| 高光谱遥感图像波段选择研究进展综述 |
| |
| 引用本文： | 杨红艳,杜健民. 高光谱遥感图像波段选择研究进展综述[J]. 计算机工程与应用, 2022, 58(10): 1-12. DOI: 10.3778/j.issn.1002-8331.2111-0403 |
| |
| 作者姓名： | 杨红艳 杜健民 |
| |
| 作者单位： | 1.内蒙古工业大学 机械工程学院，呼和浩特 0100512.内蒙古农业大学 机电工程学院，呼和浩特 0100183.内蒙古自治区特殊服役智能机器人重点实验室，呼和浩特 010051 |
| |
| 基金项目： | 国家自然科学基金;内蒙古工业大学科学研究项目 |
| |
| 摘 要： | 高光谱成像遥感技术可获取地物的光谱、辐射和空间信息,在国民经济的各个领域得到广泛的应用.但其狭窄的波段间距带来丰富光谱信息的同时,也带来了信息冗余,增加了数据处理的难度.因此,高光谱遥感数据在进行实际应用前,需要进行波段选择并提取光谱特征,降低数据维数.对高光谱遥感图像的波段选择研究进展进行了综述,在分析、归纳波段选择...
|
| 关 键 词： | 数字图像处理 遥感 高光谱图像 波段选择 |
Research Progress Review of Hyperspectral Remote Sensing Image Band Selection |
| |
| YANG Hongyan,DU Jianmin. Research Progress Review of Hyperspectral Remote Sensing Image Band Selection[J]. Computer Engineering and Applications, 2022, 58(10): 1-12. DOI: 10.3778/j.issn.1002-8331.2111-0403 |
| |
| Authors: | YANG Hongyan DU Jianmin |
| |
| Affiliation: | 1.College of Mechanical Engineering, Inner Mongolia University of Technology, Hohhot 010051, China2.College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University, Hohhot 010018, China3.Inner Mongolia Key Laboratory of Special Service Intelligent Robotics, Hohhot 010051, China |
| |
| Abstract: | Hyperspectral imaging remote sensing can obtain abundant spectral, radiation and spatial information of ground objects, which has been widely used in various fields of national economy. But its narrow band spacing brings not only rich spectral information, but also information redundancy and the difficulty of data processing. Therefore, before the practical application of hyperspectral remote sensing data, band selection is needed to extract spectral features and reduce the data dimension. This review summarizes the research progress of band selection for hyperspectral remote sensing images. Based on the analysis and summary of band selection strategies, the related technology and the latest research status are expounded from six aspects：the evaluation criteria of band selection, the band selection based on the combination of spatial and spectral features, the band selection based on semi-supervised learning, the band selection based on sparse representation, the band selection based on intelligent search and the band selection based on deep learning. Then, the current problems and challenges faced by hyperspectral image band selection are discussed. Finally, the future development direction of hyperspectral image band selection is predicted. |
| |
| Keywords: | digital image processing remote sensing hyperspectral image band selection |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载免费的PDF全文 |
|
