structed_structured output tracking with kernels
来源:互联网 发布:苹果电脑下不了淘宝 编辑:程序博客网 时间:2024/05/16 23:54
http://blog.csdn.net/ikerpeng/article/details/39525321
http://blog.csdn.net/qianxin_dh/article/details/39377959
Paper Review: Struck: Structured Output Tracking with Kernels by Sam Hare, Amir Saffari, Philip H. S. Torr
Warning
My advisor asked me to review this paper on tracking. I really enjoyed this paper, then I decided to do a small post of it, because the paper is interesting and I tend to forget the things that I read, therefore I am doing this post as a personal reminder of the cool aspects of the paper and math of it. There are still some pieces of the paper that I do not fully know how they get it, but at least the post will tell you the main ideas involved. Let's start.
What problem is solving ?
This paper is solving the problem of tracking (select an initial bounding box. The position of the bounding box is changing as the frames run, trying to keep the main object/thing was initially inside the bounding box ). Specifically they propose a variant of tracking by detection framework (detection task applied over time). These methods relies on classifiers that can be trained online in order to handle appearance change of the object. Samples from arriving frames are used to update the trainer. For this reason, a labeller must decide the label of the sample and feed the classifier. The main research focus of tracking by detection is how to deal with poorly labelled samples, then robust loss functions, semi-supervised learning methods or multiple instance learning methods are used to train the classifier.
The test process relies in sliding window technique around expected position of the object and assign the new position as the best detection.
What is this paper doing different?
In the traditional approach the classifier output tells you how similar the image inside the tested bounding box is to the trained model of the object, then giving this information you decide the position of the best bounding box. Classifier has two possible labels "look like the object" or "look like something else".
In contrast, in this paper the output of the classifier is directly how much to translate the bounding box (they are planning to add rotations as future work). They used a polar grid with 5 radial and 16 angular divisions, giving 81 possible translations. In other words, the classifier has 81 possible output labels or classes corresponding to the 81 possible translations, named y.
Structural SVM is the tool used as classifier. Before going to that point, it is good to remind a little bit the traditional SVM. In binary SVM, you use your sample data to train the best hyper plane that separates two classes (output labels). In the case of linear SVM, it is determined by the vector w which has normal direction to the hyperplane. You can build a multiclass SVM in several ways including 1 vs all or 1 vs 1 (and voting)... that is a different long story that I am not going to talk about now.
The point is that by using Structural-SVM you can do the multi class classifier in a single optimization problem, which makes a good alternative in this case where you have 81 possible outputs. Our structure is simply 81 alternatives, there is no really structure or hierarchy like in a parse tree in NLP.
Structural SVM
The main trick in this paper
If we talk about training samples then
- structed_structured output tracking with kernels
- Struck: Structured Output Tracking with Kernels
- Struck: Structrued Output Tracking with Kernels 论文笔记
- Struck Structured Output Tracking with Kernels阅读笔记
- 目标跟踪学习系列八:Struck:Structured Output Tracking with Kernels(2011 ICCV)
- 目标跟踪学习系列九:Struck:Structured Output Tracking with Kernels头文件代码框架
- 目标跟踪学习系列十:Struck:Structured Output Tracking with Kernels 代码调试
- Struck: Structured Output Tracking with Kernels中用到的样本采样方法详解
- 目标跟踪系列十一:Exploiting the Circulant Structure of Tracking-by-detection with Kernels代码思路
- Exploiting the Circulant Structure of Tracking-by-detection with Kernels 笔记
- 阅读笔记4:CSK:Exploiting the Circulant Structure of Tracking-by-detection with Kernels
- Exploiting the Circulant Structure of Tracking-by-detection with Kernels代码思路
- Supervised Hashing with Kernels
- 目标跟踪系列十二:Exploiting the Circulant Structure of Tracking-by-detection with Kernels代码关键记录
- 目标跟踪系列十三:Exploiting the Circulant Structure of Tracking-by-detection with Kernels 公式详细的推导
- KSH(Supervised Hashing with Kernels)
- kernels
- Input/Output with files
- Flash Builder几种加载外部素材的的方法
- Flash WebGame 开发经验心得和PureMVC框架细说(转载)
- hdu 1058 Humble Numbers(卑微的数字)
- 用Point类计算两点间距离 actionscript3(转)
- X11简介及Xlib参考手册地址
- structed_structured output tracking with kernels
- ActionScript3 常用公式
- css hack
- Flex中利用folderOpenIcon, folderClosedIcon和defaultLeafIcon样式改变默认文件夹和子项目图标
- Flex Tree 组件数据源 图表等 修改
- ITK学习笔记-1:图像的读写
- 自定义FLEX的滚动条样式
- Flash MX本地保存数据的三种方法
- AS3与JS之间的简单自定义参数通讯