Study on segmentation and interpretation of multi-look polarimetric SAR images

The segmentation and interpretation of multi-look polarimetric synthetic ap erture radar (SAR) images is studied. We first introduce a multi-look polar imetric whitening filter (MPWF) to reduce the speckle in multi-look polarim etric SAR images. Then, by utilizing the wavelet multiresolution approach t o extract the texture information in different scales and the Markov random field (MRF) model to characterize the spatial constraints between pixels i n each scale level, a multiresolution segmentation algorithm (MSA) to segme nt the speckle-reduced SAR images is presented. The MSA first segments the image at the lowest resolution level and then proceeds to progressively hig her resolutions until individual pixels are well classified. An unsupervise d step to estimate both the optimal number of texture classes and their mod el parameters is also included in the MSA so that the segmentation can be i mplemented without supervision. Finally, in order to interpret the results of the unsupervised segmentation and to understand the whole polarimetric S AR image, we develop an image interpretation approach which jointly utilize s the scattering mechanism identification and target decomposition approach es. Experimental results with the real-world multi-look polarimetric SAR im age demonstrate the effectiveness of the segmentation and interpretation ap proaches.