A Graph Convolutional Network Framework for Area Attention and Tracking Compensation of In-Orbit Satellite

In order to solve the problems of low tracking accuracy of in-orbit satellites by ground stations and slow processing speed of satellite target tracking images, this paper proposes an orbital satellite regional tracking and prediction model based on graph convolutional networks (GCNs). By performing superpixel segmentation on the satellite tracking image information, we constructed an intra-frame superpixel seed graph node network, enabling the conversion of spatial optical image information into artificial-intelligence-based graph feature data. On this basis, we propose and build an in-orbit satellite region of interest prediction model, which effectively enhances the perception of in-orbit satellite feature information and can be used for in-orbit target prediction. This model, for the first time, combines intra-frame and inter-frame graph structures to improve the sensitivity of GCNs to the spatial feature information of in-orbit satellites. Finally, the model is trained and validated using real satellite target tracking image datasets, demonstrating the effectiveness of the proposed model.