arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.10404cs.CV
收藏

MotionTrack:学习鲁棒的短期与长期运动以实现多目标跟踪

MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking

Xi’an Jiaotong University(西安交通大学);Wormpex AI Research(Wormpex AI研究院);University of Illinois at Chicago(伊利诺伊大学芝加哥分校)

Zheng Qin, Sanping Zhou, Le Wang, Jinghai Duan, Gang Hua, Wei Tang

AI总结:

本文提出多目标跟踪器 MotionTrack,通过 Interaction Module 和 Refind Module 在统一框架中学习短期与长期运动,以应对密集人群和极端遮挡,并在 MOT17 和 MOT20 上取得领先性能。

摘要:

多目标跟踪(MOT)的主要挑战在于为每个目标维持连续的轨迹。现有方法通常学习可靠的运动模式以在相邻帧之间匹配同一目标,并学习具有判别力的外观特征以在长时间后重新识别丢失的目标。然而,在跟踪过程中,密集人群和极端遮挡很容易损害运动预测的可靠性和外观的判别力。在本文中,我们提出了一种简单而有效的多目标跟踪器,即 MotionTrack,它在统一框架中学习鲁棒的短期和长期运动,以将轨迹从短距离关联到长距离。针对密集人群,我们设计了一个新颖的 Interaction Module,从短期轨迹中学习交互感知的运动,从而能够估计每个目标的复杂移动。针对极端遮挡,我们构建了一个新颖的 Refind Module,从目标的历史轨迹中学习可靠的长期运动,从而将被中断的轨迹与其对应的检测结果连接起来。我们的 Interaction Module 和 Refind Module 嵌入在众所周知的 tracking-by-detection 范式中,二者可以协同工作以保持优越的性能。在 MOT17 和 MOT20 数据集上的大量实验结果表明,我们的方法在具有挑战性的场景中具有优越性,并在各种 MOT 指标上取得了最先进的性能。

英文摘要:

The main challenge of Multi-Object Tracking~(MOT) lies in maintaining a continuous trajectory for each target. Existing methods often learn reliable motion patterns to match the same target between adjacent frames and discriminative appearance features to re-identify the lost targets after a long period. However, the reliability of motion prediction and the discriminability of appearances can be easily hurt by dense crowds and extreme occlusions in the tracking process. In this paper, we propose a simple yet effective multi-object tracker, i.e., MotionTrack, which learns robust short-term and long-term motions in a unified framework to associate trajectories from a short to long range. For dense crowds, we design a novel Interaction Module to learn interaction-aware motions from short-term trajectories, which can estimate the complex movement of each target. For extreme occlusions, we build a novel Refind Module to learn reliable long-term motions from the target's history trajectory, which can link the interrupted trajectory with its corresponding detection. Our Interaction Module and Refind Module are embedded in the well-known tracking-by-detection paradigm, which can work in tandem to maintain superior performance. Extensive experimental results on MOT17 and MOT20 datasets demonstrate the superiority of our approach in challenging scenarios, and it achieves state-of-the-art performances at various MOT metrics.

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。

↑