A Weighted-Overlap Based Metric for Single Visual Object Tracking Evaluation

SUN Qiao; ZHANG Sheng-xiu; ZHANG Zheng-xin; CAO Li-jia; LI Xiao-feng

doi:10.3969/j.issn.0372-2112.2017.03.036

您当前的位置：

首页 >

文章列表页 >

A Weighted-Overlap Based Metric for Single Visual Object Tracking Evaluation

更新时间：2025-07-16

- A Weighted-Overlap Based Metric for Single Visual Object Tracking Evaluation
- Acta Electronica Sinica Vol. 45, Issue 3, Pages: 753-761(2017)
- 作者机构：
  
  火箭军工程大学控制工程系,陕西,西安,710025
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.0372-2112.2017.03.036
  CLC： TP391.4
- Published：2017
- 稿件说明：
移动端阅览
SUN Qiao, ZHANG Sheng-xiu, ZHANG Zheng-xin, et al. A Weighted-Overlap Based Metric for Single Visual Object Tracking Evaluation[J]. Acta Electronica Sinica, 2017, 45(3): 753-761.
DOI：

SUN Qiao, ZHANG Sheng-xiu, ZHANG Zheng-xin, et al. A Weighted-Overlap Based Metric for Single Visual Object Tracking Evaluation[J]. Acta Electronica Sinica, 2017, 45(3): 753-761. DOI： 10.3969/j.issn.0372-2112.2017.03.036.

摘要

针对真值标注的歧义性、偏差性问题和具有缩放场景的视觉跟踪应用情况，提出了一种新的视觉跟踪单目标基准评价指标.首先，在重叠率基础上提出了加权重叠率框架；其次，提出了多区域标注方法，通过多区域标注降低标注者歧义性，在具有缩放场景的应用中，通过反演进行多区域标注，使评价更符合应用实际；再次，针对标注的偏差性，提出了多标注融合方法，提高了标注的可信度；最后，将应用于单次跟踪评价的重叠率框架推广到多次跟踪评价，利用加权结果图使评价更具解释性.通过著名评价标准VOT、OTB的真值标注融合实验验证了本文标注规则的准确性；通过在具有缩放场景的视觉跟踪实验和重复实验，与其他跟踪指标的比较验证了本文指标的有效性.

Abstract

Aimed at the problems of annotation of ground truth and the application of zooming

a new basic metric for visual tracking evaluation is proposed.Firstly

a weighted-overlap frame is reconstructed based on the traditional overlap.Secondly

we put forward multiple region annotation to decrease the deviation and apply in zooming.Thirdly

a multi-label fusion method is presented to improve the confidence level of the labels.Last but not least

the presented methods are expanded to repeated visual tracking evaluation

where a weighted result chart is utilized to make the evaluation more explanatory.Experimental results show that our annotation rule are more accurate than VOT and OTB

and the proposed metric is more appropriate than other metric.

关键词

Keywords

references

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Robust Visual Tracking via Principal Component Pursuit

Visual Tracking Algorithm Based on Feature Matching of Key Regions

Online Visual Tracking Based on Local Patch Learning

Swift Matching Exhaustive Search Based on Rotation Invariant Histogram

Related Author

JIANG Yun-yun

YE Jun-yong

WANG Tong-qing

LI Hong-you

XUE Mo-gen

YUAN Guang-lin

LIU Xiang

HUANG An-qi

Related Institution

Key Lab of Optoelectronic Technique and System of Ministry of Education,Chongqing University

Department of Scientific Research Army Officer Academy of PLA Hefei Anhui China

Eleventh Department Army Officer Academy of PLA Hefei Anhui China

Department of Scientific Research, Army Officer Academy of PLA

Eleventh Department, Army Officer Academy of PLA

⁰