MultiF-RSNet: Distributed interpretation for multi-platform collaborative in remote sensing

Abstract

Advances in remote sensing technology have significantly improved the on-orbit processing capabilities of satellites. A distributed collaborative inference approach for multi-platform remote sensing is introduced. This method leverages the synergy of multiple platforms to enhance inference precision. Initially, a feature compression module is implemented to reduce data transmission demands. Subsequently, a multi-layer feature fusion module is employed to integrate features from various platforms. Simulation experiments on public datasets confirm that our multi-platform collaborative object detection algorithm outperforms single-platform independent inference, validating its effectiveness.