发表机构
China Agricultural University; Beijing Normal University; National University of Singapore（中国农业大学; 北京师范大学; 新加坡国立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对密集同质鱼群跟踪难题，提出双分支弹性机制TIDE，采用自适应几何对应IoU关联机制，轻量L分支实现38.7倍计算量缩减，可扩展S分支提升精度，适配边缘部署。
AI 中文摘要
对鱼群等密集同质目标进行跟踪仍是多目标跟踪领域的一大挑战，原因在于个体间极端的相似性、严重的物理聚类以及快速的非刚性形变。尽管像SU-T这类采用重型骨干网络的分离检测与嵌入跟踪器通过复杂的重识别网络推动了精度边界，但它们的计算开销使其无法在边缘设备部署。此外，当外观特征因严重遮挡退化时，这些模块常失效。为解决此问题，我们提出了利用双分支弹性机制跟踪身份的TIDE。TIDE绕过了昂贵的外观线索，采用自适应几何对应IoU这种关联机制，该机制利用空间和结构一致性来稳健处理复杂的形态变化。关键的是，TIDE引入了系统级部署弹性，将算法流程与严格的硬件约束解耦。在MFT-Edge基准上的评估表明，我们的轻量L分支仅用20.47G FLOPs就达到了28.43的HOTA，与SU-T等上限相比，计算量减少了38.7倍，直接推动了实时边缘部署。同时，我们的可扩展S分支取得了29.98的HOTA，成功弥合了高精度云分析与高效边缘跟踪之间的差距。数据集和代码已在该httpsURL发布。
英文摘要
Tracking dense, homogeneous targets like schooling fish remains a major challenge for multiple object tracking due to extreme inter-individual homogeneity, severe physical clustering, and rapid non-rigid deformations. While heavy-backbone separated detection and embedding trackers like SU-T push accuracy boundaries using complex Re-Identification networks, their computational overhead prohibits edge deployment. Furthermore, these modules often fail when appearance features degrade under severe occlusions. To overcome this, we propose Tracking Identities with Dual-branch Elasticity (TIDE). Bypassing expensive appearance cues, TIDE utilizes the Adaptive Geometric Correspondence IoU, an association mechanism leveraging spatial and structural consistency to robustly handle complex morphological variations. Crucially, TIDE introduces system-level deployment elasticity, decoupling the algorithmic pipeline from strict hardware constraints. Evaluations on the MFT-Edge benchmark demonstrate that our Lightweight L-branch achieves a competitive HOTA of 28.43 using merely 20.47G FLOPs. This represents a 38.7-fold computational reduction compared to upper bounds like SU-T, directly facilitating real-time edge deployment. Concurrently, our Scalable S-branch establishes a 29.98 HOTA, successfully bridging the gap between high-precision cloud analysis and efficient edge tracking. The dataset and codes are released at https://vranlee.github.io/TIDE/.
