高光谱图像处理

导入、导出、处理和可视化高光谱数据

Image Processing Toolbox™ Hyperspectral Imaging Library 为高光谱图像处理和可视化提供 MATLAB^® 函数和工具。

使用此库中的函数可读取、写入和处理通过使用高光谱成像传感器以各种文件格式捕获的高光谱数据。该库支持国家图像传输格式 (NITF)、可视化图像环境 (ENVI)、标记图像文件格式 (TIFF) 和元数据文本扩展 (MTL) 文件格式。

该库提供一套算法，用于端元提取、丰度图估计、辐射和大气校正、降维、波段选择、光谱匹配和异常检测。

高光谱查看器使您能够读取高光谱数据，可视化单个波段图像及其直方图，为高光谱数据立方体中的像素或区域创建光谱图，生成高光谱图像的不同的彩色或假彩色表示，以及显示元数据。

要执行高光谱图像分析，请从附加功能资源管理器下载 Image Processing Toolbox Hyperspectral Imaging Library。有关下载附加功能的详细信息，请参阅获取和管理附加功能。

App

高光谱查看器

可视化高光谱数据 (自 R2020a 起)

函数

全部展开

探查、分析和可视化

读取和写入

`hypercube`	Read hyperspectral data (自 R2020a 起)
`enviwrite`	Write hyperspectral data to ENVI file format (自 R2020a 起)
`enviinfo`	Read metadata from ENVI header file (自 R2020a 起)

波段选择和条带删除

`selectBands`	Select most informative bands (自 R2020a 起)
`removeBands`	Remove spectral bands from data cube (自 R2020a 起)

ROI 选择

`assignData`	Assign new data to hyperspectral data cube (自 R2020a 起)
`cropData`	Crop regions-of-interest (自 R2020a 起)

颜色变换

colorize Estimate color image of hyperspectral data (自 R2020a 起)

滤波和增强

`denoiseNGMeet`	Denoise hyperspectral images using non-local meets global approach (自 R2020b 起)
`sharpencnmf`	Sharpen hyperspectral data using coupled nonnegative matrix factorization (CNMF) method (自 R2020b 起)

数据校正

辐射标定

`dn2radiance`	Convert digital number to radiance (自 R2020b 起)
`dn2reflectance`	Convert digital number to reflectance (自 R2020b 起)
`radiance2Reflectance`	Convert radiance to reflectance (自 R2020b 起)

大气校正

`correctOOB`	Correct out-of-band effect using sensor spectral response (自 R2020b 起)
`empiricalLine`	Empirical line calibration of hyperspectral data (自 R2020b 起)
`fastInScene`	Perform fast in-scene atmospheric correction (自 R2020b 起)
`flatField`	Apply flat field correction to hyperspectral data cube (自 R2020b 起)
`iarr`	Apply internal average relative reflectance (IARR) correction to hyperspectral data cube (自 R2020b 起)
`logResiduals`	Apply log residual correction to hyperspectral data cube (自 R2020b 起)
`rrs`	Compute remote sensing reflectance (自 R2020b 起)
`subtractDarkPixel`	Subtract dark pixel value from hyperspectral data cube (自 R2020b 起)
`sharc`	Perform atmospheric correction using satellite hypercube atmospheric rapid correction (SHARC) (自 R2020b 起)

频谱校正

`smileMetric`	Compute spectral smile metrics of hyperspectral data (自 R2021a 起)
`reduceSmile`	Reduce spectral smile effect in hyperspectral data cube (自 R2020b 起)

降维

`hyperpca`	Principal component analysis of hyperspectral data (自 R2020a 起)
`hypermnf`	Maximum noise fraction transform of hyperspectral data (自 R2020a 起)
`inverseProjection`	Reconstruct data cube from principal component bands (自 R2020a 起)

光谱解混

`ppi`	Extract endmember signatures using pixel purity index (自 R2020a 起)
`fippi`	Extract endmember signatures using fast iterative pixel purity index (自 R2020a 起)
`nfindr`	Extract endmember signatures using N-FINDR (自 R2020a 起)
`countEndmembersHFC`	Find number of endmembers (自 R2020a 起)
`estimateAbundanceLS`	Estimate abundance maps (自 R2020a 起)

