Low-latency delivery of satellite imagery is essential for time-critical applications such as disaster response, intelligence, and infrastructure monitoring. However, traditional pipelines rely on downlinking all captured images before analysis, introducing delays of hours to days due to restricted communication bandwidth. To address these bottlenecks, emerging systems perform onboard machine learning to prioritize which images to transmit. However, these solutions typically treat each satellite as an isolated compute node, limiting scalability and efficiency. Redundant inference across satellites and tasks further strains onboard power and compute costs, constraining mission scope and responsiveness. We present EarthSight, a distributed runtime framework that redefines satellite image intelligence as a distributed decision problem between orbit and ground. EarthSight introduces three core innovations: (1) multi-task inference on satellites using shared backbones to amortize computation across multiple vision tasks; (2) a ground-station query scheduler that aggregates user requests, predicts priorities, and assigns compute budgets to incoming imagery; and (3) dynamic filter ordering, which integrates model selectivity, accuracy, and execution cost to reject low-value images early and conserve resources. EarthSight leverages global context from ground stations and resource-aware adaptive decisions in orbit to enable constellations to perform scalable, low-latency image analysis within strict downlink bandwidth and onboard power budgets. Evaluations using a prior established satellite simulator show that EarthSight reduces average compute time per image by 1.9x and lowers 90th percentile end-to-end latency from first contact to delivery from 51 to 21 minutes compared to the state-of-the-art baseline.

翻译：低延迟的卫星图像交付对于灾害响应、情报收集及基础设施监测等时效性关键应用至关重要。然而传统处理流程依赖将所有采集图像下传至地面后再进行分析，受限于通信带宽，引入数小时至数天的延迟。为解决此瓶颈，新兴系统通过星载机器学习优先传输关键图像，但此类方案通常将每颗卫星视为独立计算节点，制约了可扩展性与效率。卫星间及任务间的冗余推理进一步加剧了星上功率与计算资源消耗，限制了任务范围与响应能力。本文提出EarthSight——一种重新定义卫星图像智能为轨道与地面间分布式决策问题的运行时框架。EarthSight包含三项核心创新：(1) 基于共享骨干网络的多任务星上推理，通过多视觉任务间的计算分摊降低开销；(2) 地面站查询调度器，聚合用户请求、预测优先级并为传入图像分配计算预算；(3) 动态滤波器排序，综合模型选择性、精度及执行成本，提前剔除低价值图像以节约资源。EarthSight利用地面站全局上下文与轨道端资源感知自适应决策，使卫星星座在严格的下行带宽与星上功率预算约束下实现可扩展的低延迟图像分析。基于先前建立的卫星模拟器评估表明，与最先进基线相比，EarthSight将单幅图像平均计算时间降低1.9倍，并将90%分位端到端延迟（从首次接触至交付）从51分钟降至21分钟。