# 基于运动、几何与语义自适应的复杂非线性视觉目标跟踪框架

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-05-21 08:00
- AIHOT 分数：64
- AIHOT 链接：https://aihot.virxact.com/items/cmpggte670fbfsljwzr1p465b
- 原文链接：https://arxiv.org/abs/2605.22538

## AI 摘要

传统视觉目标跟踪方法依赖特定任务的监督训练，泛化能力有限。近期以SAM 2为代表的基础模型虽具强大视频理解能力，但直接用于跟踪时缺乏对目标运动、几何一致性和语义偏移的显式建模。为此，本研究提出SAMOSA框架，通过引入轻量级非线性运动预测器建模目标动态，利用语义线索检测偏移并恢复跟踪，并结合几何约束提升稳定性，从而将SAM 2的通用先验适配到复杂跟踪任务。实验表明，SAMOSA在通用基准上优于现有SAM 2方法，并在反无人机等非线性运动场景中取得显著性能提升。

## 正文

Traditional visual object tracking (VOT) methods typically rely on task-specific supervised training, limiting their generalization to unseen objects and challenging scenarios with distractors, occlusion, and nonlinear motion. Recent vision foundation models, exemplified by SAM 2, learn strong video understanding priors from large-scale pretraining and offer a promising foundation for building more robust and generalizable trackers. However, directly applying SAM 2 to VOT remains suboptimal, as it does not explicitly model target motion dynamics or enforce geometric and semantic consistency across frames, both of which are essential for reliable tracking. To address this issue, we propose SAMOSA, a new tracking framework that adapts SAM 2 to complex VOT scenarios by explicitly leveraging motion, geometry, and semantic cues. Specifically, we introduce a lightweight nonlinear motion predictor to model target dynamics and guide mask selection as well as memory filtering. We further exploit semantic cues to detect target shifts and recover from tracking failures, while geometric cues are incorporated as structural constraints to improve tracking stability. In this way, SAMOSA bridges the gap between the implicit video understanding prior of SAM 2 and explicit tracking-oriented modeling. Extensive experiments show that SAMOSA consistently outperforms state-of-the-art SAM 2--based approaches on general benchmarks, demonstrates stronger generalization than supervised VOT methods, and achieves substantial gains on anti-UAV datasets, which typify complex nonlinear motion scenarios. Our code is available at https://github.com/DurYi/SAMOSA.