Revisiting-Aware In-Orbit Edge Computing for Earth Observation

2026-07-28

AI Summary

This work addresses the challenge of prolonged revisit cycles and poor data timeliness in Earth observation caused by limited satellite downlink bandwidth. To tackle this issue, the authors propose Stride, an on-orbit edge computing framework that introduces, for the first time, a revisit-aware mechanism. By integrating multi-temporal cloud detection, a two-stage (coarse-to-fine) reference image selection strategy, and ensemble-based local change detection, Stride transmits only temporally non-redundant regions of interest back to the ground. Experimental results on both the FlatSat testbed and a constellation simulator demonstrate substantial performance gains: Stride achieves a 4.55× improvement in RID score, a 5.02× reduction in connection latency, and a 2.56× expansion in mapping coverage, outperforming all existing approaches.

Abstract

Typically, Earth observation satellites follow a rule of revisiting cycle to periodically pass over the same area of the Earth at regular intervals, which is jointly determined by their orbital properties (e.g., eccentricity, inclination) and instrument characteristics (e.g., off-nadir pointing and swath capabilities). However, we have observed delays in perceived revisiting cycles where limited satellite downlink bandwidth allows only partial images to be delivered, pushing back the timeliness of the full set of data, which we term as revisiting cycle delay. In this paper, we present a revisiting-aware in-orbit edge computing framework for Earth observation termed Stride. Stride leverages the unique orbital revisiting properties to afford historical reference revisiting images onboard, and exploits the inherent temporal redundancy in the revisiting imagery to transmit only the Regions of Interest (RoIs). Specifically, Stride comprises a mono- and multi-temporal cloud indicator to alleviate cloud contamination, a coarse-to-fine reference selector for orbit deviation correction, and an ensemble-local change detector to address inter-band complexities and pixel-level perturbations. Experiments on a Flat-Sat testbed and a constellation simulator demonstrate Stride improves the Revisiting Imagery Delivery (RID) score by up to 4.55X, decreases the connectivity latency by 5.02X, and enlarges the mapping coverage by 2.56X, yielding state-of-the-art performance.

Problem

• revisiting cycle delay
• Earth observation
• in-orbit edge computing
• downlink bandwidth
• temporal redundancy

Innovation

• in-orbit edge computing
• revisiting-aware
• temporal redundancy
• regions of interest (RoIs)
• change detection