Real-Time Onboard AI for Remote Sensing: Cloud Detection

Abstract

In nanosatellite Earth observation, transmitting cloud-occluded imagery—about 67% of captures—wastes scarce onboard energy and downlink bandwidth. This letter presents an onboard AI framework that performs real-time on-orbit cloud detection, enabling selective transmission of only valid imagery. To counter the domain shift between public training data and onboard sensor observations, we adopt an unsupervised domain adaptation (UDA) scheme based on diffusion-driven style transfer, which produces sensor-stylized training data reflecting sensor-specific characteristics without any labeled onboard imagery, enabling robust cloud detection under real operational conditions. Hardware-in-the-loop (HIL) testing on a flight-representative Jetson Xavier NX confirms a full-image inference latency of 0.359 s, well within the 12.11-s interframe interval at 550-km altitude, supporting continuous real-time operation. The proposed approach reduces per-image energy consumption by 66.7%, with inference overhead accounting for only 0.97% of the total, and orbital simulation shows that fewer communication passes deliver equivalent valid imagery, yielding a $9.09\times $ improvement in valid-image throughput.