Search Results (2)

Atmospheric turbulence severely degrades high-resolution satellite videos through spatiotemporally coupled distortions, including temporal jitter, spatial-variant blur, deformation, and scintillation, thereby constraining downstream analytical capabilities. Restoring turbulence-corrupted videos poses a challenging ill-posed inverse problem due to the inherent randomness of turbulent fluctuations. While existing turbulence mitigation methods for long-range imaging demonstrate partial success, they exhibit limited generalizability and interpretability in large-scale satellite scenarios. Inspired by refractive-index structure constant ($C_n^2$) estimation from degraded sequences, we propose a physics-informed turbulence signature (TS) prior that explicitly captures spatiotemporal distortion patterns to enhance model transparency. Integrating this prior into a lucky imaging framework, we develop a Physics-Based Turbulence Mitigation Network guided by Turbulence Signature (TMTS) to disentangle atmospheric disturbances from satellite videos. The framework employs deformable attention modules guided by turbulence signatures to correct geometric distortions, iterative gated mechanisms for temporal alignment stability, and adaptive multi-frame aggregation to address spatially varying blur. Comprehensive experiments on synthetic and real-world turbulence-degraded satellite videos demonstrate TMTS’s superiority, achieving 0.27 dB PSNR and 0.0015 SSIM improvements over the DATUM baseline while maintaining practical computational efficiency. By bridging turbulence physics with deep learning, our approach provides both performance enhancements and interpretable restoration mechanisms, offering a viable solution for operational satellite video processing under atmospheric disturbances. Full article

Occludedperson re-identification (ReID) tasks pose a significant challenge in matching occluded pedestrians to their holistic counterparts across diverse camera views and scenarios. Robust representational learning is crucial in this context, given the unique challenges introduced by occlusions. Firstly, occlusions often result in missing or distorted appearance information, making accurate feature extraction difficult. Secondly, most existing methods focus on learning representations from isolated images, overlooking the potential relational information within image batches. To address these challenges, we propose a pose-guided partial-attention network with batch information (PPBI), designed to enhance both spatial and relational learning for occluded ReID tasks. PPBI includes two core components: (1) A node optimization network (NON) that refines the relationships between key-point nodes of a pedestrian to better address occlusion-induced inconsistencies. (2) A key-point batch attention (KBA) module that explicitly models inter-image interactions across batches to mitigate occlusion effects. Additionally, we introduce a correction of hard mining (CHM) module to handle occlusion-related misclassification and a batch enhancement (BE) model to strengthen key-point attention across image batches. Extensive experiments on occluded and holistic ReID tasks validate the effectiveness of PPBI. Our framework achieves a 2.7% mAP improvement over HoNeT on the Occluded-Duke dataset, demonstrating its robust performance. Full article