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

TL;DR

This work proposes SiamGM, a novel geometry-aware and motion-guided Siamese network, which outperforms most state-of-the-art trackers in both precision and success metrics and introduces virtually no computational overhead, enabling real-time tracking at 130 frames per second (FPS).

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.

Figures (11)

• Figure 1: Visual illustrations of the inherent challenges in satellite videos. (a) Tiny objects lack distinct texture features. (b) Targets often undergo arbitrary rotations. (c) Large aspect ratio changes introduce severe background noise within traditional horizontal bounding boxes. (d) Frequent partial or full occlusions easily lead to tracking drift.
• Figure 2: Overall architecture of the proposed SiamGM framework.
• Figure 3: Visualization of (a) 1D multi-gamma centerness comparison and (b) 2D centerness distribution in which the aspect ratio is set to 6.
• Figure 4: Visualization of nPSR curves for (a) two car targets and (b) two ship targets in SatSOT Dataset. The blue curve represents the nPSR values in normal tracking scenarios, while the red curve corresponds to occlusion scenarios.
• Figure 5: Illustration of the OMMR process.