中国空间科学技术

中国空间科学技术 ›› 2025, Vol. 45 ›› Issue (6): 99-110.doi: 10.16708/j.cnki.1000-758X.2025.0092

• 论文 • 上一篇    

深度学习在星图质心测量中的应用

熊琰1,2，齐静雅1,2，孟小迪1,2，武延鹏1,2,*   

  1. 1.北京控制工程研究所 空间光电测量与感知实验室，北京100190
    2.中国空间技术研究院，北京100094
  • 收稿日期:2024-09-24 修回日期:2025-05-21 录用日期:2025-05-30 发布日期:2025-11-17 出版日期:2025-12-01

Application of deep learning in centroid measurement of star images

XIONG Yan1,2，QI Jingya1,2,*，MENG Xiaodi1,2，WU Yanpeng1,2,*   

  1. 1.Space Optoelectronic Measurement and Perception Lab, Beijing Institute of Control Engineering，Beijing 100190,China
    2.China Academy of Space Technology，Beijing 100094，China
  • Received:2024-09-24 Revision received:2025-05-21 Accepted:2025-05-30 Online:2025-11-17 Published:2025-12-01

PDF (PC)

0

摘要： 星敏感器在轨拍摄星图时，光斑质心测量精度与计算效率是其关键性能指标。研究旨在提出一种基于深度学习的质心测量方法（Deep Learning-based Centroid Measurement, DLCM），以解决传统质心测量方法在精度和计算效率方面的不足，尤其在噪声干扰和复杂星图条件下的表现。DLCM方法采用卷积神经网络（CNN）来自动提取星图中的复杂特征，并在网络的输出层使用多个全连接层进行质心位置的回归预测。为了训练神经网络，仿真模拟了在不同噪声水平下的高斯光斑，并通过大量的训练数据优化网络结构。DLCM方法能够自适应不同噪声和图像变化，而无须手动调整参数或根据图像特性进行预处理。实验结果表明，DLCM方法在3σ内可以实现0.05像素的星图质心测量精度，并展现出较好的鲁棒性和泛化能力，此外，DLCM方法在计算效率上也具备显著优势。实验结果验证了DLCM在星图质心测量中的应用潜力，具有较好的精度和高效性。该方法为未来高精度星敏感器及其他光电指向测量设备的研发提供了有效的技术支持。

关键词: 深度学习, 星图, 质心测量算法, 卷积神经网络, 星敏感器

Abstract: The centroid measurement accuracy and computational efficiency of star spots in star charts are key performance indicators for star sensors in space. This study aims to develop a deep learning-based centroid measurement method (Deep Learning-based Centroid Measurement, DLCM) to address the limitations of traditional centroid measurement methods in terms of accuracy and computational efficiency, particularly under noisy conditions and complex star charts. The DLCM method utilizes convolutional neural networks (CNN) to automatically extract complex features from star charts, and employs multiple fully connected layers in the output layer of the network to predict the centroid position through regression. To train the neural network, Gaussian spots under various noise levels are simulated, and the network structure is optimized using a large volume of training data. The DLCM method adapts to varying noise levels and image conditions without requiring manual parameter adjustments or preprocessing based on image characteristics. Experimental results demonstrate that the DLCM method achieves a centroid measurement accuracy of 0.05 pixels within a 3σ range, with excellent robustness and generalization capabilities. Furthermore, DLCM shows significant advantages in computational efficiency. The experimental results validate the potential application of DLCM in star chart centroid measurement, showcasing its high accuracy and efficiency. This method provides effective technical support for the development of future high-precision star sensors and other electro-optical pointing measurement devices.

Key words: deep learning, star images, centroid measurement algorithm, convolutional neural network, star sensors