[论文解读] A Baseline for 3D Multi-Object Tracking

Xinshuo Weng, Kris Kitani|arXiv (Cornell University)|Jul 9, 2019

Advanced Neural Network Applications参考文献 32被引用 81

一句话总结

本文提出了一种简单但高度高效的实时3D多目标跟踪（MOT）基线系统，该系统结合了现成的3D目标检测器、3D卡尔曼滤波器和匈牙利算法进行数据关联。尽管结构简单，该方法在KITTI 3D MOT基准上实现了最先进性能，3D MOTA提升至76.47，运行速度达214.7 FPS——比先前最先进2D MOT系统快65倍。

ABSTRACT

3D multi-object tracking (MOT) is an essential component technology for many real-time applications such as autonomous driving or assistive robotics. However, recent works for 3D MOT tend to focus more on developing accurate systems giving less regard to computational cost and system complexity. In contrast, this work proposes a simple yet accurate real-time baseline 3D MOT system. We use an off-the-shelf 3D object detector to obtain oriented 3D bounding boxes from the LiDAR point cloud. Then, a combination of 3D Kalman filter and Hungarian algorithm is used for state estimation and data association. Although our baseline system is a straightforward combination of standard methods, we obtain the state-of-the-art results. To evaluate our baseline system, we propose a new 3D MOT extension to the official KITTI 2D MOT evaluation along with two new metrics. Our proposed baseline method for 3D MOT establishes new state-of-the-art performance on 3D MOT for KITTI, improving the 3D MOTA from 72.23 of prior art to 76.47. Surprisingly, by projecting our 3D tracking results to the 2D image plane and compare against published 2D MOT methods, our system places 2nd on the official KITTI leaderboard. Also, our proposed 3D MOT method runs at a rate of 214.7 FPS, 65 times faster than the state-of-the-art 2D MOT system. Our code is publicly available at this https URL

研究动机与目标

• 开发一种计算高效且准确的3D MOT系统，实现性能与速度的平衡。
• 为自动驾驶和机器人领域中的3D多目标跟踪建立一个实用的实时基线。
• 通过扩展KITTI 2D MOT基准并引入新指标，评估3D MOT性能。
• 证明简单组合标准组件可超越复杂且专用的系统。

提出的方法

• 使用现成的3D目标检测器，从LiDAR点云生成定向3D边界框。
• 采用3D卡尔曼滤波器对跟踪对象的状态进行估计。
• 应用匈牙利算法实现检测结果与现有轨迹之间的数据关联。
• 将3D跟踪结果投影到2D图像平面，以便与2D MOT方法进行跨基准比较。
• 提出一种新的3D MOT评估协议，扩展官方KITTI 2D MOT基准。
• 引入两种新指标，以评估标准MOTA之外的3D MOT性能。

实验结果

研究问题

• RQ1 简单、模块化的标准3D检测与跟踪组件组合能否实现最先进3D MOT性能？
• RQ2 当投影到2D时，实时3D MOT系统的性能与SOTA 2D MOT系统相比如何？
• RQ3 轻量级3D MOT基线系统相比复杂SOTA系统在计算效率方面表现如何？
• RQ4 在准确性和速度方面，简单3D跟踪器在多大程度上能超越专用系统？
• RQ5 所提出的3D MOT评估协议在多大程度上提升了3D跟踪性能的评估质量？

主要发现

• 所提出的3D MOT基线系统在KITTI数据集上实现了76.47的3D MOTA，超越了先前最先进水平的72.23。
• 当投影到2D时，该系统在官方KITTI 2D MOT排行榜中位列第2。
• 系统运行速度达214.7 FPS，是当前最先进2D MOT系统的65倍。
• 该方法表明，3D MOT中简洁性与高效性并不以牺牲准确性为代价。
• 新评估协议与指标使得3D MOT系统评估更加全面且公平。
• 结果表明，当正确集成时，标准组件如卡尔曼滤波器和匈牙利算法在现代3D跟踪中依然极为有效。