Distributed On-Orbit Sparse Coding for Efficient Space Situational Awareness Image Transmission

Space Situational Awareness (SSA) relies on Low Earth Orbit (LEO) satellites to capture continuous, high-resolution imagery critical for identifying space threats. The vast volume of SSA images overwhelms satellite network band-width, hindering timely transmission and processing. This paper presents a novel image compression method based on sparse coding to mitigate this transmission bottleneck. By exploiting the high sparsity and spatial-temporal redundancy of SSA images, we introduce an Aggregated Dictionary Learning (ADL) algorithm and a Context-aware Adaptive Binary Arithmetic Coding (OABAC) algorithm for further reducing dictionary and coefficient sizes. The proposed sparse coding is operated across LEO satellites in a distributed manner. Both overlapping and non-overlapping regions of the image are divided and processed paralleled on different satellites, optimizing resource usage and reducing latency. Evaluations show a 93.78% high compression ratio, surpassing existing methods and ensuring efficient SSA data transmission and processing in constrained satellite networks.