Multiscale Algorithms for the Geometric Analysis of Hyperspectral Data

高光谱数据几何分析的多尺度算法

• 批准号: 1720452
• 负责人: Demetrio Labate
• 金额: $ 27.03万
• 依托单位: University of Houston
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-10-01 至 2022-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1720452&HistoricalAwards=false
• 关键词: Multiscale; Algorithms; Geometric; Analysis; Hyperspectral

Hyperspectral imaging is a sensing technique that collects hundreds of narrowband images from across the electromagnetic spectrum. By both going beyond the visible spectrum and accurately discriminating wavelengths within the visible range, this technology can be remarkably powerful for distinguishing different materials when standard imagery is ineffective. As a result, hyperspectral remote sensing offers unique capabilities for tasks that include monitoring the development and health of crops, mapping oil spills and invasive species, and detecting objects that may be camouflaged. With modern remote sensing applications not being constrained to satellite images, however, the image acquisition in many scenarios is no longer under controlled conditions, because illumination, physical parameters, and viewing angles may change over time and objects of interest may be partially occluded. This investigation introduces a new generation of mathematical and algorithmic tools that are designed to provide robust classification of hyperspectral data under such realistic conditions. The project aims to develop a new class of analysis and classification algorithms for hyperspectral data that are robust with respect to changes of illumination, viewpoint, and physical conditions. The results are intended to have direct application to the monitoring of environmental conditions in coastal wetlands and to other observations of societal, economic, and national security interest.While hyperspectral imaging and image processing have been well developed within the remote-sensing community, image acquisition in remote sensing may occur in conditions where illumination, physical parameters, and viewing angle change over time. This research program combines ideas from sparse representations, multilayer convolutional networks, and machine learning to address the challenges to imaging posed by such changing conditions. A novelty of the approach is the adaptation of methods from sparse representations and shearlets, an anisotropic multiscale system that is particularly effective at capturing the directional content of multidimensional data. This approach provides the basis for constructing a deep learning neural convolutional network tailored to hyperspectral data and designed to generate stable and robust feature vectors. This investigation aims to develop an efficient multiscale representation that is customized to the specifics of hyperspectral data. The scattering transform will be adapted in combination with shearlets by exploiting the covariance properties of shearlets under affine transformations to build stable and viewpoint-invariant features for hyperspectral data. A novel hierarchical scheme for classification optimized for the specific structure of hyperspectral data and sparsity-based inpainting methods to restore hyperspectral data corrupted by occlusions will be developed. These new algorithms will be used for the analysis of hyperspectral data to monitor environmental conditions of coastal wetlands, a challenging case study of great social and economic importance.

高光谱成像是一种传感技术，它可以从整个电磁频谱中收集数百个窄带图像。通过超越可见光谱并准确区分可见光范围内的波长，该技术可以在标准图像无效时区分不同的材料。因此，高光谱遥感为监测作物生长和健康状况、绘制漏油和入侵物种图以及探测可能被入侵的物体等任务提供了独特的能力。然而，随着现代遥感应用不限于卫星图像，在许多情况下图像获取不再处于受控条件下，因为照明、物理参数和视角可能随时间而改变，并且感兴趣的对象可能被部分遮挡。这项调查介绍了新一代的数学和算法工具，旨在提供强大的高光谱数据在这样的现实条件下的分类。该项目旨在为高光谱数据开发一类新的分析和分类算法，这些算法对于照明，视点和物理条件的变化具有鲁棒性。 结果是为了有直接的应用程序在沿海湿地的环境条件的监测和其他观察的社会，经济和国家安全interests.While高光谱成像和图像处理已经很好地发展在遥感社区，遥感图像采集可能会发生在光照，物理参数和视角随时间变化的条件下。该研究计划结合了稀疏表示，多层卷积网络和机器学习的思想，以解决这种变化条件对成像带来的挑战。该方法的一个新奇是从稀疏表示和剪切波，各向异性的多尺度系统，是特别有效地捕捉多维数据的方向性内容的方法的适应。这种方法为构建深度学习神经卷积网络提供了基础，该网络专为高光谱数据量身定制，旨在生成稳定和强大的特征向量。这项调查的目的是开发一个有效的多尺度表示，是定制的高光谱数据的具体情况。散射变换将与剪切波相结合，利用剪切波在仿射变换下的协方差特性，为高光谱数据建立稳定和视点不变的特征。将开发一种新的分层分类方案，针对高光谱数据的特定结构进行优化，并开发基于稀疏性的修复方法来恢复被遮挡破坏的高光谱数据。这些新算法将用于分析高光谱数据，以监测沿海湿地的环境条件，这是一个具有重大社会和经济意义的具有挑战性的案例研究。

项目成果

Blind Image Inpainting with Sparse Directional Filter Dictionaries for Lightweight CNNs

• DOI: 10.1007/s10851-022-01119-6
• 发表时间: 2022-05
• 期刊: Journal of Mathematical Imaging and Vision
• 影响因子: 2
• 作者: Jenny Schmalfuss;Erik Scheurer;Hengyuan Zhao;Nikolaos Karantzas;Andrés Bruhn;D. Labate

Directional multiscale representations and applications in digital neuron reconstruction

• DOI: 10.1016/j.cam.2018.09.003
• 发表时间: 2019-03-15
• 期刊: JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS
• 影响因子: 2.4
• 作者: Kayasandik，Cihan;Guo，Kanghui;Labate，Demetrio
• 通讯作者: Labate，Demetrio

Geometric Separation in $$\mathbb {R}^3$$ R 3

$$mathbb {R}^3$$ R 3 中的几何分离

• DOI: 10.1007/s00041-017-9569-z
• 发表时间: 2018
• 期刊: Journal of Fourier Analysis and Applications
• 影响因子: 1.2
• 作者: Guo, Kanghui;Labate, Demetrio
• 通讯作者: Labate, Demetrio

Shearlet-based regularized reconstruction in region-of-interest computed tomography

感兴趣区域计算机断层扫描中基于剪切波的正则化重建

• DOI: 10.1051/mmnp/2018014
• 发表时间: 2018
• 期刊: Mathematical modelling of natural phenomena
• 影响因子: 2.2
• 作者: Bubba, T;Labate, D;Zanghirati, G;Bonettini, S
• 通讯作者: Bonettini, S

Image inpainting using sparse multiscale representations: Image recovery performance guarantees

• DOI: 10.1016/j.acha.2020.05.001
• 发表时间: 2020-09
• 期刊: Applied and Computational Harmonic Analysis
• 影响因子: 2.5
• 作者: K. Guo;D. Labate;J. P. R. Ayllon