Factors that affect the performance of a tracing algorithm

1 Illumination variation
2 Occlusion
3 Background clutters



Main modules for object tracking

1 Target representation scheme
2 Search mechanism
3 Model update



Evaluation Methodology

1 Precison plot:
The percentage of frames whose estimated location is within the given threshold distance of the ground truth.
x coordinate: threshold

2 Success plot: 
The ratios of successful frames at the thresholds varied from 0 to 1
x coordinate: threshold

3 Robustness Evaluation
A OPE: one-pass evaluation
B TRE temporal robustness evaluation
C SRE spatial robustness evaluation




Overall Performance

详见论文
1  TLD performs well in long sequences with a redetection module 
2 Struck only estimates the location of target and does not handle scale variation
3 Sparse representations are effectivemodels to account for appearance change (e.g., occlusion).
4 Local sparse representations are more effective than the ones with holistic sparse

templates.
5 It indicates the alignmentpooling technique adopted by ASLA is more robust to misalignments and background clutters.
6 When an object moves fast, dense sampling based trackers (e.g., Struck, TLD and CXT) perform much better than others
7 On the OCC subset, the Struck, SCM, TLD, LSK and ASLA methods outperform others. The results suggest that structured learning and local sparse representations are effective in dealing with occlusions.
8 On the SV subset,ASLA, SCM and Struck perform best. The results show that

trackers with affine motion models (e.g., ASLA and SCM) often handle scale variation better than others that are designed to account for only translational motion with a few exceptions such as Struck
9 The performance of TLD, CXT, DFT and LOT decreases with the increase of

initialization scale. This indicates these trackers are more sensitive to background clutters. 
10 On the other hand, some trackers perform well or even better when the initial bounding box is enlarged, such as Struck, OAB, SemiT, and BSBT. This indicates that the Haar-like features are somewhat robust to background
clutters due to the summation operations when computing features. Overall, Struck is less sensitive to scale variation than other well-performing methods.
11 Some trackers perform better when the scale factor is smaller, such as L1APG, MTT, LOT and CPF



Dataset





相应站点





Online Object Tracking: A Benchmark 论文笔记的更多相关文章

  1. Online Object Tracking: A Benchmark 论文笔记(转)

    转自:http://blog.csdn.net/lanbing510/article/details/40411877 有博主翻译了这篇论文:http://blog.csdn.net/roamer_n ...

  2. Deep Reinforcement Learning for Visual Object Tracking in Videos 论文笔记

    Deep Reinforcement Learning for Visual Object Tracking in Videos 论文笔记 arXiv 摘要:本文提出了一种 DRL 算法进行单目标跟踪 ...

  3. CVPR2018 关于视频目标跟踪(Object Tracking)的论文简要分析与总结

    本文转自:https://blog.csdn.net/weixin_40645129/article/details/81173088 CVPR2018已公布关于视频目标跟踪的论文简要分析与总结 一, ...

  4. Struck: Structrued Output Tracking with Kernels 论文笔记

    Main idear Treat the tracking problem as a classification task and use online learning techniques to ...

  5. Learning Rich Features from RGB-D Images for Object Detection and Segmentation论文笔记

    相关工作: 将R-CNN推广到RGB-D图像,引入一种新的编码方式来捕获图像中像素的地心姿态,并且这种新的编码方式比单纯使用深度通道有了明显的改进. 我们建议在每个像素上用三个通道编码深度图像:水平视 ...

  6. Online Object Tracking: A Benchmark 翻译

    来自http://www.aichengxu.com/view/2426102 摘要 目标跟踪是计算机视觉大量应用中的重要组成部分之一.近年来,尽管在分享源码和数据集方面的努力已经取得了许多进展,开发 ...

  7. [Object Tracking] Overview of algorithms for Object Tracking

    From: https://www.zhihu.com/question/26493945 可以载入史册的知乎贴 目标跟踪之NIUBILITY的相关滤波 - 专注于分享目标跟踪中非常高效快速的相关滤波 ...

  8. Correlation Filter in Visual Tracking系列一:Visual Object Tracking using Adaptive Correlation Filters 论文笔记

    Visual Object Tracking using Adaptive Correlation Filters 一文发表于2010的CVPR上,是笔者所知的第一篇将correlation filt ...

  9. 论文笔记之:Fully-Convolutional Siamese Networks for Object Tracking

    gansh Fully-Convolutional Siamese Network for Object Tracking 摘要:任意目标的跟踪问题通常是根据一个物体的外观来构建表观模型.虽然也取得了 ...

随机推荐

  1. for 循环的中的i

    for循环中的i,如果倒过来判断从某数一直到0,一定不能用unsigned int类型的i,因为unsigned int不可能小于0,当i=0后,i--将达到最大的unsigned int,依旧> ...

  2. android 自定义view 前的基础知识

    本篇文章是自己自学自定义view前的准备,具体参考资料来自 Android LayoutInflater原理分析,带你一步步深入了解View(一) Android视图绘制流程完全解析,带你一步步深入了 ...

  3. 12.0&12.1 Xcode开发包

    12.1开发包下载链接 12.0开发包下载链接 12.1(16B91)开发包下载链接 Finder打开后,按command+shift+G前往这个地址: /Applications/Xcode.app ...

  4. Windows phone开发 页面布局之屏幕方向

    (博客部分内容参考Windows phone开发文档) Windows phone的屏幕方向是利用Windows phone设备的方向传感器提供的数据实现切换的. Windows Phone支持纵向和 ...

  5. 高通处理器手机 解锁Bootloader 教程

    目前很多手机都需要解锁Bootloader之后才能进行刷机操作   本篇教程教你如何傻瓜式解锁Bootloader 首先需要在设置-关于手机 找到版本号(个别手机可能是内核版本号,甚至其他) 然后 快 ...

  6. mysql自动添加时间的方法

    时间添加方法,可以在编辑数据时方便时间选择输入: 将时间列DataType设为timestamp,设定其默认值为CURRENT_TIMESTAMP. 这样每次插入一条新纪录,数据库会自动在时间段存储当 ...

  7. MatLab之HDL coder

    1 Workflow The workflow for applying HDL code generation to the hardware design process requires the ...

  8. 使用pelican创建静态博客

    创建工作目录 首先使用pip安装pelican和markdown pip install pelican markdown 然后创建目录 mkdir my_blog 接着进入目录cd my_blog, ...

  9. Jenkins 定时 构建项目

    选择要定时构建的 项目-->配置-->构建触发器 触发项目: Poll SCM:定时检查源码变更(根据SCM软件的版本号),如果有更新就checkout最新code下来,然后执行构建动作. ...

  10. HDU 4405 Aeroplane chess(概率dp,数学期望)

    题目 http://kicd.blog.163.com/blog/static/126961911200910168335852/ 根据里面的例子,就可以很简单的写出来了,虽然我现在还是不是很理解为什 ...