Resources in Visual Tracking

这个应该是目前最全的Tracking相关的文章了

一、Surveyand benchmark:

1.      PAMI2014:VisualTracking_ An Experimental Survey,代码:http://alov300pp.joomlafree.it/trackers-resource.html

2.      CVPR2013:Online Object Tracking: A Benchmark(需FQ)

3.      SignalProcessing  2011:Video Tracking Theory andPractice

4.      ACCV2006:Tutorials-Advances in VisualTracking:中文:视觉跟踪的进展

5.      Evaluationof an online learning approach for robust object tracking

二、研究团体:

1.      Universityof California at Merced:Ming-HsuanYang视觉跟踪当之无愧第一人,后面的人基本上都和气其有合作关系,他引近9000

PublicationsPAMI:6,CVPR:26,ECCV:17,BMCV:6,NIPS:6,IJCV:3,ACCV:3

代表作:RobustVisual Tracking via Consistent Low-Rank Sparse Learning

FCT,IJCV2014:FastCompressive Tracking

RST,PAMI2014:RobustSuperpixel Tracking; SPT,ICCV2011, Superpixeltracking

SVD,TIP2014:LearningStructured Visual Dictionary for Object Tracking

ECCV2014: SpatiotemporalBackground Subtraction Using Minimum Spanning Tree and Optical Flow

PAMI2011:RobustObject Tracking with Online Multiple Instance Learning

MIT,CVPR2009: Visualtracking with online multiple instance learning

IJCV2008: IncrementalLearning for Robust Visual Tracking

2.      SeoulNational University Professor:KyoungMuLee2013年在PAMI上发表5篇,至今无人能及

文献列表PAMI:13,CVPR:30,ECCV:12,ICCV:8,PR:4

PAMI2014:A GeometricParticle Filter for Template-Based Visual Tracking

ECCV2014: Robust Visual Tracking with Double Bounding Box Model

PAMI2013:HighlyNonrigid Object Tracking via Patch-based Dynamic Appearance Modeling

CVPR2014: Interval Tracker: Tracking by Interval Analysis

CVPR2013: MinimumUncertainty Gap for Robust Visual Tracking

CVPR2012:RobustVisual Tracking using Autoregressive Hidden Markov Model

VTS,ICCV2011:Tracking by Sampling Trackers.

VTD,CVPR2010: VisualTracking Decomposition

TST,ICCV2011:Tracking by sampling trackers

3.      TempleUniversity,凌海滨

Publication List PMAI:4,CVPR:19,ICCV:17,ECCV:5,TIP:9

CVPR2014:Multi-targetTracking with Motion Context in Tenor Power Iteration

ECCV2014:TransferLearning Based Visual Tracking with Gaussian Process Regression

ICCV2013:Findingthe Best from the Second Bests - Inhibiting Subjective Bias in Evaluation ofVisual Tracking Algorithms

CVPR2013: Multi-targetTracking by Rank-1 Tensor Approximation

CVPR2012:RealTime Robust L1 Tracker Using Accelerated Proximal Gradient Approach

TIP2012: Real-timeProbabilistic Covariance Tracking with Efficient Model Update

ICCV2011: BlurredTarget Tracking by Blur-driven Tracker

PAMI2011ICCV2009: RobustVisual Tracking and Vehicle Classification via Sparse Representation

ICCV2011:RobustVisual Tracking using L1 Minimization

L1O,CVPR2011: Minimumerror bounded efficient l1 tracker with occlusion detection

L1T, ICCV2009:Robustvisual tracking using l1 minimization

4.      HongKong Polytechnic University AssociateProfessor: Lei Zhang

PapersPAMI:2,CVPR:18,ICCV:14,ECCV:12,ICPR:6,PR:28,TIP:4

STC,ECCV2014: FastTracking via Dense Spatio-Temporal Context Learning

FCT,PAMI2014,ECCV2012:Fast CompressiveTracking, Minghsuan Yang

IETComputer Vision2012:Scale and Orientation Adaptive Mean Shift Tracking

IJPRAI2009:RobustObject Tracking using Joint Color-Texture Histogram

5.      大连理工大学教授 卢湖川国内追踪领域第一人

CVPR2014:VisualTracking via Probability Continuous Outlier Model

TIP2014:VisualTracking via Discriminative Sparse Similarity Map

TIP2014: RobustSuperpixel Tracking

TIP2014: RobustObject Tracking via Sparse Collaborative Appearance Model

CVPR2013: LeastSoft-threshold Squares Tracking, MinghsuanYang

TIP2013:Online Object Trackingwith Sparse Prototypes, Minghsuan Yang

SignalProcessing Letters2013: Graph-RegularizedSaliency Detection With Convex-Hull-Based Center Prior

