arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.09672cs.CVcs.RO
收藏

IMM-MOT:一种采用交互式多模型滤波器的新型3D多目标跟踪框架

IMM-MOT: A Novel 3D Multi-object Tracking Framework with Interacting Multiple Model Filter

School of Computer Science and Technology, Xidian University(西安电子科技大学计算机科学与技术学院)

Xiaohong Liu, Xulong Zhao, Gang Liu, Zili Wu, Tao Wang, Lei Meng, Yuhan Wang

AI总结:

提出IMM-MOT框架,通过交互式多模型滤波、阻尼窗口和距离分数增强提升复杂运动下的3D多目标跟踪性能,NuScenes Val上AMOTA达73.8%。

摘要:

3D多目标跟踪(MOT)提供周围物体的轨迹,帮助机器人或车辆更智能地进行路径规划和避障。现有基于Tracking-by-Detection框架的3D MOT方法通常在物体的整个跟踪过程中使用单一运动模型。然而,物体可能会因周围环境变化而改变其运动模式。本文在IMM-MOT中引入交互式多模型(Interacting Multiple Model)滤波器,以精确拟合单个物体的复杂运动模式,克服现有方法中单模型跟踪的局限。此外,我们在轨迹生命周期管理中加入阻尼窗口(Damping Window)机制,利用轨迹的连续关联状态控制其创建与终止,减少漏检低置信度真实目标的情况。此外,我们提出基于距离的分数增强模块,通过调整检测分数增强假阳性与真阳性之间的区分度,从而提升Score Filter的有效性。在NuScenes Val数据集上,IMM-MOT优于大多数其他使用3D点云的单模态模型,AMOTA达到73.8%。项目位于https://github.com/Ap01lo/IMM-MOT。

英文摘要:

3D Multi-Object Tracking (MOT) provides the trajectories of surrounding objects, assisting robots or vehicles in smarter path planning and obstacle avoidance. Existing 3D MOT methods based on the Tracking-by-Detection framework typically use a single motion model to track an object throughout its entire tracking process. However, objects may change their motion patterns due to variations in the surrounding environment. In this paper, we introduce the Interacting Multiple Model filter in IMM-MOT, which accurately fits the complex motion patterns of individual objects, overcoming the limitation of single-model tracking in existing approaches. In addition, we incorporate a Damping Window mechanism into the trajectory lifecycle management, leveraging the continuous association status of trajectories to control their creation and termination, reducing the occurrence of overlooked low-confidence true targets. Furthermore, we propose the Distance-Based Score Enhancement module, which enhances the differentiation between false positives and true positives by adjusting detection scores, thereby improving the effectiveness of the Score Filter. On the NuScenes Val dataset, IMM-MOT outperforms most other single-modal models using 3D point clouds, achieving an AMOTA of 73.8%. Our project is available at https://github.com/Ap01lo/IMM-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。

↑