零样本卫星视频追踪，用卡尔曼滤波和状态机提升精度与鲁棒性。
SatSAM2: Motion-Constrained Video Object Tracking in Satellite Imagery using Promptable SAM2 and Kalman Priors
- 基于SAM2架构，引入卡尔曼滤波运动约束模块。
- 在OOTB数据集上比顶尖方法提升5.84% AUC。
- 适合遥感领域视频目标追踪研究者使用。
现有卫星视频追踪方法常因泛化能力差，需针对特定场景训练，且在遮挡时易丢失目标。为此，我们提出SatSAM2，一种基于SAM2的零样本卫星视频追踪器，旨在将基础模型适配至遥感领域。该方法引入两个核心模块：基于卡尔曼滤波的运动约束模块（KFCMM），用于利用时序运动信息并抑制漂移；以及运动约束状态机（MCSM），依据运动动态与可靠性调控追踪状态。为支持大规模评估，我们构建了MatrixCity视频目标追踪（MVOT）基准，包含1,500+序列、157,000标注帧，涵盖多样视角、光照及遮挡条件。在两个卫星追踪基准和MVOT上的实验表明，SatSAM2优于传统及基于基础模型的追踪器，包括SAM2及其变体。特别地，在OOTB数据集上，其AUC相比最先进方法提升5.84%。代码与数据集将公开发布，以促进后续研究。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。