利用改进相似性度量方法进行高光谱海冰检测  

Hyperspectral Sea Ice Detection Using Improved Similarity Measurement Method

作　　者：韩彦岭[1] 李珏 张云[1] 洪中华[1] 

机构地区：[1]上海海洋大学信息学院,上海201306

出　　处：《遥感信息》2018年第1期76-85,共10页Remote Sensing Information

基　　金：国家自然科学基金(41376178;41401489;41506213);上海科学技术委员会(11510501300)

摘　　要：针对高光谱数据波段之间的相似性和冗余性导致传统海冰检测方法的精度和效率都难以提高的问题,提出了一种基于改进相似性度量的方法用于海冰检测。首先,使用互信息方法确定信息量最大的波段作为第1个初始波段;随后,使用光谱相似性度量方法选择与第1个初始波段最不相似的波段作为第2个初始波段;最后,使用线性预测方法选择剩余波段,并采用支持向量机分类器模型进行海冰分类。在2个高光谱海冰实验中,将所提出方法与传统海冰检测方法进行了对比验证,实验结果表明相对于其他方法,改进相似性度量方法在总体上具有更好的性能,该方法可以更有效地应用于高光谱海冰检测。Because of the similarity and redundancy between hyperspectral data bands,it is difficult to improve the accuracy and efficiency of the traditional sea ice detection method. This article proposes an improved similarity measure method for the sea ice detection. First,the first original band with a large amount of information is determined based on the mutual information theory. Subsequently, the second original band with the least similarity is chosen by the spectral correlation measure method. Finally,the subsequent bands are selected through the linear prediction method,and the support vector machine classifier model is utilized for sea ice classification. In two experiments, comparative analyses are carried out between the proposed method and traditional sea ice detection methods. The experimental results indicate that the proposed method exhibits better performance overall than other methods and can be effectively applied in hyperspectral sea ice detection.

关 键 词：海冰 相似性度量 波段选择 分类 高光谱图像 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]