SignalProcessing2013: On-line LearningParts-based Representation via Incremental Orthogonal Projective Non-negativeMatrix Factorization

CVPR2012:RobustObject Tracking viaSparsity-based Collaborative Model, MinghsuanYang

CVPR2012:VisualTracking via Adaptive Structural Local Sparse Appearance Model, MinghsuanYang

SignalProcessing Letters 2012:Object tracking via 2DPCA and L1-regularization

IETImage Processing 2012:Visual Tracking via Bag of Features

ICPR2012:Superpixel Level Object Recognition Under Local Learning Framework

ICPR2012: Fragment-BasedTracking Using Online Multiple Kernel Learning

ICPR2012: ObjectTracking Based On Local Learning

ICPR2012: ObjectTracking with L2_RLS

ICPR2011:ComplementaryVisual Tracking

FG2011:OnlineMultiple Support Instance Tracking

SignalProcessing2010: A novel methodfor gaze tracking by local pattern model and support vector regressor

ACCV2010: OnFeature Combination and Multiple Kernel Learning for Object Tracking

ACCV: RobustTracking Based on Pixel-wise Spatial Pyramid and Biased Fusion

ACCV2010: HumanTracking by Multiple Kernel Boosting with Locality Affinity Constraints

ICCV2011:SuperpixelTracking, Minghsuan Yang

ICPR2010: RobustTracking Based on Boosted Color Soft Segmentation and ICA-R

ICPR2010: IncrementalMPCA for Color Object Tracking

ICPR2010: Bagof Features Tracking

ICPR2008: GazeTracking By Binocular Vision and LBP Features

6.      南京信息工程大学教授,KaiHua Zhang

7.      OregonstateProfessor,Sinisa Todorovic由视频分割转向Tracking

CSL,CVPR2014: Multi-ObjectTracking via Constrained Sequential Labeling

CVPR2011:MultiobjectTracking as Maximum Weight Independent Set

8.      GrazUniversity of Technology, Austria,Horst Possegger博士

CVPR2014:OcclusionGeodesics for Online Multi-Object Tracking

CVPR2013: RobustReal-Time Tracking of Multiple Objects by Volumetric Mass Densities

9.      马里兰大学Zdenek Kalal博士

TLD,PAMI2011: Tracking-Learning-Detection

TIP2010: Face-TLD:Tracking-Learning-Detection Applied to Faces

ICPR2010:Forward-BackwardError: Automatic Detection of Tracking Failures

CVPR2010: P-N Learning:Bootstrapping Binary Classifiers by Structural Constraints

BMVC2008: Weighted Sampling forLarge-Scale Boosting

中文讲解:

TLD视觉跟踪算法

TLD源码深度分析

庖丁解牛TLD

TLD(Tracking-Learning-Detection)学习与源码理解

三、其他早期工作:

Tracking of a Non-Rigid ObjectviaPatch-based Dynamic Appearance Modeling and Adaptive Basin Hopping Monte CarloSampling

tracking-by-detection

粒子滤波演示与opencv代码

opencv学习笔记-入门(6)-camshift

Camshift算法原理及其Opencv实现

Camshift算法

CamShift算法,OpenCV实现1--Back Projection

目标跟踪学习笔记_2(particle filter初探1)

目标跟踪学习笔记_3(particle filter初探2)

目标跟踪学习笔记_4(particle filter初探3)

目标跟踪学习系列一:on-line boosting and vision 阅读

原文:http://blog.csdn.net/minstyrain/article/details/38640541

时间: 2024-12-10 09:32:20

Resources in Visual Tracking的相关文章

Correlation Filter in Visual Tracking系列二:Fast Visual Tracking via Dense Spatio-Temporal Context Learning 论文笔记

