arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.10148cs.CVeess.IV
收藏

追踪无法追踪的人

Tracking the Untrackable

Fangyi Zhang

摘要:

虽然短期完全遮挡在视觉目标跟踪中很少发生,但大多数跟踪器在这些情况下都会失败。然而,即使目标是不可见的,人类仍然可以通过预测目标的轨迹来追赶目标。最近的心理学也表明,人类构建了未来的心理形象。受此启发,我们提出了一个HALLucinating特征跟踪(HAFT)模型,该模型能够预测未来帧的视觉特征嵌入。预期的未来帧聚焦于目标的运动,同时使目标的被遮挡部分产生幻觉。联合跟踪的幻觉特征和真实的功能,提高了跟踪器的鲁棒性,即使在目标是高度闭塞。通过广泛的实验评估,我们在多个数据集上取得了有希望的结果:OTB100,VOT 2018,LaSOT,TrackingNet和UAV123。

英文摘要:

Although short-term fully occlusion happens rare in visual object tracking, most trackers will fail under these circumstances. However, humans can still catch up the target by anticipating the trajectory of the target even the target is invisible. Recent psychology also has shown that humans build the mental image of the future. Inspired by that, we present a HAllucinating Features to Track (HAFT) model that enables to forecast the visual feature embedding of future frames. The anticipated future frames focus on the movement of the target while hallucinating the occluded part of the target. Jointly tracking on the hallucinated features and the real features improves the robustness of the tracker even when the target is highly occluded. Through extensive experimental evaluations, we achieve promising results on multiple datasets: OTB100, VOT2018, LaSOT, TrackingNet, and UAV123.

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。

↑