SatSAM2: Motion-Constrained Video Object Tracking in Satellite Imagery using Promptable SAM2 and Kalman Priors

TL;DR

SatSAM2 is a novel zero-shot satellite video tracker leveraging foundation models, Kalman filtering, and motion constraints to improve robustness and generalization in challenging satellite imagery scenarios.

Contribution

The paper introduces SatSAM2, combining SAM2 with motion priors and a new synthetic benchmark for satellite video tracking, advancing zero-shot capabilities.

Findings

SatSAM2 outperforms traditional and foundation model trackers on benchmarks.

Achieves 5.84% AUC improvement on the OOTB dataset.

Introduces MVOT, a large synthetic satellite video benchmark.

Abstract

Existing satellite video tracking methods often struggle with generalization, requiring scenario-specific training to achieve satisfactory performance, and are prone to track loss in the presence of occlusion. To address these challenges, we propose SatSAM2, a zero-shot satellite video tracker built on SAM2, designed to adapt foundation models to the remote sensing domain. SatSAM2 introduces two core modules: a Kalman Filter-based Constrained Motion Module (KFCMM) to exploit temporal motion cues and suppress drift, and a Motion-Constrained State Machine (MCSM) to regulate tracking states based on motion dynamics and reliability. To support large-scale evaluation, we propose MatrixCity Video Object Tracking (MVOT), a synthetic benchmark containing 1,500+ sequences and 157K annotated frames with diverse viewpoints, illumination, and occlusion conditions. Extensive experiments on two satellite tracking benchmarks and MVOT show that SatSAM2 outperforms both traditional and foundation model-based trackers, including SAM2 and its variants. Notably, on the OOTB dataset, SatSAM2 achieves a 5.84% AUC improvement over state-of-the-art methods. Our code and dataset will be publicly released to encourage further research.