Abstract
AbstractThe automated detection of coasts, riverbanks, and polynyas from synthetic aperture radar images is a difficult image processing task due to speckle noise. In this work we present a novel Fuzzy-Wavelet framework for bordeline region detection in SAR images. Our technique is based on a combination of Wavelet denoising and Fuzzy Logic which boost decision-making on noisy and poorly defined environments. Unlike most recent filtering-detection algorithms, we do not apply hypothesis tests (Wilcoxon-Mann Whitney-G0) to label the edge point candidates one by one, instead we construct a fuzzy map from wavelet denoised image and extract their borderline. We compare our algorithm performance with the popular Frost–Sobel approach and a version of Canny’s algorithm with data-dependent parameters, over a database of real polynyas and coastline simulated images under the multiplicative model. The experimental results are evaluated by comparing Pratt’s Figure of Merit index of edge map quality. In almost all tes...
Highlights
The study of polynya coasts is of paramount importance since it allows to analyze the effect of temperature variation and krill insertion in the ocean, among others (Stringer & Groves, 1991; Tamura & Ohshima, 2011)
In the case of synthetic aperture radar (SAR) imagery, it is subject to speckle noise which is of multiplicative nature, increasing drastically the variance of the data when the region observed is considered extremely-heterogeneous
The study of coastal polynyas is involved in many environmental applications such as predicting and understanding climate change, and tracking the highest concentrations of phytoplankton, the foundation of the marine food chain
Summary
The study of polynya coasts is of paramount importance since it allows to analyze the effect of temperature variation and krill insertion in the ocean, among others (Stringer & Groves, 1991; Tamura & Ohshima, 2011). A crucial point for SAR image automatic interpretation is the low level step of scene segmentation, i.e. the decomposition of the image in a tessellation of uniform areas. Testing methods consist in scanning the image with a sliding two-region window and evaluating for each position if there is a change between the two regions by hypothesis testing. Such tests are dependent of the true underlying conditional distributions that are emitted by the states (classes) of the image field, and the regions considered in the test implementation (Baselice & Ferraioli, 2012; Lim & Jang, 2002; Touzi, Lopes, & Bousquet, 1988). In all cases a standard edge detector like Sobel, Canny, or Snakes, is applied to the skeleton intermediate image to obtain a map with single pixel curves (Gambini, Mejail, Jacobo-Berlles, & Frery, 2006)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
