论文标题
与多个对象跟踪的运动建模同时检测和跟踪
Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking
论文作者
论文摘要
基于深度学习的多个对象跟踪（MOT）当前依赖于现成的探测器进行逐个检测。这将导致探测器有偏置的深层模型和受检测器影响的评估。为了解决此问题，我们引入了深度运动建模网络（DMM-NET），该网络可以估算多个对象的运动参数以端到端的方式执行关节检测和关联。 DMM-NET模型对象在多个帧上具有特征，并同时渗透对象类，可见性及其运动参数。这些输出很容易用于更新轨迹以提高MOT。对于流行的UA-Detrac挑战，DMM-NET的PR-MOTA得分为12.80 @ 120+ fps，这是更好的性能和数量级的速度。我们还为车辆跟踪贡献了一个合成的大规模公共数据集Omni-Mot，可提供精确的地面真相注释，以消除MOT评估中的检测器影响。 This 14M+ frames dataset is extendable with our public script (Code at Dataset <https://github.com/shijieS/OmniMOTDataset>, Dataset Recorder <https://github.com/shijieS/OMOTDRecorder>, Omni-MOT Source <https://github.com/shijieS/DMMN>).我们证明了Omni-Mot对DMMNET的深入学习的适用性，还将我们网络的源代码公开。
Deep learning-based Multiple Object Tracking (MOT) currently relies on off-the-shelf detectors for tracking-by-detection.This results in deep models that are detector biased and evaluations that are detector influenced. To resolve this issue, we introduce Deep Motion Modeling Network (DMM-Net) that can estimate multiple objects' motion parameters to perform joint detection and association in an end-to-end manner. DMM-Net models object features over multiple frames and simultaneously infers object classes, visibility, and their motion parameters. These outputs are readily used to update the tracklets for efficient MOT. DMM-Net achieves PR-MOTA score of 12.80 @ 120+ fps for the popular UA-DETRAC challenge, which is better performance and orders of magnitude faster. We also contribute a synthetic large-scale public dataset Omni-MOT for vehicle tracking that provides precise ground-truth annotations to eliminate the detector influence in MOT evaluation. This 14M+ frames dataset is extendable with our public script (Code at Dataset <https://github.com/shijieS/OmniMOTDataset>, Dataset Recorder <https://github.com/shijieS/OMOTDRecorder>, Omni-MOT Source <https://github.com/shijieS/DMMN>). We demonstrate the suitability of Omni-MOT for deep learning with DMMNet and also make the source code of our network public.
