arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2103.14258cs.CV
收藏

学习使用对象持久性进行跟踪

Learning to Track with Object Permanence

Toyota Research Institute(丰田研究院)

Pavel Tokmakov, Jie Li, Wolfram Burgard, Adrien Gaidon

摘要:

检测跟踪是在线多目标跟踪的主要方法,在定位和关联步骤之间交替进行。因此,它在很大程度上取决于瞬时观测的质量,当物体不完全可见时,它往往会失败。相比之下,人类的跟踪是强调对象永久性的概念:一旦一个对象被识别,我们就意识到它的物理存在,甚至在完全遮挡的情况下也可以近似地定位它。在这项工作中,我们介绍了一个端到端的联合目标检测和跟踪,是能够这样的推理可训练的方法。我们建立在最近的CenterTrack架构之上,该架构将成对的帧作为输入,并将其扩展到任意长度的视频。为此,我们增加了一个时空的,经常性的记忆模块的模型,允许它的原因对象的位置和身份在当前帧中使用所有以前的历史。然而,如何训练这种方法并不明显。我们研究了这个问题上的一个新的,大规模的,多对象跟踪,它提供了地面实况注释不可见的对象,并提出了几种方法来监督跟踪背后的闭塞。我们的模型在合成和真实数据上联合训练,由于其对遮挡的鲁棒性,在KITTI和MOT17数据集上的表现优于最先进的技术。

英文摘要:

Tracking by detection, the dominant approach for online multi-object tracking, alternates between localization and association steps. As a result, it strongly depends on the quality of instantaneous observations, often failing when objects are not fully visible. In contrast, tracking in humans is underlined by the notion of object permanence: once an object is recognized, we are aware of its physical existence and can approximately localize it even under full occlusions. In this work, we introduce an end-to-end trainable approach for joint object detection and tracking that is capable of such reasoning. We build on top of the recent CenterTrack architecture, which takes pairs of frames as input, and extend it to videos of arbitrary length. To this end, we augment the model with a spatio-temporal, recurrent memory module, allowing it to reason about object locations and identities in the current frame using all the previous history. It is, however, not obvious how to train such an approach. We study this question on a new, large-scale, synthetic dataset for multi-object tracking, which provides ground truth annotations for invisible objects, and propose several approaches for supervising tracking behind occlusions. Our model, trained jointly on synthetic and real data, outperforms the state of the art on KITTI and MOT17 datasets thanks to its robustness to occlusions.

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。

↑