An Energy-Efficient Artefact Detection Accelerator on FPGAs for Hyper-Spectral Satellite Imagery

TL;DR

This paper introduces an energy-efficient FPGA-based convolutional autoencoder for detecting artefacts in hyper-spectral satellite images, enabling faster and more power-efficient processing suitable for CubeSat deployment.

Contribution

It presents a novel unsupervised learning model and deployment architecture optimized for FPGA hardware, improving artefact detection speed and energy efficiency in satellite imaging.

Findings

Processing time per spectral band: 4 ms, 2.6x faster than Nvidia Jetson

F1-score of 92.8% with 0% FPR across datasets

Energy consumption of 21.52 mJ per image, 3.6x more efficient than Jetson inference

Abstract

Hyper-Spectral Imaging (HSI) is a crucial technique for analysing remote sensing data acquired from Earth observation satellites. The rich spatial and spectral information obtained through HSI allows for better characterisation and exploration of the Earth's surface over traditional techniques like RGB and Multi-Spectral imaging on the downlinked image data at ground stations. Sometimes, these images do not contain meaningful information due to the presence of clouds or other artefacts, limiting their usefulness. Transmission of such artefact HSI images leads to wasteful use of already scarce energy and time costs required for communication. While detecting such artefacts before transmitting the HSI image is desirable, the computational complexity of these algorithms and the limited power budget on satellites (especially CubeSats) are key constraints. This paper presents an unsupervised learning-based convolutional autoencoder (CAE) model for artefact identification of acquired HSI images at the satellite and a deployment architecture on AMD's Zynq Ultrascale FPGAs. The model is trained and tested on widely used HSI image datasets: Indian Pines, Salinas Valley, the University of Pavia and the Kennedy Space Center. For deployment, the model is quantised to 8-bit precision, fine-tuned using the Vitis-AI framework and integrated as a subordinate accelerator using AMD's Deep-Learning Processing Units (DPU) instance on the Zynq device. Our tests show that the model can process each spectral band in an HSI image in 4 ms, 2.6x better than INT8 inference on Nvidia's Jetson platform & 1.27x better than SOTA artefact detectors. Our model also achieves an f1-score of 92.8% and FPR of 0% across the dataset, while consuming 21.52 mJ per HSI image, 3.6x better than INT8 Jetson inference & 7.5x better than SOTA artefact detectors, making it a viable architecture for deployment in CubeSats.