Coordinate-Aware Multiscale Feature Fusion Network for Spacecraft Component Recognition

With the increasing number of satellites and the growing complexity of space missions, accurate recognition of spacecraft components has become a critical requirement for on-orbit servicing tasks. However, existing deep learning-based methods often struggle to detect small-scale components due to the significant size disparity among different spacecraft parts, leading to recognition degradation. To address this issue, a Coordinate-Aware Multiscale Feature Fusion Network for Spacecraft Component Recognition(CAMFFN) is proposed in order to enhance multi-scale representation and spatial sensitivity. The proposed architecture comprises two key components: the Multi-branch Feature Enhancement Module(MFEM) and the Multi-scale Coordinate-aware Pyramid Aggregation Module(MCPAM). MFEM employs a multi-branch convolutional framework, which contains three parallel branches to capture fine-grained local texture and long-range context information simultaneously, aiming at enhancing spatial structure representation and directional sensitivity. MCPAM first extracts fused features through adaptive pyramid pooling and a hierarchical separable convolutional fusion operation, and then applied a coordinate attention mechanism to these fused features to precisely capture spatial dependencies along horizontal and vertical directions. Experimental results on two publicly available datasets, UESD and URSO, show that CAMFFN outperforms existing state-of-the-art methods, especially in the recognition of fine-grained and small-scale components such as instruments and thrusters.