Procesamiento de imágenes hiperespectrales
La biblioteca Hyperspectral Imaging Library for Image Processing Toolbox™ proporciona funciones y herramientas de MATLAB® para procesar y visualizar imágenes hiperespectrales y multiespectrales.
Utilice las funciones de esta biblioteca para leer, escribir y procesar datos captados con sensores hiperespectrales y multiespectrales en distintos formatos de archivo. La biblioteca es compatible con el formato nacional de transmisión de imágenes (NITF), el formato del Entorno de Visualización de Imágenes (ENVI), el formato de archivo de imagen etiquetado (TIFF), el formato de extensión de texto de metadatos (MTL), el formato de datos jerárquicos (HDF) y el formato de archivo estándar para Europa (SAFE).
La biblioteca presenta una serie de algoritmos para la selección de bandas, la eliminación de ruido, la corrección radiométrica y atmosférica, la reducción de dimensionalidad, la extracción de miembros terminales, la estimación de mapas de abundancia, la correspondencia espectral, la detección de anomalías, el cálculo de índices espectrales y la segmentación.
La app Hyperspectral Viewer permite leer datos hiperespectrales y multiespectrales, visualizar metadatos e información geoespacial, visualizar imágenes de bandas individuales y sus histogramas, crear una gráfica espectral de un píxel o una región en un cubo de datos, representar miembros terminales, generar representaciones en color diferente o en color falso, calcular índices espectrales y exportar resultados.
Para analizar imágenes hiperespectrales y multiespectrales, descargue la biblioteca Hyperspectral Imaging Library for Image Processing Toolbox desde Add-On Explorer. Para obtener más información sobre la descarga de complementos, consulte Descargar y administrar complementos.
Apps
| Hyperspectral Viewer | Visualizar datos hiperespectrales y multiespectrales |
Funciones
Temas
Primeros pasos
- Get Started with Hyperspectral Image Processing
Basics of hyperspectral image processing. - Analyze Hyperspectral and Multispectral Images
Describes approaches to hyperspectral and multispectral imaging. - Explore Hyperspectral and Multispectral Data in the Hyperspectral Viewer
This example shows how to explore hyperspectral and multispectral data using the Hyperspectral Viewer app. - Process Large Hyperspectral and Multispectral Images
This example shows how to process small regions of large hyperspectral and multispectral images. - Hyperspectral and Multispectral 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.
Clasificación
- Classify Hyperspectral Image Using Library Signatures and SAM
Classify pixels in a hyperspectral image by using the spectral angle mapper (SAM) classification algorithm. - Classify Hyperspectral Images Using Deep Learning
This example shows how to perform hyperspectral image classification using a custom spectral convolution neural network (CSCNN). - Classify Hyperspectral Image Using Support Vector Machine Classifier
This example shows how to perform hyperspectral image classification using a support vector machine (SVM) classifier.
Identificación de una región
- 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.
Gemelo digital
- Generate RoadRunner Scene Using Aerial Hyperspectral and Lidar Data (Automated Driving Toolbox)
Generate RoadRunner scene from aerial hyperspectral and lidar data.
Segmentación
- Interactively Segment Hyperspectral Image Using Segment Anything Model
This example shows how to interactively preprocess and segment a hyperspectral image using the Segment Anything Model (SAM). (Desde R2025a)
Ejemplos destacados
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.
Classify Land Cover Using Hyperspectral and Lidar Data
Classify land cover using a fusion of hyperspectral and lidar data.
Segment Spleen in Hyperspectral Image of Porcine Tissue
Segment a spleen in a hyperspectral image of porcine tissue.
Classify Land Cover Using Sentinel-2 Multispectral Images
Fine-tune a pretrained segmentation model backbone, using Sentinel-2 Level 2A multispectral images and CORINE Land Cover 2018 data, for pixel-level land-cover classification.
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.
Map Flood Areas Using Sentinel-1 SAR Imagery
Map flooded areas using Sentinel-1 Synthetic Aperture Radar (SAR) images.
Change Detection in Hyperspectral Images
Detect changes in land cover from hyperspectral images taken at different times.
Manually Label ROIs in Multispectral Image
Manually select regions of interest (ROIs) from a multispectral image and save them in a shapefile.
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.
Endmember Material Identification Using Spectral Library
Identify the classes of endmember materials present in a hyperspectral image.
Automate Pixel Labeling of Hyperspectral Images Using Image Labeler
Load hyperspectral images into the Image Labeler (Computer Vision Toolbox) and automatically label pixels.
