深入探究单目3D目标跟踪中的运动感知匹配
Delving into Motion-Aware Matching for Monocular 3D Object Tracking
AI总结：
针对现有单目3D多目标跟踪对运动线索探索不足的问题，提出包含三类运动感知组件的MoMA-M3T框架，在nuScenes和KITTI数据集上性能达最优水平，且可灵活嵌入现有检测器无需重训练。
摘要：
单目3D目标检测的最新进展推动了基于低成本相机传感器的3D多目标跟踪任务发展。本文发现，不同时间帧下目标的运动线索在3D多目标跟踪中至关重要，而现有基于单目图像的方法对这一点探索较少。为此，我们提出了一种面向单目3D多目标跟踪（MOT）的运动感知框架——MoMA-M3T，该框架主要包含三个运动感知组件：首先，我们将目标与特征空间中所有目标轨迹相关的可能运动表示为其运动特征；随后，我们通过运动Transformer（运动变换器）从时空角度对沿时间帧的历史目标轨迹进行建模；最后，我们提出运动感知匹配模块，将历史目标轨迹与当前观测关联起来，得到最终跟踪结果。我们在nuScenes和KITTI数据集上开展了大量实验，结果表明MoMA-M3T的性能与现有最优方法相当。此外，该跟踪器具备灵活性，无需重新训练即可轻松嵌入现有基于图像的3D目标检测器中。代码与模型可在https://github.com/kuanchihhuang/MoMA-M3T获取。
英文摘要：
Recent advances of monocular 3D object detection facilitate the 3D multi-object tracking task based on low-cost camera sensors. In this paper, we find that the motion cue of objects along different time frames is critical in 3D multi-object tracking, which is less explored in existing monocular-based approaches. In this paper, we propose a motion-aware framework for monocular 3D MOT. To this end, we propose MoMA-M3T, a framework that mainly consists of three motion-aware components. First, we represent the possible movement of an object related to all object tracklets in the feature space as its motion features. Then, we further model the historical object tracklet along the time frame in a spatial-temporal perspective via a motion transformer. Finally, we propose a motion-aware matching module to associate historical object tracklets and current observations as final tracking results. We conduct extensive experiments on the nuScenes and KITTI datasets to demonstrate that our MoMA-M3T achieves competitive performance against state-of-the-art methods. Moreover, the proposed tracker is flexible and can be easily plugged into existing image-based 3D object detectors without re-training. Code and models are available at https://github.com/kuanchihhuang/MoMA-M3T.
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。
