Title :
MPM SAR Image Segmentation Using Feature Extraction and Context Model
Author :
Biao Hou ; Xiangrong Zhang ; Nan Li
Author_Institution :
Key Lab. of Intell. Perception & Image Understanding of the Minist. of Educ. of China, Xidian Univ., Xi´an, China
Abstract :
A new synthetic aperture radar (SAR) image segmentation method based on a maximization of posterior marginals (MPM) algorithm with feature extraction and context model is proposed in this letter. First, Gabor wavelet and texture descriptor are used to extract features, which enhance intraclass similarities and interclass differences. Second, the number of regions within the same class is reduced in order to improve the reliability of the regional statistical characteristics. Finally, the MPM of each region combined with the context model is calculated by considering both the intralayer correlation and interlayer correlation. The experimental results show that the proposed method is efficient and effective for SAR image segmentation.
Keywords :
Gabor filters; correlation methods; feature extraction; image matching; image segmentation; radar imaging; statistical analysis; synthetic aperture radar; wavelet transforms; Gabor wavelet descriptor; MPM SAR image segmentation; MPM algorithm; context model; feature extraction; interclass differences; intralayer correlation; maximization of posterior marginals algorithm; regional statistical characteristics; synthetic aperture radar image segmentation method; texture descriptor; Agriculture; Context; Context modeling; Feature extraction; Hidden Markov models; Image resolution; Image segmentation; Hierarchical Markov random field model; SAR image segmentation; maximization of posterior marginals (MPM); synthetic aperture radar (SAR); watershed segmentation;
Journal_Title :
Geoscience and Remote Sensing Letters, IEEE
DOI :
10.1109/LGRS.2012.2189352
