期刊
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
卷 10, 期 6, 页码 1562-1566出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2013.2262073
关键词
Ship classification; sparse representation classification (SRC); synthetic aperture radar (SAR) image.
类别
资金
- National Natural Science Foundation of China [61240058]
Ship classification is the key step in maritime surveillance using synthetic aperture radar (SAR) imagery. In this letter, we develop a new ship classification method in TerraSAR-X images based on sparse representation in feature space, in which the sparse representation classification (SRC) method is exploited. In particular, to describe the ship more accurately and to reduce the dimension of the dictionary in SRC, we propose to employ a representative feature vector to construct the dictionary instead of utilizing the image pixels directly. By testing on a ship data set collected from TerraSAR-X images, we show that the proposed method is superior to traditional methods such as the template matching (TM), K-nearest neighbor (K-NN), Bayes and Support Vector Machines (SVM).
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据