e For the images of the Farm and the Vegetation classes, the
images on the same scenes of the key images but at different
reslutions are the first ones retrieved by using the feature
sets (Or + O g - Ow). This indicates that their features are
the most similar to that of the key images among all the
images in the database, though their spatial resolutions are
very different. While for the Building class, the image on
the same scene of the key image has also been retrieved by
using the feature sets (Og 4- O g4O yw).
5 CONCLUSIONS
In this paper, we have proposed the method for indexing the re-
mote sensing images at different reslutions. The radiometric fea-
tures, the texture features (including the Gaussian wavelet fea-
tures, the Gabor features and the GCLM features) and the shape
features have been used in this paper. For the Gaussian wavelet
features, we have proposed to use the resolution invariance in or-
der to compare the features extracted from images at different
reslutions. While for the GLCM features, the distance parame-
ters are tuned according the resolutions of the images. According
to the image retreival results of remote sensing images at differ-
ent reslutions, the combination of the radiometric features, the
GLCM features and the Gaussian wavelet features is very effi-
cient though the difference of the spatial resolutions is important.
REFERENCES
Colapicchioni, A. and ieee, 2004. Kes: Knowledge enabled ser-
vices for better eo information use. In: Igarss 2004: Ieee Interna-
tional Geoscience and Remote Sensing Symposium Proceedings,
pp. 176-179.
Datcu, M., Daschiel, H., Pelizzari, A., Quartulli, M., Galoppo,
A., Colapicchioni, A., Pastori, M., Seidel, K., Marchetti, P. G.
and D’Elia, S., 2003. Information mining in remote sensing im-
age archives: System concepts. Ieee Transactions on Geoscience
and Remote Sensing 41(12), pp. 2923-2936.
Haralick, R. M., Shanmuga.K and Dinstein, L, 1973. Textural
features for image classification. Ieee Transactions on Systems
Man and Cybernetics SMC3(6), pp. 610-621.
Kamarainen, J. K., Kyrki, V. and Kalviainen, H., 2006. Invariance
properties of gabor filter-based features - overview and applica-
tions. Ieee Transactions on Image Processing 15(5), pp. 1088—
1099,
Lew, M. S., Sebe, N., Djeraba, C. and Jain, R., 2006. Content-
based multimedia information retrieval: State of the art and chal-
lenges. Acm Transactions on Multimedia Computing Communi-
cations and Applications 2(1), pp. 1-19.
Lowe, D., n.d. Distinctive image features from scale-invariant
keypoints. International Journal of Computer Vision 60, pp. 91—
110.
Luo, B., Aujol, J. E, Gousseau, Y. and Ladjal, S., 2008. Indexing
of satellite images with different resolutions by wavelet features.
Ieee Transactions on Image Processing 17(8), pp. 1465-1472.
Luo, B., Jiang, S. and Zhang, L., n.d. Performance comparisons
of the multi-scale low-level features for the indexing of remote
sensing images with different resolutions. IEEE Journal of Se-
lected Topics in Applied Earth Observations and Remote Sens-
ing. submitted.
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B3, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
