Unsupervised Change Detection for Satellite Images Using Dual-Tree Complex Wavelet Transform

• Published in: IEEE transactions on geoscience and remote sensing Vol. 48; no. 3; pp. 1199 - 1210
• Main Authors: Celik, T., Kai-Kuang Ma
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01-03-2010; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Applied geophysics; Bayesian inference; Change detection; Change detection algorithms; difference image; dual-tree complex wavelet transform (DT-DWT); Earth sciences; Earth, ocean, space; environmental monitoring; Error probability; Exact sciences and technology; expectation maximization (EM); Gaussian mixture modeling; Image analysis; Interference; Internal geophysics; Lighting; Masks; Mathematical models; multispectral images; multitemporal images; Noise; Noise level; Noise robustness; Pixel; remote sensing; satellite images; Satellites; Studies; surveillance; unsupervised thresholding; Wavelet transforms; algorithms; environmental monitoring; simulation; multispectral remote sensing; wavelet transformation; expectation maximization (EM); interferences; imagery; noise; multispectral images; surveillance; Bayesian inference; performances; satellite images; models; difference image; probability; Space remote sensing; dual-tree complex wavelet transform (DT-DWT); multitemporal images; remote sensing; Gaussian mixture modeling; monitoring; wavelet; change detection; errors; Pixel; unsupervised thresholding
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2009.2029095

In this paper, an unsupervised change-detection method for multitemporal satellite images is proposed. The algorithm exploits the inherent multiscale structure of the dual-tree complex wavelet transform (DT-CWT) to individually decompose each input image into one low-pass subband and six directional high-pass subbands at each scale. To avoid illumination variation issue possibly incurred in the low-pass subband, only the DT-CWT coefficient difference resulted from the six high-pass subbands of the two satellite images under comparison is analyzed in order to decide whether each subband pixel intensity has incurred a change. Such a binary decision is based on an unsupervised thresholding derived from a mixture statistical model, with a goal of minimizing the total error probability of change detection. The binary change-detection mask is thus formed for each subband, and all the produced subband masks are merged by using both the intrascale fusion and the interscale fusion to yield the final change-detection mask. For conducting the performance evaluation of change detection, the proposed DT-CWT-based unsupervised change-detection method is exploited for both the noise-free and the noisy images. Extensive simulation results clearly show that the proposed algorithm not only consistently provides more accurate detection of small changes but also demonstrates attractive robustness against noise interference under various noise types and noise levels.