Most background suppression algorithms are weakly robust due to the complexity and fluctuation of the star image’s background. In this paper, a background suppression algorithm for stray lights in star images is proposed, which is named BSC-Net (Background Suppression Convolutional Network) and consist of two parts: “Background Suppression Part” and “Foreground Retention Part”. The former part achieves background suppression by extracting features from various receptive fields, while the latter part achieves foreground retention by merging multi-scale features. Through this two-part design, BSC-Net can compensate for blurring and distortion of the foreground caused by background suppression, which is not achievable in other methods. At the same time, a blended loss function of smooth_L1&Structure Similarity Index Measure (SSIM) is introduced to hasten the network convergence and avoid image distortion. Based on the BSC-Net and the loss function, a dataset consisting of real images will be used for training and testing. Finally, experiments show that BSC-Net achieves the best results and the largest Signal-to-Noise Ratio (SNR) improvement in different backgrounds, which is fast, practical and efficient, and can tackle the shortcomings of existing methods.

Space debris detection is vital to space missions and space situation awareness. Convolutional neural networks are introduced to detect space debris due to their excellent performance. However, noisy labels, caused by false alarms, exist in space debris detection, and cause ambiguous targets for the training of networks, leading to networks overfitting the noisy labels and losing the ability to detect space debris. To remedy this challenge, we introduce label-noise learning to space debris detection and propose a novel label-noise learning paradigm, termed Co-correcting, to overcome the effects of noisy labels. Co-correcting comprises two identical networks, and the predictions of these networks serve as auxiliary supervised information to mutually correct the noisy labels of their peer networks. In this manner, the effect of noisy labels can be mitigated by the mutual rectification of the two networks. Empirical experiments show that Co-correcting outperforms other state-of-the-art methods of label-noise learning, such as Co-teaching and JoCoR, in space debris detection. Even with a high label noise rate, the network trained via Co-correcting can detect space debris with high detection probability.