Here, an efficient multi-objective automatic segmentation framework (MASF) is formulated and applied to synthetic aperture radar (SAR) image unsupervised classification. In the framework, three important issues are presented: 1) two reasonable image preprocessing techniques, including spatial filtering and watershed operator, are discussed at the initial stage of the framework; 2)then, an efficient immune multi-objective optimization algorithm with uniform clone, adaptive selection by online nondominated solutions, and dynamic deletion in diversity maintenance is proposed; 3 two very simple, but very efficient conflicting clustering validity indices are incorporated into the framework and simultaneously optimized. Two simulated SAR data and two complicated real images are used to quantitatively validate its effectiveness. In addition, four other state-of-the-art image segmentation methods are employed for comparison.
In this paper, we present a novel approach for detecting the changed regions caused by flooding events in multi-temporal
SAR images. And the proposed method concludes two parts: 1) constructing difference image (DI) by fusion strategy
proposed in this paper; 2) producing change-detection map based on FCM and fuzzy degree of nearness. Experimental
comparisons on real multi-temporal SAR images indicate that the proposed method can reduce the affection by speckle
noise. Meanwhile, the proposed method can accurately detect the interested changed regions.
A novel and effective immune multi-objective clustering algorithm (IMCA) is presented in this study. Two conflicting
and complementary objectives, called compactness and connectedness of clusters, are employed as optimization targets.
Besides, adaptive ranks clone, variable length chromosome crossover operation and k-nearest neighboring list based
diversity holding strategies are featured by the algorithm. IMCA could automatically discover the right number of
clusters with large probability. Seven complicated artificial data sets and two widely used synthetic aperture radar (SAR)
imageries are used for test IMCA. Compared with FCM and VGA, IMCA has obtained good and encouraging clustering
results. We believe that IMCA is an effective algorithm for solving these nine problems, which should deserve further
research.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.