原文再续,书接一上回.话说上一次我们讲到了Correlation Filter类 tracker的老祖宗MOSSE,那么接下来就让我们看看如何对其进一步地优化改良.这次要谈的论文是我们国内Zhang Kaihua团队在ECCV 2014上发表的STC tracker:Fast Visual Tracking via Dense Spatio-Temporal Context Learning.相信做跟踪的人对他们团队应该是比较熟悉的了,如Compressive Tracking就是他们的杰作之一

Paper Reading: Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking

Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual TrackingECCV 2016  The key point of KCF is the ability to efficiently exploit available negative data by including all shifted versions of a training sample, in anthor w

论文笔记之:Learning Multi-Domain Convolutional Neural Networks for Visual Tracking

Learning Multi-Domain Convolutional Neural Networks for Visual Tracking CVPR 2016 本文提出了一种新的CNN 框架来处理跟踪问题.众所周知,CNN在很多视觉领域都是如鱼得水,唯独目标跟踪显得有点“慢热”,这主要是因为CNN的训练需要海量数据,纵然是在ImageNet 数据集上微调后的model 仍然不足以很好的表达要跟踪地物体,因为Tracking问题的特殊性,至于怎么特殊的,且听细细道来. 目标跟踪之所以很少被 C

论文笔记:目标追踪-CVPR2014-Adaptive Color Attributes for Real-time Visual Tracking

基于自适应颜色属性的目标追踪 Adaptive Color Attributes for Real-Time Visual Tracking 基于自适应颜色属性的实时视觉追踪 3月讲的第一篇论文,个人理解,存在非常多问题,欢迎交流! 这是CVPR2014年的文章. 名字翻译为基于自适应选择颜色属性的实时视觉跟踪.首先理解什么是Adaptive color attributes,文章中colorattributes把颜色分为11类,就是将RGB三种颜色细化为黑.蓝.棕.灰.绿.橙.粉.紫.红.白和

论文笔记之: Hierarchical Convolutional Features for Visual Tracking

Hierarchical Convolutional Features for Visual Tracking  ICCV 2015 摘要:跟卢湖川的那个文章一样,本文也是利用深度学习各个 layer 之间提取出来的不同特征进行跟踪.因为各个层次提出来的 feature 具有不同的特征.并且将各个层级的特征用现有的 correlation filter 进行编码物体的外观,我们在每一个层上寻找最佳响应来定位物体. 引言:老套路的讨论了现有的跟踪问题存在的挑战以及现有方法取得的一些进展,并且引出了

论文笔记之:Multiple Feature Fusion via Weighted Entropy for Visual Tracking

Multiple Feature Fusion via Weighted Entropy for Visual Tracking ICCV 2015 本文主要考虑的是一个多特征融合的问题.如何有效的进行加权融合,是一个需要解决的问题.本文提出一种新的 data-adaptive visual tracking approach 通过 weighted entropy 进行多特征融合.并非像许多方法所做的简单的链接在一起的方法,本文采用加权的 entropy 来评价目标状态和背景状态之间的区分性,

论文笔记:Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking

Parallel Tracking and Verifying: A Framework for Real-Time and High Accuracy Visual Tracking 本文目标在于 tracking performance 和 efficiency 之间达到一种平衡.将 tracking 过程分解为两个并行但是相互协作的部分: 一个用于快速的跟踪(fast tracking): 另一个用于准确的验证(accurate verification). 本文的 Motivation

Correlation Filter in Visual Tracking

涉及两篇论文:Visual Object Tracking using Adaptive Correlation Filters 和Fast Visual Tracking via Dense Spatio-Temporal Context Learning 可参考这位博主笔记:http://www.cnblogs.com/hanhuili/p/4266990.html 第一篇我说下自己的理解:训练时的输出都认为是高斯形状,因为这种形状符合PSR. 训练得到模板后开始跟踪,由输出继续按照新的规则

Adaptive Color Attributes for Real-Time Visual Tracking

下面显示了Adaptive Color Attributes for Real-Time Visual Tracking, http://www.cvl.isy.liu.se/research/objrec/visualtracking/colvistrack/index.html 代码在50个benchmark数据集上的试验结果.数据集地址http://www.cvl.isy.liu.se/research/objrec/visualtracking/colvistrack/index.htm