FFBL-Coop：关联解耦的协作式三维多目标跟踪
FFBL-Coop: Association-Decoupled Cooperative 3D Multi-Object Tracking
浏览论文内容
中文总结 AI 辅助
提出FFBL-Coop框架，通过解耦实例准入与身份管理，采用置信度排序槽位准入、统一表示聚合和协作优先身份锚定，实现协作三维多目标跟踪，在V2X-Seq和Griffin-25M上取得领先性能。
中文摘要 AI 辅助
协作式三维跟踪必须在跨智能体和时间上整合互补观测，同时保持一致的身份。当证据整合与身份继承共享一个匹配决策时，由跨视角外观差异和空间错位引起的误差会同时损害特征融合和轨迹连续性。我们提出FFBL-Coop，一种“先融合后绑定”的框架，将实例准入与身份管理分离。置信度排序的槽位准入（CSA）利用置信度和空间邻近性将协作查询分配给可用的自我槽位。统一表示聚合（URA）使用协作语义特征和对齐的锚点来引导自我特征检索，在共享的Transformer解码器中精炼增强的查询库。精炼后，协作优先身份锚定（CPIA）结合学习到的关联与持久映射，建立跨帧的已接受身份分配。一个共享码本减少了传输负载，同时保持AP和AMOTA接近未压缩版本。FFBL-Coop在V2X-Seq上达到AMOTA/AP为0.611/0.548，在Griffin-25M上达到0.688/0.653。代码将发布。
英文摘要
Cooperative 3D tracking must integrate complementary observations across agents and time while maintaining consistent identities. When evidence integration and identity inheritance share a matching decision, errors arising from cross-view appearance differences and spatial misalignment can compromise both feature fusion and track continuity. We propose FFBL-Coop, a fuse first, bind later framework that separates instance admission from identity management. Confidence-ranked Slot Admission (CSA) allocates cooperative queries to available ego slots using confidence and spatial proximity. Unified Representation Aggregation (URA) uses cooperative semantic features and aligned anchors to guide ego-feature retrieval, refining the augmented query bank within a shared transformer decoder. After refinement, Cooperative-Priority Identity Anchoring (CPIA) combines learned association with persistent mappings to establish accepted identity assignments across frames. A shared codebook reduces transmitted payload while retaining AP and AMOTA close to the uncompressed variant. FFBL-Coop achieves AMOTA/AP of 0.611/0.548 on V2X-Seq and 0.688/0.653 on Griffin-25M. Code will be released.
发表机构
- Zhejiang University（浙江大学）
机构由 AI 辅助整理，请以论文原文为准。
