How to fully explore the low-rank property for data recovery of hyperspectral images

Shaohui Mei, Qianqian Bi, Jingyu Ji, Junhui Hou, Qian Du

科研成果: 书/报告/会议事项章节会议稿件同行评审

1 引用 (Scopus)

摘要

The performance of hyperspectral classification is affected by within-class spectral variation since different materials may present similar spectral signatures. In this paper, we investigate how to fully use the low-rank property of hyperspectral images to alleviate spectra variation. Particulary, two effective strategies that explore the low-rank property in local spectral and spatial space are proposed. According to experimental results, we conclude that exploring the low-rank property in local spectral-spatial space can help to alleviate spectral variation and improve the performance of classification obviously for all tested data, while exploring the low-rank property in spatial space is more effective for images presenting large homogeneous areas.

源语言英语
主期刊名2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings
出版商Institute of Electrical and Electronics Engineers Inc.
3314-3317
页数4
ISBN(电子版)9781509033324
DOI
出版状态已出版 - 1 11月 2016
活动36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Beijing, 中国
期限: 10 7月 201615 7月 2016

出版系列

姓名International Geoscience and Remote Sensing Symposium (IGARSS)
2016-November

会议

会议36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016
国家/地区中国
Beijing
时期10/07/1615/07/16

指纹

探究 'How to fully explore the low-rank property for data recovery of hyperspectral images' 的科研主题。它们共同构成独一无二的指纹。

引用此