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

Abstract

Abstract-In this research paper, we propose supervised and unsupervised change detection methodologies focused on the analysis of multitemporal Synthetic Aperture Radar (SAR) images. These approaches are based on three main steps: (1) a comparison of multitemporal image was carried out by normalized difference ratio (NDR) operator; (2) implementing a novel supervised or unsupervised thresholding and (3) generating the change map by coupling of thresholding along with a region growing algorithm. In the first step, two filtered multitemporal images were used to generate NDR image that was subjected to analysis. In the second step, by assuming a Gaussian distribution in the no-change area, we identified the pixel range that fits the Gaussian distribution better than any other range iteratively to detect the no-change area that eventually separates the change areas. In the supervised method, several sample no-change pixels were selected and the mean (μ) and the standard deviation (σ) were obtained. Then, μ ± 3σ was applied to select the best threshold values. Finally, a traditional thresholding algorithm was modified and implemented with the coupling of the region growing algorithm to consider the spatial information to generate the change map. The Gaussian distribution was assumed because it better fits the conditional densities of the no-change class in the NDR image. The effectiveness of the proposed methods was verified with the simulated images and the real images associated with geographical locations. The results were compared with the manual trial and error procedure (MTEP) and traditional unsupervised expectation-maximization (EM) method. Both proposed methods gave similar results with MTEP and significant improvement in Kappa coefficient in comparison to the traditional EM method was found in both geographical locations. 520 Mishra and SusakiThe coupling of the modified thresholding with the region growing algorithm is very effective with all methods.

Sensitivity Analysis for L-Band Polarimetric Descriptors and Fusion for Urban Land Cover Change Detection

“…This method appears to give nearly the same results as the manual trial-and-error procedure, but it depends on the selected sample [12].…”

“…In order to reduce the speckle noise present in the SAR image, enhanced Lee filter [11] of window size 5 × 5 was implemented. The window size was selected with caution, if the size is bigger, the spatial resolution will lose and if the window size is smaller, the filter will not be effective [1], [12].…”

“…This operator was introduced by Coppin and Bauer in [13] and later used on optical images in [14] and on SAR images in [12]. The NDR operator is better for change detection than other traditional operators [12], [14], because the NDR image has less errors than an image produced by difference or ratio operator. We now compare the errors generated from NDR and ratio operator.…”

“…Regarding the probability density function (PDF) of such multimodel images, the authors in [2] performed a comparative study of Nakagami, Lognormal, and Weibull distribution for ratio images and concluded that all have comparable results. Similarly, the no-change area is better modeled with Gaussian distribution than the Logistic and Student's t distribution with the image generated by the NDR operator [12].…”

“…Similarly, pixels with value less than t 1 − σ are classified as having a decrease in intensity and those with values greater than t 2 + σ are classified as having an increase in intensity. The remaining pixels, from t 1 − σ to t 1 + σ and from t 2 − σ to t 2 + σ, remained unclassified [12].…”