During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in these family of trackers significantly affect the performance of visual tracking. The ultimate goal is to utilize robust features invariant to any kind of appearance change of the object, while predicting the object location as properly as in the case of no appearance change. As the deep learning based methods have emerged, the study of learning features for specific tasks has accelerated. For instance, discriminative visual tracking methods based on deep architectures have been studied with promising performance. Nevertheless, correlation filter based (CFB) trackers confine themselves to use the pre-trained networks which are trained for object classification problem. To this end, in this manuscript the problem of learning deep fully convolutional features for the CFB visual tracking is formulated. In order to learn the proposed model, a novel and efficient backpropagation algorithm is presented based on the loss function of the network. The proposed learning framework enables the network model to be flexible for a custom design. Moreover, it alleviates the dependency on the network trained for classification. Extensive performance analysis shows the efficacy of the proposed custom design in the CFB tracking framework. By fine-tuning the convolutional parts of a state-of-the-art network and integrating this model to a CFB tracker, which is the top performing one of VOT2016, 18% increase is achieved in terms of expected average overlap, and tracking failures are decreased by 25%, while maintaining the superiority over the state-of-the-art methods in OTB-2013 and OTB-2015 tracking datasets.


翻译:近些年来,相关过滤器显示视觉物体跟踪的主要和显著效果。 这些跟踪器组中使用的特征类型对视觉跟踪的性能产生了显著影响。 最终目标是利用强势特征,不易出现任何物体的外观变化,同时对对象位置作出与外观变化一样的适当预测。 随着深层次学习方法的出现,对具体任务学习特征的研究加快了。 例如,基于深层结构的歧视性视觉跟踪方法得到了有希望的性能研究。 尽管如此,基于相关过滤器(CFB)的跟踪器(CFB)只能使用事先训练的网络,对目标分类问题产生显著影响。 最终目标是利用强势特征,不易出现任何物体的外观变化,同时对对象位置进行精确变化,同时根据网络损失功能的功能,提出新的和高效的反向调节算法。 拟议的网络模型使网络20 能够灵活地进行定制设计。 此外,基于目标分类培训的网络依赖性(CFB) 高级性分析显示深度的轨迹运行效率,同时将常规网络的轨迹进行精确的轨迹上,而运行的轨迹图则通过SFCFLB的轨图进行。

9
下载
关闭预览

相关内容

因果图,Causal Graphs,52页ppt
专知会员服务
246+阅读 · 2020年4月19日
Hierarchically Structured Meta-learning
CreateAMind
26+阅读 · 2019年5月22日
Transferring Knowledge across Learning Processes
CreateAMind
28+阅读 · 2019年5月18日
Call for Participation: Shared Tasks in NLPCC 2019
中国计算机学会
5+阅读 · 2019年3月22日
Unsupervised Learning via Meta-Learning
CreateAMind
42+阅读 · 2019年1月3日
【跟踪Tracking】15篇论文+代码 | 中秋快乐~
专知
18+阅读 · 2018年9月24日
STRCF for Visual Object Tracking
统计学习与视觉计算组
14+阅读 · 2018年5月29日
论文浅尝 | Reinforcement Learning for Relation Classification
开放知识图谱
9+阅读 · 2017年12月10日
Arxiv
5+阅读 · 2018年4月30日
Arxiv
8+阅读 · 2018年3月20日
Arxiv
6+阅读 · 2018年2月8日
VIP会员
相关VIP内容
因果图,Causal Graphs,52页ppt
专知会员服务
246+阅读 · 2020年4月19日
Top
微信扫码咨询专知VIP会员