makes
for the
wn, the
ig. 6a).
steresis
acking
ing the
| in the
t every
resents
nk of a
om the
olution
ed at a
ps, can
Uwe Bacher
be distinguished based on the extracted branches already at this stage. The outline can be determined based on the end
points of the branches, the blurred edge defined by the shadow projection of the twigs, and the compactness of the tree
crown using a snake-based approach. We expect that the parameters nowadays collected manually, such as the height of
the tree, the width of the tree crown, and the base of the trunk can then be determined fully automatically. An analysis of
the structure of the branches and the shape of the outline should allow a classification of the type of the tree. A further
improvement of the robustness of the extraction could be achieved by employing the relations to other objects, such as
buildings and roads. For instance, rows of trees can often be found along a road and the base of a tree might be occluded
by a given building. On the other hand, an avenue can be defined by parallel rows of trees.
REFERENCES
Ballard, D. and Brown, C., 1982. Computer Vision. Prentice-Hall International, Englewood Cliffs, USA.
. Baumann, H., 1957. Forstliche Luftbild-Interpretation. Schriftenreihe 2, Landesforstverwaltung Baden-Württemberg,
Selbstverlag.
Brandtberg, T., 1996. Automated Tree Species Classification in High Resolution Aerial Images Using a Hough Transform
Technique. In: Swedish Symposium on Image Analysis.
Canny, J., 1986. A Computational Approach to Edge Detection. IEEE Transactions on Pattern Analysis and Machine
Intelligence 8(6), pp. 679—698.
Gougeon, F., 1995. À System for Individual Tree Crown Classification of Conifer Stands at High Spatial Resolutions. In:
Canadian Symposium on Remote Sensing, Vol. 17, pp. 635-642.
Hildebrandt, G. (ed.), 1996. Fernerkundung und Luftbildmessung für Forstwirtschaft, Vegetationskartierung und Land-
schaftsókologie. Wichmann Verlag, Heidelberg.
Jaynes, C., Stolle, F. and Collins, R., 1994. Task Driven Perceptual Organization for Extraction of Rooftop Polygons. In:
2nd IEEE Workshop on Applications of Computer Vision, pp. 152-159.
Kass, M., Witkin, A. and Terzopoulos, D., 1987. Snakes: Active Contour Models. International Journal of Computer
Vision 1(4), pp. 321-331.
Krummheuer, F., 1998. Auswertung von Luftbildern ausgewählter Buchenbestände mit Fouriertechniken. Photogramme-
trie — Fernerkundung — Geoinformation 3/98, pp. 165-176.
Larsen, M., 1998. Finding an Optimal Match Window for Spruce Top Detection Based on an Optical Tree Model. In:
International Forum on Automated Interpretation of High Spatial Resolution Digital Imagery for Forestry, 10.-12.02.1998,
Victoria, B.C., Kanada.
Lin, C. and Nevatia, R., 1998. Building Detection and Description from a Single Intensity Image. Computer Vision and
Image Understanding 72(2), pp. 101-121.
Mayer, H., 1998. Automatische Objektextraktion aus digitalen Luftbildern. Deutsche Geodátische Kommission (C) 494,
München.
Pollock, R., 1996. The Automatic Recognition of Individual Trees in Aerial Images of Forests Based on a Synthetic Tree
Crown Image Model. PhD Thesis, The Faculty of Computer Science, The University of British Columbia, Vancouver,
Kanada.
Serra, J., 1982. Image Analysis and Mathematical Morphology. Academic Press, London, Großbritannien.
Shufelt, J., 1996. Exploiting Photogrammetric Methods for Building Extraction in Aerial Images. In: International
Archives of Photogrammetry and Remote Sensing, Vol. (31) B6/VI, pp. 74-79.
Spurr, S. (ed.), 1960. Photogrammetry and Photo-Interpretation. The Ronald Press Company, New York.
Steger, C., 1998. An Unbiased Extractor of Curvilinear Structures. IEEE Transactions on Pattern Analysis and Machine
Intelligence 20, pp. 113-125.
Tónjes, R., 1997. 3D Reconstruction of Objects from Aerial Images Using a GIS. In: International Archives of Pho-
togrammetry and Remote Sensing, Vol. (32) 3-2W3, pp. 140-147.
International Archives of Photogrammetry and Remote Sensing. Vol. XXXIII, Part B3. Amsterdam 2000. 57