arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.01771cs.CV
收藏

使用同现约束学习跟踪部件的鲁棒社会

Learning a Robust Society of Tracking Parts using Co-occurrence Constraints

Bitdefender(比特梵德);Institute of Mathematics of the Romanian Academy(罗马尼亚科学院数学研究所);University of Bucharest(布加勒斯特大学);University Politehnica of Bucharest(布加勒斯特理工大学)

Elena Burceanu, Marius Leordeanu

摘要:

目标跟踪是计算机视觉中的一个基本问题,已经研究了几十年。跟踪的主要挑战之一是适应对象外观随时间的变化,并避免漂移到背景杂波。我们通过提出一个由不同部分组成的深度神经网络来应对这一挑战,它的功能是作为一个跟踪部分的社会。它们根据一定的策略协同工作,并以稳健的方式相互学习,使用共现约束来确保稳健的推理和学习。从结构的角度来看,我们的网络是由两个主要途径。一种途径更为保守。它仔细监控了大量简单的跟踪器部分,这些部分是作为深度特征激活图上的线性过滤器学习的。它为各个部分分配了不同的角色。它提升了可靠的,并删除了不一致的。我们学习这些过滤器同时在一个有效的方式,与一个单一的封闭形式的制定,我们提出了新的理论性质。第二条道路更加进步。它是完全在线学习的,因此它能够更好地模拟对象外观的变化。为了以鲁棒的方式适应,它只在高度置信的帧上学习,这些帧是使用与第一路径的同现来决定的。因此,我们的系统在跟踪中具有两种主要方法的全部益处。更大的简单过滤器部分提供了鲁棒性,而在线学习的完整深度网络提供了对变化的适应性。如实验部分所示,我们的方法在具有挑战性的VOT17基准测试中实现了最先进的性能,在一般EAO指标和失败次数方面都优于已发表的方法,并且有很大的优势。

英文摘要:

Object tracking is an essential problem in computer vision that has been researched for several decades. One of the main challenges in tracking is to adapt to object appearance changes over time and avoiding drifting to background clutter. We address this challenge by proposing a deep neural network composed of different parts, which functions as a society of tracking parts. They work in conjunction according to a certain policy and learn from each other in a robust manner, using co-occurrence constraints that ensure robust inference and learning. From a structural point of view, our network is composed of two main pathways. One pathway is more conservative. It carefully monitors a large set of simple tracker parts learned as linear filters over deep feature activation maps. It assigns the parts different roles. It promotes the reliable ones and removes the inconsistent ones. We learn these filters simultaneously in an efficient way, with a single closed-form formulation, for which we propose novel theoretical properties. The second pathway is more progressive. It is learned completely online and thus it is able to better model object appearance changes. In order to adapt in a robust manner, it is learned only on highly confident frames, which are decided using co-occurrences with the first pathway. Thus, our system has the full benefit of two main approaches in tracking. The larger set of simpler filter parts offers robustness, while the full deep network learned online provides adaptability to change. As shown in the experimental section, our approach achieves state of the art performance on the challenging VOT17 benchmark, outperforming the published methods both on the general EAO metric and in the number of fails, by a significant margin.

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。

↑