A New Digital Repository for Hyperspectral Imagery With Unmixing-Based Retrieval Functionality Implemented on GPUs

Abstract

Over the last few years, hyperspectral image data have been collected for a large number of locations over the world, using a variety of instruments for Earth observation. In addition, several new hyperspectral missions will become operational in the near future. Despite the increasing availability and large volume of hyperspectral data in many applications, there is no common repository of hyperspectral data intended to distribute and share free hyperspectral data sets in the community. Quite opposite, the hyperspectral data sets which are available for public use are spread among different storage locations and exhibit significant heterogeneity regarding their format, associated meta-data (if any), or ground-truth information. The development of a standardized hyperspectral data repository is a highly desired goal in the remote sensing community. In this paper, we take a necessary first step toward the development of a completely open digital repository for remotely sensed hyperspectral data. The proposed system (available online for public use at: http://www.hypercomp.es/repository) allows uploading new hyperspectral data sets along with meta-data, ground-truth, analysis results, and pointers to bibliographic references describing the use of the data. The current implementation consists of a front-end which allows management of hyperspectral images through a web interface. The system is implemented on a parallel cluster system in order to guarantee storage availability and fast performance. The system includes a spectral unmixing-guided content-based image retrieval (CBIR) functionality which allows searching for images from the database using queries or available information such as spectral libraries. Specifically, for each new hyperspectral scene which is cataloged in our system, we extract the spectrally pure components (endmembers) and their associated fractional abundances, and then store this information as metadata associated to the hyperspectral image. The meta-data can be used to efficiently retrieve images based on their information content. In order to accelerate the process of obtaining the metadata for a new entry in the system, we develop efficient implementations of spectral unmixing algorithms on graphics processing units (GPUs). This paper particularly focuses on the software design of the system and provides an experimental validation of the unmixing-based retrieval functionality using both synthetic and real hyperspectral images.