A model for suppressing stray light in astronomical images based on deep learning

Abstract

Wide-Field Small Aperture Telescopes (WFSAT) are widely used for surveilling space objects. Due to their wide-field of view (FOV) characteristics, these telescopes can cover a large areas of the sky at once, improving observation efficiency. However, a wide-field optical telescope is highly sensitive to external stray light (such as moonlight and thin clouds), which can significantly reduce the quality of observation data. In severe cases, it can cause the telescope to malfunction and inaccurately position the object. In response to this problem, this paper proposes a model for suppressing stray light in astronomical images based on deep learning: the Pyramid Deformable Large Kernel Attention (PD-LKA) Model. This model expands the receptive field through a pyramid structure, captures multi-scale features, and improves the model’s robustness to various scales of stray light interference. Meanwhile, through the Deformable Large Kernel Attention (D-LKA), the model can more accurately locate and enhance the feature extraction ability in areas affected by stray light interference, thereby better suppressing stray light.Using simulated astronomical image pairs to train the model, the tests achieved a PSNR of up to 32.540 and an SSIM of up to 0.938. Finally, the model is applied to a image sequence with real stray light interference. The restored images undergo astronomical positioning and orbital association processing. The results show that the positioning accuracy of the object is better than 5 arcseconds. This indicates that the model proposed in this paper not only recovers the object and background stars but also effectively preserves their gray values, shapes, and positional information.