Onboard deep lossless and near-lossless predictive coding of hyperspectral images with line-based attention
This addresses the challenge of applying deep learning to hyperspectral image compression onboard spacecrafts, offering a novel solution for space missions.
The paper tackled onboard compression of hyperspectral images by designing a predictive neural network, LineRWKV, which outperformed the CCSDS-123.0-B-2 standard in lossless and near-lossless compression on the HySpecNet-11k dataset and PRISMA images, with promising throughput results on a 7W embedded system.
Deep learning methods have traditionally been difficult to apply to compression of hyperspectral images onboard of spacecrafts, due to the large computational complexity needed to achieve adequate representational power, as well as the lack of suitable datasets for training and testing. In this paper, we depart from the traditional autoencoder approach and we design a predictive neural network, called LineRWKV, that works recursively line-by-line to limit memory consumption. In order to achieve that, we adopt a novel hybrid attentive-recursive operation that combines the representational advantages of Transformers with the linear complexity and recursive implementation of recurrent neural networks. The compression algorithm performs prediction of each pixel using LineRWKV, followed by entropy coding of the residual. Experiments on the HySpecNet-11k dataset and PRISMA images show that LineRWKV is the first deep-learning method to outperform CCSDS-123.0-B-2 at lossless and near-lossless compression. Promising throughput results are also evaluated on a 7W embedded system.