Image segmentation has been an important procedure in object-based image analysis (OBIA), which takes image object as a processing unit. The spatial scale in image segmentation has great importance in OBIA. Due to the high heterogeneity and large dynamic range of polarimetric synthetic aperture radar (PolSAR) images, it is often difficult to choose optimal spatial scales. This letter proposes a polarimetric semivariogram-based spatial scale selection method for PolSAR image segmentation. The optimal spatial bandwidth parameter in the mean-shift algorithm is pre-estimated based on the combined polarimetric and statistical analysis of PolSAR images. By implementing a quantitative evaluation of segmentation result, the effectiveness of the proposed method in optimal spatial bandwidth selection for PolSAR image segmentation is verified. Experiments on both the EMISAR and UAVSAR L-band PolSAR data sets testify the validity of the proposed adaptive optimal bandwidth selection strategy for PolSAR images.

Recently, an object-based Markov random field (OMRF) with auxiliary fields (OMRF-A) was developed for the processing of optical remote sensing images and it provided satisfactory results. However, it cannot be directly applied to polarimetric synthetic aperture radar (PolSAR) images with high heterogeneity. In addition, polarimetric information which plays a dominant role in PolSAR image interpretation cannot be effectively incorporated by the OMRF-A model. In order to solve this problem, an OMRF with polarimetric auxiliary fields (OMRF-PA) is developed in this letter for the classification of PolSAR images. A polarimetric index is developed to evaluate the information loss during iterations of label fields and auxiliary label fields. Then, an improved conditional probability distribution which incorporates the polarimetric index is proposed to account for the interactions between label fields and auxiliary label fields. Experiments on PolSAR data sets acquired by ESAR and EMISAR systems demonstrate that the proposed OMRF-PA model can generate a higher classification accuracy compared to the original OMRF-A method.

Morphology profiles (MPs) have been applied to the processing of different types of imagery, which have highly improved the segmentation and classification results. MPs can both preserve spatial structures of objects and construct the multiscale description of images. Since the speckle noise inherent in the images, the classification of PolSAR images cannot obtain satisfied results. In this paper, the framework of polarimetric object-based morphological profiles (POMPs) is proposed in which the MPs features and polarimetric features are combined and object-based image analysis (OBIA) is introduced to PolSAR image classification. Based on statistical measures of central tendency, the POMPs are obtained by integrating the feature vector of images with the segments of meanshift segmentation. To evaluate the effectiveness of the proposed method, POMPs are introduced to support vector machine (SVM) classifier. Experiments on the EMISAR image using object-based polarimetric features, object-based MPs and POMPs features respectively are implemented and compared. The results show that the proposed method can effectively improve classification accuracy of high resolution PolSAR images.