Mingrui Fan

Small celestial body (SCB) exploration is a research hotspot in deep space exploration technology. However, the scarcity of small celestial body surface images severely hinders the development of probe intelligence systems, and it is challenging to redeploy probes to obtain massive images due to the high cost. In recent years, with the growth of deep learning, generative adversarial networks have shown excellent potential in generating real images. This paper presents a high-quality small celestial body surface image synthesis method SCB-GAN, which can generate a massive amount and large diversity of small celestial body surface images that match human perception from a limited dataset. Specifically, we propose MineAug, which can automatically select appropriate data augmentations from the given SCB surface imageset based on an efficient mining mechanism, improving the robustness of the GAN training process. We also add the vision-aided loss to our network to further improve image quality. Through extensive experiments, our method outperforms recent methods under a variety of metrics in terms of visual quality comparison, no-referenced image quality assessment, and human subjective evaluation, which has significant implications for the development of intelligent systems. The source code and associated data are available at https://github.com/LUWENL/SCB-GAN

Small Celestial Body (SCB) image matching is essential for deep space exploration missions. In this paper, a large-scale invariant method is proposed to improve the matching accuracy of SCB images under large-scale variations. Specifically, we designed a novel network named DeepSpace-ScaleNet, which employs an attention mechanism for estimating the scale ratio to overcome the significant variation between two images. Firstly, the Global Attention-DenseASPP (GA-DenseASPP) module is proposed to refine feature extraction in deep space backgrounds. Secondly, the Correlation-Aware Distribution Predictor (CADP) module is built to capture the connections between correlation maps and improve the accuracy of the scale distribution estimation. To the best of our knowledge, this is the first work to explore large-scale SCB image matching using Transformer-based neural networks rather than traditional handcrafted feature descriptors. We also analysed the effects of different scale and illumination changes on SCB image matching in the experiment. To train the network and verify its effectiveness, we created a simulation dataset containing light variations and scale variations named Virtual SCB Dataset. Experimental results show that the DeepSpace-ScaleNet achieves a current state-of-the-art SCB image scale estimation performance. It also shows the best accuracy and robustness in image matching and relative pose estimation.

This paper presents an approach for the detection of moving point targets in very low SNR based on purely time-domain analysis of pixels. The problem of detecting point targets in image sequences is formulated as a one-dimensional weak transient signal detection problem. The mathematical model of the transient signal is proposed. The key impact factors, such as the frame-rate, target velocity and SNR of the weak transient signal are studied. The detection ability is evaluated from the view of time-domain energy accumulation and correlation. The experimental results with both simulated and realworld data demonstrate that our approach can efficiently detect extremely low-SNR targets and the detection ability is decided by the key impact factors.