当前位置: X-MOL 学术J. Indian Soc. Remote Sens. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Two-Level Band Selection Framework for Hyperspectral Image Classification
Journal of the Indian Society of Remote Sensing ( IF 2.2 ) Pub Date : 2020-11-19 , DOI: 10.1007/s12524-020-01262-w
Munmun Baisantry , Anil Kumar Sao , Dericks Praise Shukla

Dimensionality reduction strategies can be broadly categorized as band selection and feature extraction. Researchers and analysts from the remote sensing community give greater preference to band selection over feature extraction as the latter modifies the original reflectance values of hyperspectral data, making it difficult to understand the behavior of the materials in terms of their reflectance values. However, feature extraction strategies have their own advantages which cannot be ignored. Thus, a two-level, PCA-based band selection framework is proposed to unify the two dimensionality reduction strategies so that benefits of both the strategies can be derived. The proposed approach selects bands based on their relationship with a given set of principal components explained in terms of component loadings, thus keeping the original bands intact. Additionally, contrary to the popular notion that the complete information of all bands is adequately coalesced in the top principal components, middle principal components play a far stronger discriminative role when the competing classes are spectrally confusing to each other. Thus, for each level of classification, a different range of principal components is used to select the bands, on the basis of the level of spectral similarity expected between the classes at each level. Experimental results indicate that the proposed two-level band selection algorithm can select bands with varying levels of discriminative capabilities to effectively classify hyperspectral images consisting of classes spectrally very similar in nature.

中文翻译:

高光谱图像分类的两级波段选择框架

降维策略可以大致分为波段选择和特征提取。遥感界的研究人员和分析师更倾向于选择波段而不是特征提取,因为后者会修改高光谱数据的原始反射率值,因此很难根据反射率值来理解材料的行为。然而,特征提取策略有其自身不可忽视的优势。因此,提出了一个基于 PCA 的两级波段选择框架来统一二维降维策略,从而可以得出两种策略的好处。建议的方法根据波段与一组给定的主成分的关系来选择波段,这些主成分是根据分量载荷解释的,从而保持原始乐队完好无损。此外,与所有波段的完整信息在顶部主成分中充分结合的流行观念相反,当竞争类在频谱上相互混淆时,中间主成分发挥更强的区分作用。因此,对于每个分类级别,根据每个级别的类别之间预期的光谱相似性级别,使用不同范围的主成分来选择波段。实验结果表明,所提出的两级波段选择算法可以选择具有不同级别判别能力的波段,以有效地对由光谱性质非常相似的类组成的高光谱图像进行分类。与所有波段的完整信息在顶部主成分中充分合并的流行观念相反,当竞争类在光谱上相互混淆时,中间主成分发挥更强的区分作用。因此,对于每个分类级别,根据每个级别的类别之间预期的光谱相似性级别,使用不同范围的主成分来选择波段。实验结果表明,所提出的两级波段选择算法可以选择具有不同级别判别能力的波段,以有效地对由光谱性质非常相似的类组成的高光谱图像进行分类。与所有波段的完整信息在顶部主成分中充分合并的流行观念相反,当竞争类在光谱上相互混淆时,中间主成分发挥更强的区分作用。因此,对于每个分类级别,根据每个级别的类别之间预期的光谱相似性级别,使用不同范围的主成分来选择波段。实验结果表明,所提出的两级波段选择算法可以选择具有不同级别判别能力的波段,以有效地对由光谱性质非常相似的类组成的高光谱图像进行分类。当竞争类在频谱上相互混淆时,中间主成分发挥更强的判别作用。因此,对于每个分类级别,根据每个级别的类别之间预期的光谱相似性级别,使用不同范围的主成分来选择波段。实验结果表明,所提出的两级波段选择算法可以选择具有不同级别判别能力的波段,以有效地对由光谱性质非常相似的类组成的高光谱图像进行分类。当竞争类在频谱上相互混淆时,中间主成分发挥更强的判别作用。因此,对于每个分类级别,根据每个级别的类别之间预期的光谱相似性级别,使用不同范围的主成分来选择波段。实验结果表明,所提出的两级波段选择算法可以选择具有不同级别判别能力的波段,以有效地对由光谱性质非常相似的类组成的高光谱图像进行分类。
更新日期:2020-11-19
down
wechat
bug