An unsupervised approach based on the generalized Gaussian model to automatic change detection in multitemporal SAR images

Abstract

Abstract-In this paper, we present a novel automatic and unsupervised change-detection approach specifically oriented to the analysis of multitemporal single-channel single-polarization synthetic aperture radar (SAR) images. This approach is based on a closed-loop process made up of three main steps: 1) a novel preprocessing based on a controlled adaptive iterative filtering; 2) a comparison between multitemporal images carried out according to a standard log-ratio operator; and 3) a novel approach to the automatic analysis of the log-ratio image for generating the change-detection map. The first step aims at reducing the speckle noise in a controlled way in order to maximize the discrimination capability between changed and unchanged classes. In the second step, the two filtered multitemporal images are compared to generate a log-ratio image that contains explicit information on changed areas. The third step produces the change-detection map according to a thresholding procedure based on a reformulation of the Kittler-Illingworth (KI) threshold selection criterion. In particular, the modified KI criterion is derived under the generalized Gaussian assumption for modeling the distributions of changed and unchanged classes. This parametric model was chosen because it is capable of better fitting the conditional densities of classes in the log-ratio image. In order to control the filtering step and, accordingly, the effects of the filtering process on change-detection accuracy, we propose to identify automatically the optimal number of despeckling filter iterations [Step 1)] by analyzing the behavior of the modified KI criterion. This results in a completely automatic and self-consistent change-detection approach that avoids the use of empirical methods for the selection of the best number of filtering iterations. Experiments carried out on two sets of multitemporal images (characterized by different levels of speckle noise) acquired by the European Remote Sensing 2 satellite SAR sensor confirm the effectiveness of the proposed unsupervised approach, which results in change-detection accuracies very similar to those that can be achieved by a manual supervised thresholding.

OBSERVATION OF CENTER DISASTER DAMAGE ON PARIAMAN AND WASIOR USING DIFFERENTIAL SAR INTERFEROMETRY (DInSAR)

“…Assuming that c and u in the image ratio (the log ratio results) represented two opposite classes, the minimum error threshold or also called threshold selection criteria Kittler Illingworth (KI) [15], is derived from the assumption that the object and background are normally distributed. KI method is based on Bayesian decision theory and requires a parametric model to describe the statistical distribution for the region that has changed or not [14].…”

Coupling of Thresholding and Region Growing Algorithm for Change Detection in Sar Images

“…Most of the thresholding algorithms are based on parametric approaches that assume a predefined statistical model in all change and no-change classes [2,3,5,10,12]. But, due to the dynamic behavior of the changing area and its complex nature, assuming a predefined statistical model for change class may not be valid in all cases.…”

“…Several methodologies are found in the literature for change detection using SAR images. Most of them started from generating the change image using multi-temporal intensity or amplitude images [3][4][5]. They then used the supervised or unsupervised thresholding algorithm to segment the change and no-change areas but very few works have been done by including spatial information in the SAR change detection when moderate to low resolution images are used.…”

“…A few other similar papers [5][6][7] also recommended the ratio method, which is sensitive to the presence of image speckles in the scene. Paper [3] implemented controlled adaptive iterative filtering and comparing the multi-temporal images using the log-ratio operator; finally an Expectation-Maximization (EM) thresholding algorithm was implemented. Paper [5] examines the effective methods for urban change detection using multi-temporal space borne SAR images.…”

“…Most of the above thresholding algorithms are applicable to bi-level thresholding [2,3,9,10]. The histogram of the image is assumed to have one valley between two peaks.…”