Adaptive multispectral GPU accelerated architecture for Earth Observation satellites

Abstract

Abstract-In recent years the growth in quantity, diversity and capability of Earth Observation (EO) satellites, has enabled increase's in the achievable payload data dimensionality and volume. However, the lack of equivalent advancement in downlink technology has resulted in the development of an onboard data bottleneck. This bottleneck must be alleviated in order for EO satellites to continue to efficiently provide high quality and increasing quantities of payload data.This research explores the selection and implementation of state-of-the-art multidimensional image compression algorithms and proposes a new onboard data processing architecture, to help alleviate the bottleneck and increase the data throughput of the platform. The proposed new system is based upon a backplane architecture to provide scalability with different satellite platform sizes and varying mission's objectives. The heterogeneous nature of the architecture allows benefits of both Field Programmable Gate Array (FPGA) and Graphical Processing Unit (GPU) hardware to be leveraged for maximised data processing throughput.

Error Resilient GPU Accelerated Image Processing for Space Applications

“…CCSDS-123 has been chosen as a case study for this research because it is the state-of-the-art lossless image compression algorithm for next generation onboard image processing, as discussed in [1]. Additionally, it is characteristically representative of other typical onboard data processing algorithms, featuring elements which are highly sequential in nature, which can be challenging to implement efficiently on GPU hardware.…”

“…Previous work conducted has focused on identifying suitable state-of-the-art image compression algorithms and the proposal of a new GPU accelerated onboard data processing system architecture. An extensive review of image compression algorithms was conducted and is summarised in [1]. In this review, the lossless image compression algorithm CCSDS-123 was demonstrated to be one of the most suitable for onboard implementation.…”

“…It provides an appropriate trade-off between minimising the required computational resources and maximising compression ratio performance for raw image data [2]. In [1], a new GPU accelerated scalable onboard data processing architecture for satellites was also proposed. To determine the feasibility and capabilities of a GPU based onboard data processing architecture, a new GPU accelerated parallel CCSDS-123 application has been developed [3].…”

GPU accelerated multispectral EO imagery optimised CCSDS-123 lossless compression implementation

“…Traditional space qualified processors are no longer able to meet the demands of current nor future onboard data processing system requirements [4]. Therefore, as part of previous research a new onboard data processing architecture has been proposed [1]. The new GPU accelerated scalable heterogeneous hardware architecture aims to facilitate the implementation of state-of-the-art parallel image processing and compression algorithm to help alleviate the growing onboard data bottleneck of EO satellite platforms.…”

“…This is due to the importance of data fidelity to many EO data applications, particularly as computer based image processing becomes increasingly prominent for information extraction. Currently most operational satellites implement standardised algorithms such as JPEG-LS or JPEG-2000 where both these algorithms typically achieve compression ratios of approximately 2.0 [1]. However, in order to help alleviate the increasing onboard data bottleneck, new state-of-the-art compression and processing algorithms will need to be deployed to achieve increased compression ratios onboard spaceborne platforms.…”