arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2208.03571cs.CVcs.AI
收藏

用于多目标跟踪的基于Transformer的分配决策网络

Transformer-based assignment decision network for multiple object tracking

Remote Sensing Laboratory(遥感实验室);National Technical University of Athens(希腊国家技术大学)

Athena Psalta, Vasileios Tsironis, Konstantinos Karantzalos

AI总结:

本文提出基于Transformer的分配决策网络TADN,在单次前向传递中直接推断检测与目标之间的分配对,无需推理时显式优化,并在MOT17、MOT20和UA-DETRAC上验证了其在线多目标跟踪性能。

摘要:

数据关联是任何遵循检测跟踪范式的多目标跟踪(MOT)方法的关键组成部分。为了生成完整轨迹,此类方法在每个时间步采用数据关联过程来建立检测与现有目标之间的分配。最近的数据关联方法试图解决多维线性分配任务或网络流最小化问题,或通过多假设跟踪来处理。然而,在推理过程中,每个序列帧都需要一个计算最优分配的优化步骤,这给任何给定解决方案带来了额外的复杂性。为此,在本工作的背景下,我们提出了基于Transformer的分配决策网络(TADN),它在推理过程中无需任何显式优化即可处理数据关联。特别是,TADN可以在网络的单次前向传递中直接推断检测与活跃目标之间的分配对。我们将TADN集成到一个相当简单的MOT框架中,设计了一种新颖的训练策略以实现高效的端到端训练,并在几个流行的基准上展示了我们的方法在在线视觉检测跟踪MOT中的巨大潜力,即MOT17、MOT20和UA-DETRAC。尽管我们提出的方法作为一个跟踪器性质简单,缺乏遮挡处理或重识别等重要辅助组件,但它在大多数评估指标中表现出强劲的性能。我们的方法实现已在https://github.com/psaltaath/tadn-mot上公开提供。

英文摘要:

Data association is a crucial component for any multiple object tracking (MOT) method that follows the tracking-by-detection paradigm. To generate complete trajectories such methods employ a data association process to establish assignments between detections and existing targets during each timestep. Recent data association approaches try to solve either a multi-dimensional linear assignment task or a network flow minimization problem or tackle it via multiple hypotheses tracking. However, during inference an optimization step that computes optimal assignments is required for every sequence frame inducing additional complexity to any given solution. To this end, in the context of this work we introduce Transformer-based Assignment Decision Network (TADN) that tackles data association without the need of any explicit optimization during inference. In particular, TADN can directly infer assignment pairs between detections and active targets in a single forward pass of the network. We have integrated TADN in a rather simple MOT framework, designed a novel training strategy for efficient end-to-end training and demonstrated the high potential of our approach for online visual tracking-by-detection MOT on several popular benchmarks, i.e. MOT17, MOT20 and UA-DETRAC. Our proposed approach demonstrates strong performance in most evaluation metrics despite its simple nature as a tracker lacking significant auxiliary components such as occlusion handling or re-identification. The implementation of our method is publicly available at https://github.com/psaltaath/tadn-mot.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