The detection of dim and small space-targets is crucial in space situational awareness missions; however, low signal-to-noise ratio (SNR) targets and complex backgrounds pose significant challenges to such detection. This paper proposes a space-target detection framework comprising a space-target detection network and a k-means clustering target centroid positioning method. The space-target detection network performs a three-dimensional convolution of an input star image sequence to learn the motion features of the target, reduces the interference of noise using a soft thresholding module, and outputs the target detection result after positioning via the offsetting branch. The k-means centroid positioning method enables further high-precision subpixel-level centroid positioning of the detection network output. Experiments were conducted using simulated data containing various dim and small space-targets, multiple noises, and complex backgrounds; semi-real data with simulated space-targets added to the real star image; and fully real data. Experiments on the simulated data demonstrate the superior detection performance of the proposed method for multiple SNR conditions (particularly with very low false alarm rates), robustness regarding targets of varying numbers and speeds, and complex backgrounds (such as those containing stray light and slow motion). Experiments performed with semi-real and real data both demonstrate the excellent detection performance of the proposed method and its generalization capability.

Moving target detection in optical remote sensing is important for satellite surveillance and space target monitoring. Here, a new moving point target detection framework under a low signal-to-noise ratio (SNR) that uses an end-to-end network (1D-ResNet) to learn the distribution features of transient disturbances in the temporal profile (TP) formed by a target passing through a pixel is proposed. First, we converted the detection of the point target in the image into the detection of transient disturbance in the TP and established mathematical models of different TP types. Then, according to the established mathematical models of TP, we generated the simulation TP dataset to train the 1D-ResNet. In 1D-ResNet, the structure of CBR-1D (Conv1D, BatchNormalization, ReLU) was designed to extract the features of transient disturbance. As the transient disturbance is very weak, we used several skip connections to prevent the loss of features in the deep layers. After the backbone, two LBR (Linear, BatchNormalization, ReLU) modules were used for further feature extraction to classify TP and identify the locations of transient disturbances. A multitask weighted loss function to ensure training convergence was proposed. Sufficient experiments showed that this method effectively detects moving point targets with a low SNR and has the highest detection rate and the lowest false alarm rate compared to other benchmark methods. Our method also has the best detection efficiency.

Deep space exploration missions may encounter opportunities to visit previously unplanned small bodies, which require timely and reliable observation planning under complex engineering constraints. However, traditional manual planning is labor-intensive and difficult to adapt to multi-objective flyby scenarios, while fully autonomous systems still face reliability limitations. To address these challenges, this study proposes SB-ObsGen, a framework for flyby small-body observation plan generation that integrates large language models (LLMs) with physics-informed tools. The framework follows a Generate-and-Optimize paradigm: an Observation Plan Generation Module decomposes tasks and invokes domain-specific tools to derive feasible observation information, and a Plan Optimization Module iteratively refines the initial plan through discriminator-guided feedback. Experiments on 80 mission scenarios show that SB-ObsGen achieves strong performance across different LLM backbones, with the best configurations reaching over 85% plan consistency with reference recommendation plans. Comparative experiments against classical planning methods further show that the proposed framework is competitive on structured planning tasks while offering additional advantages in tool use, flexible constraint handling, and end-to-end planning from heterogeneous inputs. Ablation studies confirm the critical role of the Plan Optimization Module in improving final plan quality.