帮助 关于我们

返回检索结果

高光谱图像分数域信息提取理论与方法进展
Recent Developments in Fractional Information Extraction Theory and Methods of Hyperspectral Image

查看参考文献58篇

文摘 高光谱传感技术具有光谱、空间、辐射等信息同步获取的优势,促使地物描述呈现多尺度、多角度、多维度的特性,基于高光谱图像实施信息精确提取及解析,是建设先进对地观测系统等国家战略的核心需求.然而,高光谱图像信息提取存在光谱维诊断信息不确定、空间维信息利用不充分、协同维信息表征不全面等问题,导致信息感知与解译效果差,严重制约了其行业应用.高光谱智能感知在对地观测等多元领域中的应用,需要机理清晰、关联合理、协同有效的多域信息提取理论与方法.本文综述了高光谱图像分数域信息提取理论与方法进展,首先给出了现有的高光谱图像信息提取方法及其关键问题,然后从光谱维、空谱维、协同维三方面给出了高光谱图像分数域信息提取理论与方法体系.本文随后从光谱维精确控制、空谱维强化感知、协同维信息联合三方面分别总结了关键理论与应用:在光谱维,针对高光谱图像光谱信息提取易受到光谱不确定性现象影响而难以准确区分微弱点目标与复杂背景的问题,分数域光谱信号表征方法可提升光谱域辨识性能,实施高光谱异常检测;在空谱维,针对高光谱场景中地物空间分布不均衡,标签样本不足导致场景解译困难的问题,分数域空谱特征提取方法在有效训练集合扩充的同时提升网络学习的多样性,实施小样本情况下的场景解译;在协同维,针对高光谱与其他传感源存在异质性,导致地物三维信息表征不全面的问题,分数域多源协同特征提取与融合方法可实现多源多域特征联合,完成高精度地物分类.最后,本文指出了未来高光谱图像分数域信息提取理论与方法面临的挑战和发展趋势:面向高光谱数据体量大、分辨率较差等局限性,开展数据、特征层结合的质量提升方法研究;面向训练样本缺失问题,通过深度特征迁移学习技术,充分挖掘高光谱遥感图像中海量无标签数据的多维度光谱、空间、协同信息;面向广域空天遥感对地观测需求,研究模态缺失情况下的深度样本生成、特征扩充、多源跨场景分类方法.
其他语种文摘 Hyperspectral sensing technology can acquire spectral, spatial, radiation and other information synchronously, which provides the multi-scale, multi-angle, and multi-dimensional features of land covers. However, there are significant challenges in hyperspectral information extraction, e.g., spectral uncertainty, insufficient utilization of spatial information, and incomplete representation of collaborative information, resulting in poor information extraction and scene interpretation. The applications of hyperspectral interpretation, e.g., earth observation, requires multi-domain information extraction theories and methods to breakthrough these problems. In this survey, we firstly present the existing methods for hyperspectral information extraction and their main problems, and then introduce the fractional information extraction theory and methods of hyperspectral image, which consists of spectral dimension, spatial-spectral dimension, and collaborative dimension. Then, the main theories and applications are introduced, including spectral information adjustment, spatial-spectral information enhancement, and information fusion and transferring of multisource remote sensing data. For spectral dimension, the spectral uncertainty phenomenon makes it difficult to distinguish small targets from complex backgrounds. Focusing on this problem, the fractional-domain spectral information extraction method can improve the performance of hyper-spectral anomaly detection. For spatial dimension, the complex spatial distribution of hyperspectral scenes and the lack of labeled samples make the scene interpretation challenging. Focusing on this problem, the fractional-domain spatial-spectral feature extraction methods can effectively generate more discriminative training features and improve the diversity of training sets, which contribute to handling small sample size problems. For the collaborative dimension, the fractional-domain multi-source feature extraction and fusion method can realize the joint use of multi-source and multi-domain features, and achieve high-precision classification. Finally, this survey points out the challenges and development trends of fractional information extraction theory for hyperspectral images. To breakthrough the limitations of hyperspectral data, e.g., high-dimension and low-resolution, it is important to improve the data quality at data- and feature-level. To solve the problem of unavailable training samples, transfer learning techniques are in need to fully exploit the spectral, spatial and collaborative information of the massive unlabeled data in hyperspectral remote sensing images. Targeting the global-scale earth observation by remote sensing, focusing on the condition when some modalities are missing, researches on domain generation and cross-scene classification are in need.
来源 电子学报 ,2022,50(12):2874-2883 【核心库】
DOI 10.12263/DZXB.20221215
关键词 高光谱图像 ; 分数域信息提取 ; 特征提取 ; 异常检测 ; 高光谱图像分类 ; 多源遥感
地址

