Target tracker with masked discriminative correlation filter

Target tracker with masked discriminative correlation filter
复制标题

具有屏蔽判别相关滤波器的目标跟踪器

DOI:
10.1049/iet-ipr.2019.0881
复制
发表时间:
2020-03
影响因子:
2.3
通讯作者:
Bodong Li
Bodong Li
中科院分区:
计算机科学4区
文献类型:
--
作者:
Hang Liu;Bodong Li

文献摘要

参考文献

相似文献

鉴别相关滤波(DCF)方法由于其实时性而被广泛应用于目标跟踪。然而,DCF的计算效率导致边界效应,这降低了快速运动场景中的跟踪精度。此外,背景噪声总是需要小心处理,因为它们会在场景中造成麻烦,如背景杂波,遮挡,变形等。针对这两个问题,本研究提出了掩蔽判别相关滤波器,它使用掩码处理DCF滤波器以及目标样本,以抑制边界效应和背景噪声。在基准数据集上的实验结果表明,该跟踪器的性能优于一系列基准跟踪器,并在几乎所有的场景下优于它们上级。
The discriminative correlation filter (DCF) method is widely used in target tracking due to its real-time performance. However, the computational efficiency of DCF results in boundary effect, which reduces the tracking accuracy in fast motion scene. Besides, background noise is always required to be carefully handled for they will cause trouble in scenes such as background clutter, occlusion, deformation etc. To address the two issues, this study proposes masked discriminative correlation filter, which uses mask to process DCF filter as well as target samples so as to suppress boundary effect and background noise. Experimental results on benchmark datasets show that the proposed tracker performs better than a series of benchmark trackers, and is superior to them in almost various scenes.
DOI: 10.1049/iet-ipr.2017.0443
发表时间: 2018-03
期刊: IET Image Process.
影响因子: --
作者:
Zhaohui Hao;Guixi Liu;Haoyang Zhang
通讯作者: Zhaohui Hao;Guixi Liu;Haoyang Zhang
DOI: --
发表时间: --
期刊: --
影响因子: --
作者:
João F. Henriques;Rui Caseiro;P. Martins;Jorge Batista
通讯作者: João F. Henriques;Rui Caseiro;P. Martins;Jorge Batista
DOI: 10.1109/tpami.2010.226
发表时间: 2011-08-01
影响因子: 23.6
作者:
Babenko, Boris;Yang, Ming-Hsuan;Belongie, Serge
通讯作者: Belongie, Serge
DOI: 10.1109/tip.2009.2019809
发表时间: 2009-07-01
影响因子: 10.6
作者:
van de Weijer, Joost;Schmid, Cordelia;Larlus, Diane
通讯作者: Larlus, Diane
DOI: 10.1049/iet-ipr.2017.1043
发表时间: 2018-04
期刊: IET Image Process.
影响因子: --
作者:
Min Jiang;Jianyu Shen;Jun Kong;Hongtao Huo
通讯作者: Min Jiang;Jianyu Shen;Jun Kong;Hongtao Huo