Abstract
Dimensionality reduction represents a critical preprocessing step in order to increase the efficiency and the performance of many hyperspectral imaging algorithms. However, dimensionality reduction algorithms, such as the Principal Component Analysis (PCA), suffer from their computationally demanding nature, becoming advisable for their implementation onto high-performance computer architectures for applications under strict latency constraints. This work presents the implementation of the PCA algorithm onto two different high-performance devices, namely, an NVIDIA Graphics Processing Unit (GPU) and a Kalray manycore, uncovering a highly valuable set of tips and tricks in order to take full advantage of the inherent parallelism of these high-performance computing platforms, and hence, reducing the time that is required to process a given hyperspectral image. Moreover, the achieved results obtained with different hyperspectral images have been compared with the ones that were obtained with a field programmable gate array (FPGA)-based implementation of the PCA algorithm that has been recently published, providing, for the first time in the literature, a comprehensive analysis in order to highlight the pros and cons of each option.
Highlights
Hyperspectral imaging systems are nowadays considered as one of the most powerful remote sensing tools for acquiring precise information of the Earth’s surface
The dimensionality of the space spanned by the pixels of a particular hyperspectral image is generally much lower than its number of spectral bands, which means that some bands of hyperspectral images usually provide redundant information that can be reduced by identifying an appropriate subspace
When comparing these results with those that were obtained with the NVIDIA Graphics Processing Unit (GPU), it is clear that the results obtained with the GPU for the images considered in this work are much faster than those that were obtained with the manycore architecture
Summary
Hyperspectral imaging systems are nowadays considered as one of the most powerful remote sensing tools for acquiring precise information of the Earth’s surface. By selecting only the eigenvectors that correspond to the largest eigenvalues, a reduction of the dimensionality of the original data is achieved while retaining a wealth of information (variance) in the data This PCA dimensionality reduction has proven to bring the aforementioned benefits to the whole hyperspectral image processing chain, it is true that its utilization is not exempt from a formidable computational effort, which may compromise its use in time-sensitive (real-time or near real-time) applications. In these applications, the algorithms that are required for processing the data are typically implemented onto high-performance computing architectures in which the operations involved are executed in parallel devices [7,8,9].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
