An Approach Based on Multi-feature Classification for Azimuth Ambiguity Identification with ATI-SAR Systems

Konferenz: EUSAR 2018 - 12th European Conference on Synthetic Aperture Radar
04.06.2018 - 07.06.2018 in Aachen, Germany

Tagungsband: EUSAR 2018

Seiten: 5Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Xu, Huajian; Yang, Jian (National Laboratory of Radar Signal Processing, Xidian University, China)
Yang, Zhiwei (National Laboratory of Radar Signal Processing and the Collaborative Innovation Centre of Information Sensing and Understanding, Xidian University, China)

It is a core issue for moving target (or ship) detection to identify azimuth ambiguities in the inshore region with along-track interferometric (ATI)-synthetic aperture radar (SAR) systems. To this end, an approach based on multi-feature classification is proposed in this paper without any geographic information. The proposed method first classify SAR image automatically according to the distance between azimuth ambiguities and main clutter in the joint distribution of interferogram's phase and magnitude by using the expectation maximum (EM) algorithm, and then the Markov random field (MRF) technique is exploited to smooth the segmented results. Finally, the experiments on real TerraSAR-X data set demonstrate the effectiveness of the proposed approach.