1175
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B4. Beijing 2008
mark with more high-frequency texture. The fluctuated range of
RC is 1.83 ~ 2.58, which is in an acceptable range.
As for the right segmented parameter RS, as shown in Figure 6,
it is also increased with the texture marking from low frequency
to high. The image is better segmented in small scale, that is,
scale 1 and scale 2. Certainly, the region count is also more in
these scales. RS of the image is between 66.2% ~ 82.44% for all
of scales.
5. CONCLUSIONS
In conclusion, a scheme for segmenting high-spatial resolution
satellite image based on vector field model and texture-marked
watershed transform is proposed. With first fundamental form,
the gradient information from all bands is accessed simul
taneously, and the multiscale texture features of all bands are
fused together. Moreover, the spectral information and texture
information are integrated in the procedure of segmentation.
The inclusion of texture features based on the actual frequency
content of the image may ensure that differently textured
regions are segmented effectively. Marking with different-
frequency texture features may produce different scale
segment-ation results, and the image is better segmented in
small scale than large scale.
In experiments, the proposed method demonstrates excellent
performance in very-high resolution image even where compli
cated agriculture areas. In particular, the proposed approach
gives a better solution for the segmentation of multispectral
remotely sensed image. It also has an effect of intrinsic hie
rarchy that reduces dramatically the over-segmentation problem
of the watershed approach.
The drawback of the proposed method concerns the heavy
computation of the multichannel log Gabor filtering, which may
prevent the approach applied in real-time applications. Further
study is needed on how to describe texture effectively even
where the severe texture regions.
REFERENCES
Acharyya, M., De, R.K., Kundu, M.K., 2003. Segmentation of
remotely sensed images using wavelet features and their
evaluation in soft computing framework. IEEE Transactions on
Geoscience and Remote Sensing, 41(12), pp. 2900-2905.
Baatz, M., Schape, A., 1999. Object-oriented and multi-scale
image analysis in semantic networks. In: Proceedings of the
2nd International Symposium on Operationalization of Remote
Sensing, ITC, Netherlands.
Blaschke, T., Lang, S., Lorup, E., Strobl, J., Zeil, P., 2000.
Object-oriented image processing in an integrated GIS / remote
sensing environment and perspectives for environmental
applications. In: Environmental Information for Planning,
Politics and the Public. Metropolis-Verlag, Marburg, Vol. 2, pp.
555-570.
Carleer, A.P., Debeir, O., Wolff, E., 2005. Assessment of very
high spatial resolution satellite image segmentations. Photo-
grammetric Engineering and Remote Sensing, 71(11), pp. 1285-
1294.
Chen, Z., Zhao, Z., Gong, P., Zeng, B., 2006. A new process for
the segmentation of high resolution remote sensing imagery.
Inter-national Journal of Remote Sensing, 27(22), pp. 4991-
5001.
Cumani, A., 1991. Edge detection in multispectral images.
Computer Vision Graphics and Image Processing, 53(1), pp.
40-51.
Devereuxa, B.J., Amablea, G.S., Posada, C.C., 2004. An
efficient image segmentation algorithm for landscape analysis.
International Journal of Applied Earth Observation and
Geoinformation, 6, pp. 47-61.
Evans, C., Jones, R., Svalbe, I., Berman, M., 2002. Segmenting
multispectral Landsat TM images into field units. IEEE Trans
actions on Geoscience and Remote Sensing. 40(5), pp. 1054-
1064.
Field, D.J., 1987. Relations between the statistics of natural
images and the response properties of cortical cells. Journal of
the Optical Society of America A, 4(2), pp. 2379-2394.
Hall, O., Hay, G.J., Bouchard, A., Marceau, D.J., 2004.
Detecting dominant landscape objects through multiple scales:
an integration of object-specific methods and watershed seg
mentation. Landscape Ecology, 19(1), pp. 59-76.
Hill, P.R., Canagarajah, C.N., Bull, D.R., 2003. Image
segmentation using a texture gradient based watershed
transform. IEEE Transactions on Image Processing, 12(12), pp.
1618-1633.
Hu, X., Tao, C.V., Prenzel, B., 2005. Automatic segmentation
of high-resolution satellite imagery by integrating texture,
intensity, and color features. Photogrammetric engineering and
remote sensing. 71(12), pp. 1399-1406.
Jain, A.K., Farrokhnia, F., 1991. Unsupervised texture
segmentation using Gabor filters. Pattern Recognition, 24(12),
pp. 1167-1186.
Kartikeyan, B., Sarkar, A., Majumder, K.L., 1998. A segment
ation approach to classification of remote sensing imagery.
International Journal of Remote Sensing, 19(9), pp. 1695-1709.
Kettig, R.L., Landgrebe, D.A., 1976. Classification of
multispectral image data by extraction and classification of
homogeneous objects. IEEE Transactions on Geoscience
Electronics, GE-14(1), pp. 19-26.
Kovesi, P., 1996. Invariant Measures of Image Features from
Phase Information. PhD dissertation, University of Western
Australia, Nedlands, Western Australia, Australia.
Li, P., Xiao, X., 2007. Multispectral image segmentation by a
multichannel watershed-based approach. International Journal
of Remote Sensing, 28(19), pp. 4429-4452.
Li, W., Benie, G.B., He, D.C., Wang, S., Ziou, D., Hugh, Q.,
Gwyn, J., 1999. Watershed-based hierarchical SAR image
segmentation. International Journal of Remote Sensing, 20(17),
pp, 3377-3390.
Li, Y., Gong, P., 2005. An efficient texture image segmentation
algorithm based on the GMRF model for classification of