In view of the fact that the technology of polarization detection performs better at identifying targets through clouds and fog, the recognition ability of the space target detection system under haze conditions will be improved by applying the technology. However, due to the low ambient brightness and limited target radiation information during space target detection, the polarization information of space target is seriously lost, and the advantages of polarization detection technology in identifying targets through clouds and fog cannot be effectively exerted under the condition of haze detection. In order to solve the above problem, a dehazing enhancement strategy specifically applied to polarization images of space targets is proposed. Firstly, a hybrid multi-channel interpolation method based on regional correlation analysis is proposed to improve the calculation accuracy of polarization information during preprocessing. Secondly, an image processing method based on full polarization information inversion is proposed to obtain the degree of polarization of the image after inversion and the intensity of the image after dehazing. Finally, the image fusion method based on discrete cosine transform is used to obtain the dehazing polarization fusion enhancement image. The effectiveness of the proposed image processing strategy is verified by carrying out simulated and real space target detection experiments. Compared with other methods, by using the proposed image processing strategy, the quality of the polarization images of space targets obtained under the haze condition is significantly improved. Our research results have important practical implications for promoting the wide application of polarization detection technology in the field of space target detection.

Ground-based telescopes often encounter challenges such as stray light and vignetting when capturing space objects, leading to non-uniform image backgrounds. This not only weakens the signal-to-noise ratio for target tracking but also reduces the accuracy of recognition systems. To address this challenge, We have proposed a novel network architecture called CycleMRSNet, which is based on the CycleGAN framework and incorporates a multi-scale attention mechanism to enhance image processing capabilities. Specifically, we have introduced a multi-scale feature extraction module (MSFEM) at the front end of the generator and embedded an efficient multi-scale attention residual block (EMA-residual block) within the Resnet backbone network. This design improves the efficiency of feature extraction and increases the focus on multi-scale information in high-dimensional feature maps, enabling the network to more comprehensively understand and concentrate on key areas within images, thereby capably correcting non-uniform backgrounds. To evaluate the performance of CycleMRSNet, we trained the model using a small-scale dataset and conducted corrections on simulated and real images within the test set. Experimental results showed that our model achieved scores of PSNR 32.7923, SSIM 0.9814, and FID 1.9212 in the test set, outperforming other methods. These metrics suggest that our approach significantly improves the correction of non-uniform backgrounds and enhances the robustness of the system.

Under ground-based observation geometry, infrared radiant-intensity sequences of space objects are jointly influenced by object micromotion, thermal radiation, time-varying viewing conditions, and atmospheric propagation. Existing simulation studies often prescribe the line of sight or simplify the coupling between viewing geometry and atmospheric attenuation, which limits long-duration ground-based sequence analysis. This study develops a physics-informed framework for generating atmosphere-attenuated infrared radiant-intensity sequences of space objects undergoing precession or tumbling. The framework reconstructs observation geometry from azimuth–elevation–range trajectories, updates facet normals through a unified micromotion attitude model, computes visible projected area and transient facet temperature, and incorporates MODTRAN-derived elevation-dependent atmospheric transmittance. Using this framework, we construct IRPeriodic, an eight-class simulated dataset for long-duration univariate time-series classification. We further propose LPD-Net, which integrates large-kernel residual feature extraction, prototype-guided dynamic temporal alignment, and differential periodic representation to capture long-range waveform morphology, sample-dependent temporal correspondence, and segment-level local variation. On IRPeriodic, LPD-Net achieves an accuracy of 0.8618 ± 0.0057, a macro-F1 of 0.8615 ± 0.0061, and a Matthews correlation coefficient of 0.8426 ± 0.0065, outperforming the evaluated neural-network and ROCKET-type baselines. Ablation and synthetic-noise sensitivity analyses indicate that the performance gain is mainly associated with long-context feature extraction, with additional improvements from dynamic alignment and differential periodic statistics. Auxiliary experiments on selected public UCR datasets suggest that the representation is also competitive for univariate time-series classification. These results demonstrate the effectiveness of LPD-Net on the proposed physics-informed benchmark for long-duration ground-based infrared radiant-intensity sequence classification.