B3, 1996.
[Shufelt, 1996b] J. Shufelt. Performance evaluation and
analysis of vanishing point detection techniques. In Pro-
ceedings of the ARPA Image Understanding Workshop,
Palm Springs, California, February 1996. Advanced Re-
search Projects Agency, Morgan Kaufmann Publishers, Inc.
KEY
ABST
Linea.
and
Unde
invari
is cor
techni
Image
gener
dimer
points
meth
featur
copy |
has «
featur
huma
auton
alone
photo
devel
Imag
derive
imagi
or pe
in gr:
ratio.
(IU)
signif
photc
prece
appli
objec
applic
Feat
photc
imag:
2. A^.
uses
using
