Immortal Tracker:Tracklet永不消亡
Immortal Tracker: Tracklet Never Dies
摘要:
先前的在线3D多对象跟踪(3DMOT)方法在轨迹片段与几帧的新检测不相关联时终止轨迹片段。但是,如果一个对象只是变暗,比如暂时被其他对象遮挡或只是离开FOV,过早终止轨迹将导致身份切换。我们发现,过早的轨迹终止是现代3DMOT系统中身份切换的主要原因。为了解决这个问题,我们提出了不朽的跟踪器,一个简单的跟踪系统,利用轨迹预测,以保持跟踪对象变暗。我们采用了一个简单的卡尔曼滤波器的轨迹预测和保存的轨迹时,目标是不可见的预测。通过这种方法,我们可以避免96%的车辆身份切换所造成的过早tracklet终止。在没有任何学习参数的情况下,我们的方法在Waymo开放数据集测试集上实现了0.0001水平的失配率和具有竞争力的MOTA。我们的错配率比任何以前公布的方法低几十倍。nuScenes上也报道了类似的结果。我们相信,建议不朽的跟踪器可以提供一个简单而强大的解决方案,推动3DMOT的极限。我们的代码可在https://github.com/ImmortalTracker/ImmortalTracker上获得。
英文摘要:
Previous online 3D Multi-Object Tracking(3DMOT) methods terminate a tracklet when it is not associated with new detections for a few frames. But if an object just goes dark, like being temporarily occluded by other objects or simply getting out of FOV, terminating a tracklet prematurely will result in an identity switch. We reveal that premature tracklet termination is the main cause of identity switches in modern 3DMOT systems. To address this, we propose Immortal Tracker, a simple tracking system that utilizes trajectory prediction to maintain tracklets for objects gone dark. We employ a simple Kalman filter for trajectory prediction and preserve the tracklet by prediction when the target is not visible. With this method, we can avoid 96% vehicle identity switches resulting from premature tracklet termination. Without any learned parameters, our method achieves a mismatch ratio at the 0.0001 level and competitive MOTA for the vehicle class on the Waymo Open Dataset test set. Our mismatch ratio is tens of times lower than any previously published method. Similar results are reported on nuScenes. We believe the proposed Immortal Tracker can offer a simple yet powerful solution for pushing the limit of 3DMOT. Our code is available at https://github.com/ImmortalTracker/ImmortalTracker.
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。