无需微调，实现零样本多目标跟踪与分割的稳定一致
Seg2Track++: Probabilistic Track Validation and Data Association for Multi-Object Tracking and Segmentation
- 结合SAM2与新跟踪管理模块，通过中心距和置信度调节关联轨迹
- 在KITTI MOTS上显著减少误报传播，提升身份一致性
- 适合需要高鲁棒性的自动驾驶场景使用
自主系统需在动态环境中实现可靠的多目标跟踪与分割（MOTS），以维持物体身份一致性并精确分割掩码。尽管像SAM2这样的基础模型在零样本分割上表现优异，但其直接用于MOTS时受限于不可靠的轨迹关联和误报传播。本文提出Seg2Track++，将实例分割与SAM2结合，并引入新颖的轨迹管理模块，实现无需微调的零样本MOTS，增强时间一致性。轨迹关联采用掩码中心距（MCD）与置信度感知代价调制（CCM），而概率轨迹验证（PTV）利用伯努利滤波器判断轨迹存在性，抑制伪轨迹。在KITTI MOTS数据集上的实验表明，该方法显著提升了身份保持能力，减少了误报传播，且具备强鲁棒性。
原文摘要 · Abstract (English)
Autonomous systems require robust Multi-Object Tracking and Segmentation (MOTS) to operate reliably in dynamic environments, ensuring consistent object identities and precise mask-level delineation. Foundation models such as SAM2 have shown strong zero-shot generalization for segmentation, but their direct application to MOTS is limited by unreliable track association and false-positive propagation. This work introduces Seg2Track++, a framework that integrates instance segmentation with SAM2 and a novel track management module to perform zero-shot MOTS with enhanced temporal consistency. Tracks are associated using Mask Centroid Distance (MCD) and Confidence-Aware Cost Modulation (CCM), while Probabilistic Track Validation (PTV) employs a Bernoulli filter to validate track existence and suppress ghost tracks. Experimental results on KITTI MOTS demonstrate improved identity preservation, reduced false-positive propagation, and robust track management without fine-tuning.
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。