SiamGM: Siamese Geometry-Aware and Motion-Guided Network for Real-Time Satellite Video Object Tracking

2026-03-08

AI Summary

This work addresses the challenges of single object tracking in satellite videos, where small target scales, ambiguous backgrounds, drastic aspect ratio variations, and frequent occlusions often lead to tracking failure. To this end, the authors propose a geometry-aware and motion-guided Siamese network. Fine-grained spatial correspondence is achieved through an inter-frame graph attention mechanism combined with aspect ratio-constrained label assignment, effectively suppressing background interference. Furthermore, a motion vector-guided online optimization strategy based on normalized peak-to-sidelobe ratio (nPSR) confidence leverages historical trajectories to enhance tracking robustness. The proposed method achieves state-of-the-art precision and success rates on the SatSOT and SV248S benchmarks, operating at 130 FPS with negligible additional computational overhead.

Technology Category

• Computer Vision: Motion & Tracking
• Constraint Satisfaction and Optimization: Satisfiability
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Security and Privacy: Tracking, profiling, and countermeasures against them
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Single object tracking in satellite videos is inherently challenged by small target, blurred background, large aspect ratio changes, and frequent visual occlusions. These constraints often cause appearance-based trackers to accumulate errors and lose targets irreversibly. To systematically mitigate both spatial ambiguities and temporal information loss, we propose SiamGM, a novel geometry-aware and motion-guided Siamese network. From a spatial perspective, we introduce an Inter-Frame Graph Attention (IFGA) module, closely integrated with an Aspect Ratio-Constrained Label Assignment (LA) method, establishing fine-grained topological correspondences and explicitly preventing surrounding background noise. From a temporal perspective, we introduce the Motion Vector-Guided Online Tracking Optimization method. By adopting the Normalized Peak-to-Sidelobe Ratio (nPSR) as a dynamic confidence indicator, we propose an Online Motion Model Refinement (OMMR) strategy to utilize historical trajectory information. Evaluations on two challenging SatSOT and SV248S benchmarks confirm that SiamGM outperforms most state-of-the-art trackers in both precision and success metrics. Notably, the proposed components of SiamGM introduce virtually no computational overhead, enabling real-time tracking at 130 frames per second (FPS). Codes and tracking results are available at https://github.com/wenzx18/SiamGM.

Problem

• satellite video object tracking
• small target
• aspect ratio variation
• visual occlusion
• background blur

Innovation

• Siamese network
• geometry-aware tracking
• motion-guided optimization
• graph attention
• real-time satellite tracking