低频检测下也能稳定追踪多目标，性能提升11.6%。
StableTrack: Stabilizing Multi-Object Tracking on Low-Frequency Detections
- 两阶段匹配+基于框距的新距离度量，提升跨帧关联精度。
- 在1Hz检测频率下，MOT17-val上HOTA提升11.6%。
- 适合计算资源受限场景，兼顾低频与全频跟踪性能。
多目标追踪（MOT）是计算机视觉中的核心挑战之一，需准确检测目标并在帧间正确关联。现有方法通常依赖每帧处理，难以在计算资源受限时运行。为此，我们提出StableTrack，一种在低频检测下保持追踪质量的新方法。该方法引入新的两阶段匹配策略，优化低频检测间的跨帧关联。提出基于边框的距离度量（Bbox-Based Distance），替代传统马氏距离，结合重识别（Re-ID）模型实现更有效的匹配。同时将视觉追踪集成至卡尔曼滤波器及整体追踪流程中。在低频检测条件下，StableTrack在MOT17-val数据集上以1Hz检测频率实现11.6%的HOTA提升；在标准数据集MOT17、MOT20和DanceTrack上，全频检测下性能媲美当前最优方法。
原文摘要 · Abstract (English)
Multi-object tracking (MOT) is one of the most challenging tasks in computer vision, where it is important to correctly detect objects and associate these detections across frames. Current approaches mainly focus on tracking objects in each frame of a video stream, making it almost impossible to run the model under conditions of limited computing resources. To address this issue, we propose StableTrack, a novel approach that stabilizes the quality of tracking on low-frequency detections. Our method introduces a new two-stage matching strategy to improve the cross-frame association between low-frequency detections. We propose a novel Bbox-Based Distance instead of the conventional Mahalanobis distance, which allows us to effectively match objects using the Re-ID model. Furthermore, we integrate visual tracking into the Kalman Filter and the overall tracking pipeline. Our method outperforms current state-of-the-art trackers in the case of low-frequency detections, achieving $\textit{11.6%}$ HOTA improvement at $\textit{1}$ Hz on MOT17-val, while keeping up with the best approaches on the standard MOT17, MOT20, and DanceTrack benchmarks with full-frequency detections.
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。