光谱匹配和目标检测

`readEcostressSig`	Read data from ECOSTRESS spectral library (自 R2020a 起)
`resampleSignature`	Resample spectral signature to required wavelengths (自 R2024a 起)
`removeContinuum`	Normalize spectral signature (自 R2024a 起)
`sam`	Measure spectral similarity using spectral angle mapper (自 R2020a 起)
`sid`	Measure spectral similarity using spectral information divergence (自 R2020a 起)
`jmsam`	Measure spectral similarity using Jeffries Matusita-Spectral Angle Mapper method (自 R2020b 起)
`sidsam`	Measure spectral similarity using spectral information divergence-spectral angle mapper hybrid method (自 R2020b 起)
`ns3`	Measure normalized spectral similarity score (自 R2020b 起)
`spectralMatch`	Identify unknown regions or materials using spectral library (自 R2020a 起)
`detectTarget`	Detect target in hyperspectral image (自 R2024a 起)
`anomalyRX`	Detect anomalies using Reed-Xiaoli detector (自 R2020a 起)
`spectralIndices`	Compute hyperspectral indices (自 R2020b 起)
`customSpectralIndex`	Compute hyperspectral index using custom formula (自 R2023a 起)
`ndvi`	Normalized difference vegetation index (自 R2020a 起)

分割

`hyperslic`	2-D superpixel oversegmentation of hyperspectral images (自 R2023b 起)
`hyperseganchor`	Segment hyperspectral images using fast spectral clustering with anchor graphs (自 R2024a 起)

主题

快速入门

Getting Started with Hyperspectral Image Processing
Basics of hyperspectral image processing.
Explore Hyperspectral Data in the Hyperspectral Viewer
This example shows how to explore hyperspectral data using the 高光谱查看器 app.
Process Large Hyperspectral Images
This example shows how to process small regions of large hyperspectral images.
Hyperspectral Data Correction
Describes radiometric calibration, atmospheric correction, and spectral correction.
Spectral Matching and Target Detection Techniques
Techniques for target detection and spectral matching.
Spectral Indices
Describes spectral indices.
Support for Singleton Dimensions
Analysis of 1-D and 2-D spectral data using singleton hypercube.

区域标识

Target Detection Using Spectral Signature Matching
Detect a known target in the hyperspectral image by using the spectral matching method.
Identify Vegetation Regions Using Interactive NDVI Thresholding
Identify the types of vegetations regions in a hyperspectral image through interactive thresholding of a normalized difference vegetation index (NDVI) map.
Find Regions in Spatially Referenced Multispectral Image
This example shows how to identify water and vegetation regions in a Landsat 8 multispectral image and spatially reference the image.

精选示例

Predict Sugar Content in Grape Berries Using PLS Regression on Hyperspectral Data

Perform non-destructive testing (NDT) using hyperspectral data to predict sugar content in grape berries.

打开实时脚本

Classify Land Cover Using Hyperspectral and Lidar Data

Classify land cover using a fusion of hyperspectral and lidar data.

打开实时脚本

Segment Spleen in Hyperspectral Image of Porcine Tissue

Segment a spleen in a hyperspectral image of porcine tissue.

打开实时脚本

Ship Detection from Sentinel-1 C Band SAR Data Using YOLOX Object Detection

Detect ships from Sentinel-1 C Band SAR Data using YOLOX object detection.

打开实时脚本

Map Flood Areas Using Sentinel-1 SAR Imagery

Map flooded areas using Sentinel-1 Synthetic Aperture Radar (SAR) images.

打开实时脚本

Change Detection in Hyperspectral Images

Detect changes in land cover from hyperspectral images taken at different times.

打开实时脚本

Manually Label ROIs in Multispectral Image

Manually select regions of interest (ROIs) from a multispectral image and save them in a shapefile.

打开实时脚本

Hyperspectral Image Analysis Using Maximum Abundance Classification

Identify different regions in a hyperspectral image by performing maximum abundance classification (MAC). An abundance map characterizes the distribution of an endmember across a hyperspectral image. Each pixel in the image is either a pure pixel or a mixed pixel. The set of abundance values obtained for each pixel represents the percentage of each endmembers present in that pixel. In this example, you will classify the pixels in a hyperspectral image by finding the maximum abundance value for each pixel and assigning it to the associated endmember class.

打开实时脚本