arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.04367cs.CV
收藏

基于不确定流的鲁棒实例跟踪

Robust Instance Tracking via Uncertainty Flow

Carnegie Mellon University(卡内基梅隆大学)

Jianing Qian, Junyu Nan, Siddharth Ancha, Brian Okorn, David Held

摘要:

当前最先进的跟踪器经常由于干扰和大对象外观变化而失败。在这项工作中,我们探讨了使用密集的光流,以提高跟踪的鲁棒性。我们的主要观点是,由于流量估计也可能存在误差,因此我们需要对流量不确定性进行估计,以实现鲁棒跟踪。我们提出了一种新的跟踪框架,它结合了外观和流动的不确定性信息,以跟踪具有挑战性的场景中的对象。我们通过实验验证了我们的框架提高了跟踪鲁棒性,从而获得了新的最先进的结果。此外,我们的实验消融显示了强大的跟踪流量的不确定性的重要性。

英文摘要:

Current state-of-the-art trackers often fail due to distractorsand large object appearance changes. In this work, we explore the use ofdense optical flow to improve tracking robustness. Our main insight is that, because flow estimation can also have errors, we need to incorporate an estimate of flow uncertainty for robust tracking. We present a novel tracking framework which combines appearance and flow uncertainty information to track objects in challenging scenarios. We experimentally verify that our framework improves tracking robustness, leading to new state-of-the-art results. Further, our experimental ablations shows the importance of flow uncertainty for robust tracking.

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。

↑