A new digital repository for remotely sensed hyperspectral imagery with unmixing-based retrieval functionality

摘要

Hyperspectral imaging is concerned with the measurement, analysis, and interpretation of spectra acquired froma given scene (or specific object) at a short, medium or long distance by an airbone or satellite sensor. Over thelast few years, hyperspectral image data sets have been collected for a great amount of locations over the world,using a variety of instruments for Earth observation. Despite the increasing importance of hyperspectral imagesin remote sensing applications, there is no common repository of hyperspectral data intended to distribute andshare hyperspectral data sets in the community. Quite opposite, the hyperspectral data sets which are availablefor public use are spread among different storage locations and present significant heterogeneity regarding thestorage format, associated meta-data (if any), or ground-truth availability. As a result, the development ofa standardized hyperspectral data repository is a highly desired goal in the remote sensing community. Inthis paper, we take a necessary first step towards the development of a digital repository for remotely sensedhyperspectral data. The proposed system allows uploading new hyperspectral data sets along with meta-data,ground-truth and analysis results, with the ultimate goal of sharing publicly available hyperspectral images withinthe remote sensing community. The database has been designed in order to allow storing relevant information forthe hyperspectral data available through the system, including basic image characteristics (width, height, numberof bands, format) and more advanced meta-data (ground-truth information, publications in which the data hasbeen used). The current implementation consists of a front-end to ease the management of images througha web interface, thus containing both synthetic and real hyperspectral images from two highly representativeinstruments, such as NASAs Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) over the Cuprite MiningDistrict in Nevada. Most importantly, the developed system includes a spectral unmixing-based content basedimage retrieval (CBIR) functionality which allows searching for images on the spectral unmixing information(spectrally pure components or endmembers and their associated abundances in the scene). This informationis stored as meta-data associated to each hyperspectral image instance, and then used to search and retrieveimages based on information content. This paper presents the design of the system and a preliminary validationof the unmixing-based retrieval functionality using both synthetic and real hyperspectral images stored in thedatabase.© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.