融合随机与确定性方法，提升复杂场景下的多目标跟踪鲁棒性。
GenTrack3: Hybrid Stochastic-Deterministic Online Multi-Object Tracking with Cluster-Aware Association
- 采用粒子集建模不确定性，结合确定性轨迹管理提升稳定性。
- 支持群体追踪，匹配效率随目标数量增长仍保持高效。
- 适合动态场景中需高精度与抗干扰能力的跟踪任务。
多目标跟踪（MOT）旨在物体进出场景时维持目标身份一致性。确定性方法如基于检测的关联跟踪，结果可复现且计算高效，但依赖运动模型，对噪声检测敏感，易产生关联错误。相反，随机方法显式建模不确定性，能更好处理复杂非线性动态，但计算开销大且结果受随机采样影响。本文提出一种在线多目标跟踪框架，融合确定性与随机原理，在不确定性下实现鲁棒跟踪。引入新型轨迹-检测匹配机制，提升目标数量增加时的可扩展性，并支持群体追踪。跟踪推理采用包含标识、状态、速度、轨迹惩罚和年龄的轨迹片段（tracklet），构建系统化跟踪流程。每个目标关联一个随机粒子集，用于计算与检测的匹配代价。相关实现已开源：https://github.com/SDU-VelKoTek/GenTrack3。
原文摘要 · Abstract (English)
Multi-object tracking (MOT) involves maintaining consistent target identities as objects dynamically enter and leave a scene. Deterministic approaches, such as tracking-by-detection with data association, produce reproducible results and are computationally efficient, but they rely heavily on motion models and are sensitive to noisy detections that can lead to association errors. In contrast, stochastic methods explicitly model uncertainty and can better handle complex non-linear dynamics, albeit at the cost of increased computational complexity and variability arising from random sampling. This paper presents an online MOT framework that integrates deterministic and stochastic principles to achieve robust tracking under uncertainty. Furthermore, a novel track-to-detection matching approach is introduced to enhance scalability with increasing target numbers while supporting group tracking. The tracking inference mechanism employs a tracklet that includes identifiers, states, velocities, track penalties and track ages of targets, supporting a systematic tracking pipeline. Each target is associated with a stochastic particle set to compute the matching cost to detections. Reference implementations of the proposed approach and baseline trackers can be found on GitHub: https://github.com/SDU-VelKoTek/GenTrack3.
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。