北京理工大学信息与电子学院, 北京, 100081

语种 中文
文献类型 研究性论文
ISSN 0372-2112
学科 电子技术、通信技术
基金 北京市自然科学基金
文献收藏号 CSCD:7415467

参考文献 共 58 共3页

1.  Landgrebe D. Hyperspectral image data analysis. IEEE Signal Processing Magazine,2002,19(1):17-28 CSCD被引 49 次    
2.  童庆禧. 高光谱遥感:原理、技术与应用,2006 CSCD被引 60 次    
3.  张兵. 高光谱图像分类与目标探测,2011:85-101 CSCD被引 2 次    
4.  Chen C. Spectral-spatial classification of hyperspectral image based on kernel extreme learning machine. Remote Sensing,2014,6(6):5795-5814 CSCD被引 20 次    
5.  Dalponte M. Fusion of hyperspectral and LIDAR remote sensing data for classification of complex forest areas. IEEE Transactions on Geoscience and Remote Sensing,2008,46(5):1416-1427 CSCD被引 25 次    
6.  Xu X D. Multisource remote sensing data classification based on convolutional neural network. IEEE Transactions on Geoscience and Remote Sensing,2018,56(2):937-949 CSCD被引 31 次    
7.  Ravikanth L. Extraction of spectral information from hyperspectral data and application of hyperspectral imaging for food and agricultural products. Food and Bioprocess Technology,2017,10(1):1-33 CSCD被引 5 次    
8.  Camps-Valls G. Advances in hyperspectral image classification: Earth monitoring with statistical learning methods. IEEE Signal Processing Magazine,2014,31(1):45-54 CSCD被引 27 次    
9.  Durkee N. Longwave infrared hyperspectral emissivity retrieval with robustness to spectral uncertainty. IEEE Transactions on Geoscience and Remote Sensing,2022,60:1-13 CSCD被引 1 次    
10.  Tao C. Unsupervised spectralspatial feature learning with stacked sparse autoencoder for hyperspectral imagery classification. IEEE Geoscience and Remote Sensing Letters,2015,12(12):2438-2442 CSCD被引 22 次    
11.  Mei X G. Spectral-spatial attention networks for hyperspectral image classification. Remote Sensing,2019,11(8):963 CSCD被引 14 次    
12.  Hang R L. Classification of hyperspectral and LiDAR data using coupled CNNs. IEEE Transactions on Geoscience and Remote Sensing,2020,58(7):4939-4950 CSCD被引 14 次    
13.  Ehlers M. Multi-sensor image fusion for pansharpening in remote sensing. International Journal of Image and Data Fusion,2010,1(1):25-45 CSCD被引 6 次    
14.  Tao R. Hyperspectral anomaly detection by fractional Fourier entropy. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2019,12(12):4920-4929 CSCD被引 15 次    
15.  Winograd S. On computing the discrete Fourier transform. Mathematics of Computation,1978,32(141):175-199 CSCD被引 10 次    
16.  Tang Y Y. Hyperspectral image classification based on three-dimensional scattering wavelet transform. IEEE Transactions on Geoscience and Remote Sensing,2015,53(5):2467-2480 CSCD被引 6 次    
17.  Li W. Collaborative representation for hyperspectral anomaly detection. IEEE Transactions on Geoscience and Remote Sensing,2015,53(3):1463-1474 CSCD被引 58 次    
18.  Mei S H. Hyperspectral image spatial super-resolution via 3D full convolutional neural network. Remote Sensing,2017,9(11):1139 CSCD被引 10 次    
19.  Du B. A discriminative metric learning based anomaly detection method. IEEE Transactions on Geoscience and Remote Sensing,2014,52(11):6844-6857 CSCD被引 19 次    
20.  Li W. A survey on representation-based classification and detection in hyperspectral remote sensing imagery. Pattern Recognition Letters,2016,83:115-123 CSCD被引 5 次    
引证文献 1 篇

1 林知心 基于轻量级全连接张量映射网络的高光谱图像分类方法 电子学报,2024,52(10):3541-3551
CSCD被引 0 次

显示所有1篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号