研究人员开发了 Seg2Track++，一个用于多目标跟踪和分割 (MOTS) 的新框架，可增强时间一致性和身份保持。该系统集成了来自 SAM2 的实例分割和一个新颖的轨迹管理模块。它使用掩码质心距离和置信度感知成本调制进行轨迹关联，并使用伯努利滤波器进行概率轨迹验证以抑制假阳性。在 KITTI MOTS 数据集上的实验表明，无需微调即可提高性能。 AI
影响 通过提高对象身份保持和分割准确性来增强自主系统的可靠性。
排序理由 该集群包含一篇详细介绍多目标跟踪和分割新框架的研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2512.22105v2 Announce Type: replace Abstract: Multi-object tracking aims to maintain object identities over time by associating detections across video frames. Two dominant paradigms exist in literature: tracking-by-detection methods, which are computationally efficient but…
arXiv:2606.03875v1 Announce Type: new Abstract: 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 ha…
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 seg…