An Improved YOLOv5 Model Based on Feature Fusion and Attention Mechanism for Multiscale Satellite Recognition

Space target recognition is a crucial task in space situational awareness (SSA) and a significant research area in space exploration. Recognizing space targets poses challenges due to their varying scales and reflective surface materials, resulting in a lack of reliable visual features. This article proposes a multiscale spatial target recognition method based on YOLOv5 to address these limitations. The proposed method overcomes the challenges by optimizing the initial anchor frame using an improved K-means++ algorithm, enhancing network stability. Selective kernel networks are introduced to mitigate complex background interference and enhance effective feature representation, even when optical features are missing. In addition, an improved bidirectional feature pyramid network (FPN) structure extracts features from small targets in deep space by fusing multiscale features through partial cross-stage connectivity. Combining these three improvements enables high-accuracy recognition of multiscale targets. To diversify the dataset, Unity3D is used to simulate multiscale targets with reflective optical characteristics, complementing existing darkroom target images. This hybrid dataset with multiscale targets is used for training and testing. Experimental results demonstrate the model’s superiority in extracting critical target features. mAP@.5 improved by 2.55% and mAP@.5:.95 improved by 4.3%. Ablation analysis further validates the effectiveness of each improved module. Overall, the proposed model substantially enhances the recognition accuracy of multiscale targets.