A Multiphase Level Set Evolution Scheme for Aerial Image Segmentation Using Multi-scale Image Geometric Analysis

This paper describes a new aerial images segmentation algorithm. The algorithm is based upon the knowledge of image multi-scale geometric analysis which can capture the image’s intrinsic geometrical structure efficiently. The Contourlet transform is selected to represent the maximum information of the image and obtain the rotation invariant features of the image. A modified Mumford-Shah model is built to segment the aerial image by a necessary level set evolution. To avoid possible local minima in the level set evolution, we control the value of weight numbers of features in different evolution periods in this algorithm, instead of using the classical technique which evolve in a multi-scale fashion.

[1]  Minh N. Do.  Contourlets and sparse image expansions , 2003, SPIE Optics + Photonics.

[2]  Truong T. Nguyen,et al.  Multiresolution direction filterbanks: theory, design, and applications , 2005, IEEE Transactions on Signal Processing.

[3]  S. Levitt,et al.  Texture measures for building recognition in aerial photographs , 1997, Proceedings of the 1997 South African Symposium on Communications and Signal Processing. COMSIG '97.

[4]  A. L. Reno,et al.  Using models to recognise man-made objects , 1999, Proceedings Second IEEE Workshop on Visual Surveillance (VS'99) (Cat. No.98-89223).

[5]  Robert M. Gray,et al.  Image classification by a two dimensional hidden Markov model , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[6]  Alok Gupta,et al.  Dynamic Programming for Detecting, Tracking, and Matching Deformable Contours , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Gilles Aubert,et al.  Wavelet-based level set evolution for classification of textured images , 2003, IEEE Trans. Image Process..

[8]  Prabir Kumar Biswas,et al.  Rotation invariant texture features using rotated complex wavelet for content based image retrieval , 2004, 2004 International Conference on Image Processing, 2004. ICIP '04..

[9]  Xin Yang,et al.  A two-stage level set evolution scheme for man-made objects detection in aerial images , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[10]  Minh N. Do,et al.  CRISP contourlets: a critically sampled directional multiresolution image representation , 2003, SPIE Optics + Photonics.

[11]  Tony F. Chan,et al.  A Multiphase Level Set Framework for Image Segmentation Using the Mumford and Shah Model , 2002, International Journal of Computer Vision.

[12]  David J. Marchette,et al.  Identification of Man-Made Regions in Unmanned Aerial Vehicle Imagery and Videos , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  Mark J. T. Smith,et al.  A filter bank for the directional decomposition of images: theory and design , 1992, IEEE Trans. Signal Process..

[14]  M. Vetterli,et al.  Contourlets: a new directional multiresolution image representation , 2002, Conference Record of the Thirty-Sixth Asilomar Conference on Signals, Systems and Computers, 2002..

[15]  D. Mumford,et al.  Optimal approximations by piecewise smooth functions and associated variational problems , 1989 .