Ground-based telescopes are often affected by vignetting, stray light and detector nonuniformity when acquiring space images. This paper presents a space image nonuniform correction method using the conditional generative adversarial network (CGAN). Firstly, we create a dataset for training by introducing the physical vignetting model and by designing the simulation polynomial to realize the nonuniform background. Secondly, we develop a robust conditional generative adversarial network (CGAN) for learning the nonuniform background, in which we improve the network structure of the generator. The experimental results include a simulated dataset and authentic space images. The proposed method can effectively remove the nonuniform background of space images, achieve the Mean Square Error (MSE) of 4.56 in the simulation dataset, and improve the target’s signal-to-noise ratio (SNR) by 43.87% in the real image correction.

To achieve seamless integration within Internet of Things (IoT)-enabled distributed observation networks, electro-optical telescopes must adeptly handle heterogeneous external guidance sources. In the routine operation of electro-optical telescopes, telescope control based on external guidance is one of the common functions. Telescope control systems need to have the ability to receive multiple external guidance protocols and guide the telescope pointing. According to operational requirements, the telescope control system will select an external guidance protocol to drive the telescope to bring the target into the field of view. This paper proposes an external guidance system with heterogeneous protocols compatibility which supports a self-verification capability. Specifically, it presents a modularized framework comprising three decoupled layers, namely the communicator, codec, and optimizer, facilitated by standardized interfaces to ensure enhanced scalability and protocol interoperability. We propose an instance of the optimizer with trajectory prediction function to integrate into the telescope guidance system, which is beneficial for bringing a target into the field of view and reducing the tracking jitter. Furthermore, based on the module reuse principle, two alternative channels are created, including a self-verification channel and an actual external guidance channel, with the selection depending on the usage scenario. The experimental results indicate that, compared with traditional external guidance systems, the design scheme proposed in this paper can reduce the lines of code (LOC) related to external guidance system by approximately 63.1%. Before deployment in the field, system developers can finish the self-verification work of an external guidance protocol and related functions to reduce the field joint debugging time. For common types of external guidance data errors, the optimizer has an outlier recognition rate of 98.2%, a false rejection rate for normal values of only 2.3%, while reducing average errors in guidance pointing, velocity, and acceleration by 31.3%, 40.4%, and 47.9%, respectively.

Video jitter in electro-optical telescope observations frequently arises from the complex interplay of low-precision closed-loop tracking, low-frequency external guidance, and environmental disturbances such as wind, all of which compromise scientific measurements. To address this challenge, we propose a real-time hybrid video stabilization framework that establishes a rigorous coupling between hardware-level measurements—Coordinated Universal Time (UTC) timing synchronization and encoder feedback—with software-based image processing. This integration enables adaptive algorithm selection tailored to varying observation conditions. When high-precision orbital data are available, the Orbit-Predicted Motion Compensation (OPMC) module combines timing-aligned encoder readings with orbital data to constrain jitter within 1.0–3.0 pixels. During continuous target tracking, the Target-Locked Stabilization (TLS) module restricts jitter to within 1.5 pixels. In general cases, the Historical Trajectory Regression (HTR) module leverages historical encoder trajectories and timing alignment to achieve an average jitter reduction exceeding 35%. The proposed architecture sustains a 2 ms per-frame processing budget, meeting the real-time requirements of 100 Hz telescope imaging systems. Systematic evaluations demonstrate that our hybrid approach, which synergizes timing systems, encoders, and image processing, surpasses established video stabilization algorithms in both jitter suppression and sequence stability, while preserving real-time online processing capability.

In visible-light optical observations for Space Surveillance and Tracking (SST) from ground-based dynamic platforms, attitude disturbances and field-of-view discontinuities frequently undermine interframe geometric consistency, leading to energy diffusion and unstable gain in multi-frame stacking for faint space objects. We propose orbit-prior- guided target-centered stacking (OPG-TCS), a tracking-oriented post-processing method designed to stabilize target energy accumulation and improve enhancement reliability under dynamic observation conditions. OPG-TCS performs frame-wise astrometric calibration using star fields (WCS) and leverages projected orbit priors to predict target pixel locations, enabling local cropping and target-centered alignment/stacking without relying on full-frame geometric consistency. We evaluate OPG-TCS on multiple real-world dynamic-platform sequences and compare it with direct stacking and representative robust baselines. Signal-to-noise ratio (SNR) is used as the primary metric, while auxiliary indicators of peak prominence, energy concentration, and shape consistency are employed to assess robustness across varying stacking depths. The results show that OPG-TCS provides stable enhancement over different frame counts; in representative 50-frame fusions, its relative SNR surpasses direct stacking by 33.7–97.8%. These findings suggest that OPG-TCS offers a practical and robust enhancement strategy for SST-oriented observation of faint space objects, supporting more reliable detection and subsequent tracking analysis.