Understanding andDiagnosing Visual Tracking Systems
2016-08-15 21:41
549 查看
Understanding andDiagnosing Visual Tracking Systems
A tracking system usually worksby initializing the observation model with the given bounding box of the targetin the first frame. In each of the following frames, the motion model
firstgenerates candidate regions or proposals for testing based on the estimationfrom the previous frame. The candidate regions or proposals are fed into theobservation model to compute their probability of being the target. The onewith the highest probability
is then selected as the estimation result of thecurrent frame. Based on the output of the observation model, the model updaterdecides whether the observation model needs any update and, if needed, theupdate frequency. Finally, if there are multiple trackers,
the bounding boxesreturned by the trackers will be combined by the ensemble post-processor toobtain a more accurate estimate. This pipeline is illustrated in Fig.
Five constituent parts:
1. Motion Model: Based on theestimation from the previous frame, the motion model generates a set ofcandidate regions or bounding boxes which may contain the target
in the currentframe.
2.Feature Extractor: Thefeature extractor represents each candidate in the candidate set using somefeatures.
3.Observation Model: Theobservation model judges whether a candidate is the target based on thefeatures extracted from the candidate.
4.Model Updater: The modelupdater controls the strategy and frequency of updating the observation model. Ithas to strike a balance between model adaptation and drift.
5. Ensemble Post-processor:When a tracking system consists of multiple trackers, the ensemblepostprocessor takes the outputs of the constituent trackers and uses
the ensemblelearning approach to combine them into the final result.
Details of all these components
1.Motion Model :ParticleFilter Sliding
,Window Radius ,Sliding Window
2.Feature Extractor: RawGrayscale ,Raw Color , Haar-like Features, HOG ,HOG
+Raw Color
3.Observation Model:LogisticRegression ,Ridge Regression ,SVM ,Structured
Output SVM (SO-SVM)
4.Model Updater:
①update the model whenever the confidence of the target falls below athreshold.
②update the model whenever the difference between the confidence of thetarget and that of the background examples is below a threshold.
5.Ensemble post-processing:
①a loss function for bounding box majority voting and then extended it toincorporate tracker weights, trajectory continuity and removal of bad trackers
②a factorial hidden Markov model that considers the temporal smoothnessbetween frames.
文章来源:http://arxiv.org/abs/1504.06055
A tracking system usually worksby initializing the observation model with the given bounding box of the targetin the first frame. In each of the following frames, the motion model
firstgenerates candidate regions or proposals for testing based on the estimationfrom the previous frame. The candidate regions or proposals are fed into theobservation model to compute their probability of being the target. The onewith the highest probability
is then selected as the estimation result of thecurrent frame. Based on the output of the observation model, the model updaterdecides whether the observation model needs any update and, if needed, theupdate frequency. Finally, if there are multiple trackers,
the bounding boxesreturned by the trackers will be combined by the ensemble post-processor toobtain a more accurate estimate. This pipeline is illustrated in Fig.
Five constituent parts:
1. Motion Model: Based on theestimation from the previous frame, the motion model generates a set ofcandidate regions or bounding boxes which may contain the target
in the currentframe.
2.Feature Extractor: Thefeature extractor represents each candidate in the candidate set using somefeatures.
3.Observation Model: Theobservation model judges whether a candidate is the target based on thefeatures extracted from the candidate.
4.Model Updater: The modelupdater controls the strategy and frequency of updating the observation model. Ithas to strike a balance between model adaptation and drift.
5. Ensemble Post-processor:When a tracking system consists of multiple trackers, the ensemblepostprocessor takes the outputs of the constituent trackers and uses
the ensemblelearning approach to combine them into the final result.
Details of all these components
1.Motion Model :ParticleFilter Sliding
,Window Radius ,Sliding Window
2.Feature Extractor: RawGrayscale ,Raw Color , Haar-like Features, HOG ,HOG
+Raw Color
3.Observation Model:LogisticRegression ,Ridge Regression ,SVM ,Structured
Output SVM (SO-SVM)
4.Model Updater:
①update the model whenever the confidence of the target falls below athreshold.
②update the model whenever the difference between the confidence of thetarget and that of the background examples is below a threshold.
5.Ensemble post-processing:
①a loss function for bounding box majority voting and then extended it toincorporate tracker weights, trajectory continuity and removal of bad trackers
②a factorial hidden Markov model that considers the temporal smoothnessbetween frames.
文章来源:http://arxiv.org/abs/1504.06055
相关文章推荐
- 如何使用Visual Studio 2010在数据库中生成随机测试数据
- Visual Style中的shellstyle.dll文件修改方法
- Chrome Visual Studio 2005下的编译过程
- MSN Messenger 化繁为简(用 Visual Studio 2005 去掉 MSN 广告)
- Visual C++中Tab View的多种实现方法
- Visual Studio快速开发以及Visual Studio 2010新功能介绍
- C#中几个未知的Visual Studio编码技巧分享
- 微软 Visual Studio 2010官方下载地址给大家
- Visual Studio 2008中文版官方下载地址
- Visual C#类的定义及实现方法实例解析
- Web版彷 Visual Studio 2003 颜色选择器
- jquery1.4.2 for Visual studio 2010 模板文件
- Visual C#.Net 网络程序开发-Socket篇第1/2页
- 解决Visual Studio 2012 Update 4 RC启动调试失败的方案
- Visual Studio调试技巧汇总
- 积累Visual Studio 常用快捷键的动画演示
- visual studio 2012安装配置方法图文教程 附opencv配置教程
- Visual Studio中根据系统区分引用64位、32位DLL动态库文件的配置方法
- 在Visual Studio中用C++语言创建DLL动态链接库图文教程
- Visual Studio 2013更新内容简介