The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. XXXVII. Part B4. Beijing 2008 
Figure 4. Extract edge of a block. Upper: image with initial 
curve. Underside: result curve 
method is very flexible, we can just extract the edge that we 
want and we can have some controls when the curve moves. 
Second, when we use edge detectors, sometimes we will meet a 
lot of problems of how to track the edges, while using level set 
method, the curve is continuous which make it easy to be 
tracking. At the end, we did not need to compute how accurate 
of the edge would be, but from the image, we can find that the 
result is very good. 
The disadvantage of this method is also obviously, because the 
algorithm of this method is much more complicated that other 
methods, it will cost a very long time if running on a low 
assembled PC which would limit its application of processing 
remote sensing image to a certain degree. 
REFERENCES 
Dusan Heric,Damjan Zazula, 2007. Combined edge detection 
using wavelet transform and signal registration. Image and 
Vision Computing, 25(5), pp. 652-662 
Ety Navon, Ofer Miller, Amir Arerbuch, 2005. Color image 
segmentation based on adaptive local thresholds. Image and 
Vision Computing, 23(1), pp. 69-85. 
Florence Jacquey, Frédéric Comby, Olivier Strauss, 2008. 
Fuzzy edge detection for omnidirectional images. Fuzzy Sets 
and Systems, In Press, Uncorrected Proof, Available online 18 
March 
Jiangping Fan, Guihua Zeng, Mathurin Body,Mohand-Said 
Hacid, 2005. Seeded region growing: an extensive and 
comparative study. Pattern Recognition, 26(8), pp. 1139-1156. 
Li Jiangtao, Ni Guoqiang, Huang Guanghua, 2007. Improved 
multiple entropy information segmentation algorithms for 
remote sensing images. Optical Technique, 33(4), pp. 543-550. 
Lijun Ding, Ardeshir Goshtasby, 2001. On the Canny edge 
detector. Pattern Recognition, 34(3), pp. 721-725. 
Figure 5. Extract edge of Jiuduansha Shoal in Changjiang 
Estuary. Upper: image with initial curve. Underside: result 
curve 
Liming Hu, H.D. Cheng, MingZhang, 2007. A high 
performance edge detector based on fuzzy inference rules. 
Information Sciences, 177(21), pp. 4768-4784 
M.Emin Yuksel, 2007. Edge detection in noisy images by 
neuro-fuzzy processing. AEU-Intemational Journal of 
Electronics and Communications, 61(2), pp. 82-89 
Ming-Yu,Shih, Din-Chang Tseng, 2005. A wavelet-based 
multiresolution edge detection and tracking. Image and Vision 
Computing 23(4), pp. 441-451. 
Phillip A. Mlsna, Jeffrey J. Rodriguez, 2005. Gradient and 
Laplacian Edge Detection. Handbook of Image and Video 
Processing (Second Edition). 
R.Medina-Camicer, F.J.Madrid-Cuevas, 2008. Unimodal 
thresholding for edge detection. Pattern Recognition, 41(7), pp. 
2337-2346. 
5. CONCLUSIONS 
Up to now, there are few papers about processing remote 
sensing image using level set method. But there are several 
advantages of extract edge using level set method. First, this 
Ronald P.Fedkiw, Guillermo Sapiro, Chi-Wang Shu, 
2003.Shock capturing,level sets and PDE based methods in 
computer vision and image processing: a review of Osher’s 
contributions. Journal of Computational Physics, 185(2), pp. 
309-341. 
436