The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B4. Beijing 2008 
4. CONCLUSION AND DISCUSSION 
This study proposed a new multi-scale segmentation method 
based on SRM and MHR where QuickBird imageries are used. 
Compared with multi-scale SRM and FNEA method, the results 
indicates that the proposed method overcomes the 
disadvantages of them, integrates the advantages of them and is 
an efficient multi-scale segmentation for HR imagery. The 
SRM method used for initial segmentation achieves robust and 
accurate segmentation results through using not only the 
spectral, shape, scale information, but also has the ability to 
cope with significant noise corruption, handle occlusions. The 
MHR used for merging objects relies on both the effectiveness 
local quality and global quality and its consideration of shape 
and spectral features. 
Nevertheless, there are many other issues that require future 
investigation, including the improvement of sort function and 
merge predicate of SRM, the study of evaluation index for 
estimating segmentation results, the determination of 
parameters for various classes, and the applications of the 
proposed method in different styles of RS imagery such as SAR, 
and so on. 
REFERENCE 
Baatz, M. and Schape, A., 2000. Multiresolution segmentation: 
an optimization approach for high quality multi-scale image 
segmentation. Angewandte Geographische Informations 
verarbeitung, pp. 12-23. 
Benz, U., Hofmann, P., Willhauck, G., Lingenfelder, I., and 
Heynen, M., 2004. Multi-resolution, object-oriented fuzzy 
analysis of remote sensing data for GIS-ready information. 
ISPRS Journal of Photogrammetry and Remote Sensing, 58, 
pp.239-258. 
Blaschke,T. and Strobl, J., 2001.What’s wrong with pixels? 
Some recent developments interfacing remote sensing and GIS. 
GeoBIT/GIS 6. pp.12-17. 
Cao, D.D., Yin, Q. and Guo, P., 2006. Mallat fusion for multi 
source remote sensing classification. Sixth international 
conference on intelligent systems design and applications, 1, pp. 
588-593. 
CASM Imagelnfo, 2007. UserGuide, Website: www.image- 
info.com (accessed. 18 Jun. 2007). 
Chen, Q. X. , Luo, J. C., Zhou, C. H., Pei, T., 2003. A hybrid 
multi-scale segmentation approach for remotely sensed 
imagery.In: Proceedings of IEEE International Geoscience and 
Remote Sensing Symposium, IGARSS ’0i.pp.3416-3419. 
Chen, Z., Zhao, Z.M., Yan, D.M., Chen, R.X., 2005.Multi-scale 
segmentation of the high resolution remote sensing image. In: 
Proceedings of IEEE International Geoscience and Remote 
Sensing Symposium, IGARSS ’05.pp.3682-3684. 
Erdas Imagine, 2003. FieldGuide, Website: www.erdas.com 
(accessed. 21 Jan. 2007). 
Fu, K.S. and Mui, J.K., 1981. A survey on image segmentation. 
Pattern Recognition, 13( 1 ),pp.3-16. 
Kartikeyan, B., Sarkar, A. and Majumder, K.L., 1998. A 
Segmentation approach to classification of remote sensing 
imagery. International Journal of Remote Sensing, 19(9), 
pp. 1695-1709. 
Liu, J. G., 2000. Smoothing Filter-based Intensity Modulation: 
a spectral preserve image fusion technique for improving spatial 
details. International Journal of Remote Sensing, 21(18), pp. 
3461-3472. 
Nock,R., 2001. Fast and reliable color region merging inspired 
by decision tree pruning.In: Proceedings of IEEE International 
Conference on Computer Vision and Pattern 
Recognition, pp.271 -276. 
Nielsen, F., and Nock, R.,2003.On region merging: the 
statistical soundness of fast sorting , with applications, 
in .Proceedings of IEEE International Conference on Computer 
Vision and Pattern Recognition , IEEE Computer Society 
Press,Silver Spring,MD, pp.19 - 27. 
Nock, R. and Nielsen, F., 2004. Statistical region merging. 
IEEE transctions on pattern analysis and machine 
intelligence, 26(1 l),pp. 1452-1458. 
Nock,R., Nielsen, F., 2005. Semi-supervised statistical region 
refinement for color image segmentation. Pattern 
Recognition, 38(6), pp. 835-846. 
Sramek,M. and Wrbka,T.,1997. Watershed based image 
segmentation- an effective tool for detecting landscape structure. 
In .Digital Image Processing and Computer 
Graphics(DIP ’97),Proc. SPIE 3346,pp.227-235. 
Xu, H.Q., 2004. Classification of fused imagery based on the 
SFIM Algorithm. Geomatics and Information Science of Wuhan 
University,29(10), pp.920-923. 
I’lHH 
sfcsSa 
1261