本文主要是介绍基于图像特征的视觉跟踪系统（Feature-based visual tracking systems）--一篇Visual Tracking Benchmark (2013)综述，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
reference:http://blog.csdn.net/anshan1984/article/details/8866455
最近读到一篇关于视觉跟踪的综述性文章，“Evaluation of Interest Point Detectors and Feature Descriptors for Visual Tracking”，发表在2011年3月International Journal of Computer Vision上。作者非常详尽的评估了2010年之前的图像检测子及图像描述子（检测子包括Harris Corner、Shi-Tomasi' feature、DoG、Fast Hessian、FAST、CenSurE；描述子包括Image Patch、SIFT、SURF、keypoint classification with Randomized Trees、keypoint classification with Randomized Ferns），以及它们用于视觉跟踪时的各项性能，并且提供精心设计的数据集http://ilab.cs.ucsb.edu/tracking_dataset_ijcv/。
视觉跟踪是许多应用的核心部分，包括视觉里程计（visual odomety）、基于视觉的同步定位与地图创建（visual Simultaneous Localization and Mapping)以及增强视觉(Augmented Reality)。这些应用的需求不同，但是都需要鲁棒、精确、快速实时的底层视觉跟踪方法。光流法(optical flow)与基于特征的跟踪方法(feature-basedvisual tracking)是视觉跟踪的两种主要方法，而后者更为常用。
文中归纳了截止2010年已有的基于特征的视觉跟踪系统，已经算非常详尽。
论文下载地址：cs.iupui.edu/~tuceryan/pdf-repository/Gauglitz2011.pdf
Visual Tracking 领域最新paper与code
（2016-csdn blog:http://blog.csdn.net/cyh_24/article/details/51592156）
最近在研究 tracking，所以总结了一些较新的 tracking 相关的论文和源码。
希望能够为刚进入这个领域的同学节省一些时间。
如您有其他优秀的paper或者code，欢迎在回复中留言~谢谢！
Learning Multi-Domain Convolutional Neural Networks for Visual Tracking (VOT2015 冠军)
author: Hyeonseob Nam, Bohyung Han
homepage: http://cvlab.postech.ac.kr/research/mdnet/
code: https://github.com/HyeonseobNam/MDNet
阅读笔记: http://blog.csdn.net/cyh_24/article/details/51590174
Learning to Track: Online Multi-Object Tracking by Decision Making (ICCV 2015)
author: Yu Xiang, Alexandre Alahi, Silvio Savarese
slides: https://yuxng.github.io/Xiang_ICCV15_12162015.pdf
code: https://github.com/yuxng/MDP_Tracking
Hierarchical Convolutional Features for Visual Tracking (ICCV 2015)
author: Chao Ma, Jia-Bin Huang, Xiaokang Yang, Ming-Husan Yang
project page: https://sites.google.com/site/jbhuang0604/publications/cf2
code: https://github.com/jbhuang0604/CF2
Robust Visual Tracking via Convolutional Networks without Training (2015)
author: Kaihua Zhang, Qingshan Liu, Yi Wu, and Ming-Hsuan Yang
code: http://kaihuazhang.net/CNT_matlab.rar
Transferring Rich Feature Hierarchies for Robust Visual Tracking (2015)
author: Naiyan Wang, Siyi Li, Abhinav Gupta, Dit-Yan Yeung
slides: http://valse.mmcheng.net/ftp/20150325/RVT.pptx
Understanding and Diagnosing Visual Tracking Systems (ICCV 2015)
author: Naiyan Wang, Jianping Shi, Dit-Yan Yeung, Jiaya Jia
project page: http://winsty.net/tracker_diagnose.html
code: http://120.52.72.43/winsty.net/c3pr90ntcsf0/diagnose/diagnose_code.zip
RATM: Recurrent Attentive Tracking Model (2015)
author: Samira Ebrahimi Kahou, Vincent Michalski, Roland Memisevic
code: https://github.com/saebrahimi/RATM
Visual Tracking with Fully Convolutional Networks (ICCV 2015)
author: Lijun Wang, Wanli Ouyang, Xiaogang Wang, Huchuan Lu
code: https://github.com/scott89/FCNT
Deep Tracking: Seeing Beyond Seeing Using Recurrent Neural Networks (AAAI 2016)
author: Peter Ondr úška and Ingmar Posner
code: https://github.com/pondruska/DeepTracking
Learning to Track at 100 FPS with Deep Regression Networks (2016)
author: David Held, Sebastian Thrun, Silvio Savarese
Online Multi-target Tracking using Recurrent Neural Networks (2016)
author: Anton Milan, Seyed Hamid Rezatofighi, Anthony Dick, Konrad Schindler, Ian Reid
code: https://bitbucket.org/amilan/rnntracking
Multi-Target Tracking by Discrete-Continuous Energy Minimization (2016)
author: A. Milan, K. Schindler, S. Roth
author homepage: http://www.milanton.de/
project page: http://www.milanton.de/dctracking/index.html
Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor (2015)
author: Wongun Choi
这篇关于基于图像特征的视觉跟踪系统（Feature-based visual tracking systems）--一篇Visual Tracking Benchmark (2013)综述的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
