CFAR-Based Adaptive PolSAR Speckle Filter

Abstract

The patch-based polarimetric synthetic aperture radar (PolSAR) nonlocal means (NLM) speckle filters are efficacious in noise suppression and detail preservation, but are computationally inefficient. The objective of this paper is to develop a filter that provides better noise suppression and edge preservation along with reduced computational complexity for PolSAR applications. In this paper, the patch-based NLM adaptive speckle filter based on constant false alarm rate (CFAR) edge detector is proposed. The CFAR-based edge detector is used to generate a map that classifies the data into three regions: homogeneous, heterogeneous, and strong edge dominant regions. The proposed speckle filter adapts itself suitably based on the heterogeneity of the region using classified regions as a mask. The performance of proposed filtering technique is evaluated on 1-look simulated (generated by Monte Carlo simulation), 1-look RADARSAT-2, and 4-look AIRSAR data. The performance evaluation is done based on the extent of noise reduction measured by equivalent number of looks, edge preservation degree, bias in estimation, polarimetric structure preservation, and visual appearance. The performance of the proposed filtering technique is found to be better than the state-of-the-art speckle filtering techniques like refined Lee, NLM pretest, and NL-SAR. The order of computational complexity of the proposed filter is found to be better than the pretest or NL-SAR filters.