A Multiphase Level Set Method Based on Total Variation Density Estimation for Image Classification


Article Preview

Remotely sensed imagery with high spatial resolution often shows serious intra-class spectral variations and details disturbances. This leads to disadvantages on automatic image classification. To increase accuracy of classification, this paper presents a novel multiphase level set method by an optimization of probability density function(pdf) estimation using Total Variation(TV). Specifically, density estimation method using Total Variation originally from image denoising is introduced to well improve “roughness” of pdf caused by spectral variations and details disturbances. Then, the optimized pdf is used to improve Mansouri’s model so as to alleviate local minimum solutions and to further increase classification accuracy. Evidential experiments on IKONOS, QuickBird-2 satellite imagery have demonstrated that our proposed density estimation method is very effective and robust even if in complex scene. Consequently, the improved multiphase level set model has yielded a great increase in classification accuracy. The classification result is more approaching to that of human vision interpretation.



Advanced Materials Research (Volumes 121-122)

Edited by:

Donald C. Wunsch II, Honghua Tan, Dehuai Zeng, Qi Luo






Y. Yang et al., "A Multiphase Level Set Method Based on Total Variation Density Estimation for Image Classification", Advanced Materials Research, Vols. 121-122, pp. 458-463, 2010

Online since:

June 2010




[1] T. Blaschke, S. Lang: Object Based Image Analysis for Automated Information Extraction-A Synthesis, MAPPS/ASPRS, (2006).

[2] G. Cao, Z. h. Mao and X. Yang: Optical aerial image partitioning using level sets based on modified Chan-Vese model. Patter Recognition Letters, Vol. 29, 457-464(2008).

DOI: 10.1016/j.patrec.2007.10.024

[3] C. Samson, L. Blanc-Féraud, G. Aubert and J. Zerubia: Multiphase Evolution and Variational Image Classification, INRIA , Technical Report, No. 3662(1999).

[4] C. Samson, L. Blanc-Féraud, G. Aubert and J. Zerubia: A Level Set Model for Image Classification, International Journal of Computer Vision, Vol. 40, No. 3, pp.187-197(2000).

DOI: 10.1023/a:1008183109594

[5] J.E. Ball and L.M. Bruce: Level Set Segmentation of Remotely Sensed Hyper-spectral Images, IGARSS '05, Vol. 8, 5638- 5642(2005).

DOI: 10.1109/igarss.2005.1526055

[6] A.R. Mansouri and J. Konrad: Multiple motion segmentation with level sets. IEEE Transactions on Image Processing, Vol. 12, No. 2, 201-220(2003).

DOI: 10.1109/tip.2002.807582

[7] A.R. Mansouri, A. Mitiche and C. Va'zquez: Multiregion competition: A level set extension of region competition to multiple region image partitioning, Computer Vision and Image Understanding, No. 101, 137-150 (2006).

DOI: 10.1016/j.cviu.2005.07.008

[8] L. Vese, T. F. Chan, A Multiphase Level Set Framework for Image Segmentation Using the Mumford and Shah Model, International Journal of Computer Vision, Vol. 50, No. 3, p.271293, (2002).

[9] T. Brox and J. Weickert: Level Set Based Image Segmentation with Multiple Regions, In Pattern Recognition, Springer LNCS 3175, C-E, 415-423(2004).

DOI: 10.1007/978-3-540-28649-3_51

[10] C.P. Lee: Robust Image Segmentation using Active Contours: Level Set Approaches, PhD Dissertation, North Carolina State University(2005).

[11] L. Ying, Y. Yun: Non-parametric multiple level set model for efficient image classification in urban areas, 2009 Joint Urban Remote Sensing Event, 1-6(2009).

DOI: 10.1109/urs.2009.5137591

[12] G.O. Mohler, Andrea L. Bertozzi, Thomas A. Goldstein, et al.,: Fast TV Regularization for 2D Maximum Penalized Likelihood Estimation(2009), http: /www. math. ucla. edu/applied/cam.

[13] P.J. Green: Penalized Likelihood, Encyclopedia of Statistical Sciences, Vol. 2, 578-586(1996).

[14] L.M. Smith, M.S. Keegan, T. Wittman et al.: Improving Density Estimation by Incorporating Spatial Information, 2009, http: /www. math. ucla. edu/~lsmith/ research. html.

[15] L. Rudin, S. Osher, and E. Fatemi: Nonlinear Total Variation based Noise Removal Algorithms. Physica D, 60: 259-268(1992).

DOI: 10.1016/0167-2789(92)90242-f

[16] D J. Field: Relation between the statistics of natural images and the response properties of cortical cells. Journal of the Optical Society of American, 4(12): 2379-2394(1987).

[17] T. Bailloeul, Active contours and prior knowledge for change analysis: application to digital urban building map updating from optical high resolution remote sensing images, Ph.D. dissertation, CASIA and. INPT, Oct. (2005).

In order to see related information, you need to Login.