期刊
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
卷 14, 期 5, 页码 597-601出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2017.2657818
关键词
Anomaly detection; convolutional neural network (CNN); deep learning; hyperspectral imagery
类别
资金
- National Natural Science Foundation of China [NSFC-91638201, 61571033]
- Higher Education and High-Quality and World-Class Universities [PY201619]
In this letter, a novel anomaly detection framework with transferred deep convolutional neural network (CNN) is proposed. The framework is designed by considering the following facts: 1) a reference data with labeled samples are utilized, because no prior information is available about the image scene for anomaly detection and 2) pixel pairs are generated to enlarge the sample size, since the advantage of CNN can be realized only if the number of training samples is sufficient. A multilayer CNN is trained by using difference between pixel pairs generated from the reference image scene. Then, for each pixel in the image for anomaly detection, difference between pixel pairs, constructed by combining the center pixel and its surrounding pixels, is classified by the trained CNN with the result of similarity measurement. The detection output is simply generated by averaging these similarity scores. Experimental performance demonstrates that the proposed algorithm outperforms the classic Reed-Xiaoli and the state-of-the-art representation-based detectors, such as sparse representation-based detector (SRD) and collaborative representation-based detector.
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