上海交通大学:Hierarchical Convolutional Features for Visual Tracking(Online Object Tracking with Proposal Selection)

Hierarchical Convolutional Features for Visual Tracking Chao Ma, SJTU Jia-Bin Huang, UIUC Xiaokang Yang, SJTU Ming-Hsuan Yang, UC Merced
Hierarchical Convolutional Features for Visual Tracking Chao Ma,SJTU Jia-Bin Huang,UIUC Xiaokang Yang,SJTU Ming-Hsuan Yang,UC Merced

Hierarchical Convolutional features for visual racking What is visual tracking? How to do it? What is the novel point of this paper
Hierarchical Convolutional Features for Visual Tracking • What is visual tracking? • How to do it? • What is the Novel point of this paper?

Visual Tracking A typical scenario of visual tracking is to track an unknown target object, specified by a bounding box in the first frame #050 #080 #02
Visual Tracking • A typical scenario of visual tracking is to track an unknown target object, specified by a bounding box in the first frame

Visual tracking ng Method Tracking by binary Classifiers Visual tracking can be posed as a repeated detection problem in a local window. For each frame, a set of positive and negative training samples are collected for incrementally learning a discriminative classifier to separate a target from its backgrounds Sampling ambiguity Tracking by Correlation Filters Tracking methods based on correlation filters regress all the circular-shifted versions of input features to a target gaussian function and thus no hard-thresholded samples of target appearance are needed. Tracking by CNNs Visual representations are of great importance for object tracking
Visual Tracking Method • Tracking by Binary Classifiers. • Visual tracking can be posed as a repeated detection problem in a local window. For each frame, a set of positive and negative training samples are collected for incrementally learning a discriminative classifier to separate a target from its backgrounds. • Sampling ambiguity • Tracking by Correlation Filters. • Tracking methods based on correlation filters regress all the circular-shifted versions of input features to a target Gaussian function and thus no hard-thresholded samples of target appearance are needed. • Tracking by CNNs • Visual representations are of great importance for object tracking

Chao mas Work Learn correlation filters over multi-dimensional features in a way similar to existing methods The main differences lie in the use of learned CNN features rather than hand-crafted features Former CNn trackers all rely on positive and negative training samples and only exploit the features from the last layer. In contrast, our approach builds on adaptive correlation filters which regress the dense, circularly shifted samples with soft labels and effectivel alleviate sampling ambiguity
Chao Ma’s Work • Learn correlation filters over multi-dimensional features in a way similar to existing methods. The main differences lie in the use of learned CNN features rather than hand-crafted features • Former CNN trackers all rely on positive and negative training samples and only exploit the features from the last layer. In contrast, our approach builds on adaptive correlation filters which regress the dense, circularly shifted samples with soft labels and effectively alleviate sampling ambiguity

Conv W Conv conv W Position in Estimated Cropped search Window Tracking Output Figure 3 Main steps of the proposed algorithm. Given an image, we first crop the search window centered at the estimated position in the previous frame. We use the third, fourth and fifth convolu- tional layers as our target representations. Each layer indexed by i is then convolved with the learned linear correlation filter w to generate a response map, whose location of the maximum value indicates the estimated target position. We search the multi-level response maps to infer the target location in a coarse-to-fine fash- ion

Algo orithm Use the convolutional feature maps from a cnn alex Net or VGG-Net to encode target appearance along with the cnn forward propagation, the semantical discrimination between objects from different categories is strengthened, as well as a gradual reduction of spatial resolution for precise localization Learn a discriminative classifier and estimate the translation of target objects by searching for the maximum value of correlation response map. Given the set of correlation response maps we hierarchically infer the target translation of each layer
Algorithm • Use the convolutional feature maps from a CNN, AlexNet or VGG-Net to encode target appearance. Along with the CNN forward propagation, the semantical discrimination between objects from different categories is strengthened, as well as a gradual reduction of spatial resolution for precise localization. • Learn a discriminative classifier and estimate the translation of target objects by searching for the maximum value of correlation response map. • Given the set of correlation response maps , we hierarchically infer the target translation of each layer

Implementation details Experimental Validations
•Implementation Details • Experimental Validations

Conclusion Combine cnn and correlation filters together. Use not only the last layer but also the early layers of cnn to achieve better performance Extensive experimental results show that the proposed algorithm performs favorably against the state-of-the -art methods in terms of accuracy and robustness
Conclusion • Combine CNN and Correlation Filters together. • Use not only the last layer but also the early layers of CNN to achieve better performance. • Extensive experimental results show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of • accuracy and robustness

Online obiect tracking with Proposal selection Reporter: Liu Cun Student i:115413910018 201605.03
Online Object Tracking with Proposal Selection Reporter : Liu Cun Student ID: 115413910018 2016.05.03
按次数下载不扣除下载券;
注册用户24小时内重复下载只扣除一次;
顺序:VIP每日次数-->可用次数-->下载券;
- 大连民族大学(大连民族学院):《工程管理信息系统》课程教学资源(PPT课件讲稿)第一章 工程信息管理概论(主讲:王楠楠).ppt
- 电子商务中的智能卡技术(PPT讲稿)Smart Card Technology in Electronic Commerce.ppt
- 大连民族大学(大连民族学院):《工程管理信息系统》课程教学资源(PPT课件讲稿)第二章 工程管理信息系统的开发.ppt
- 《管理信息系统》课程教学资源(PPT课件讲稿)第二章 管理信息系统概论.ppt
- 管理学院信息管理与信息系统专业必修课程教学大纲汇编.doc
- 《信息资源建设与组织》教学资源(PPT讲稿)主题标引.ppt
- 《信息系统分析与设计》课程教学资源(教学大纲).pdf
- 清华大学出版社:《现代微机原理及接口技术》课程教学课件(PPT讲稿)第四章 程序设计技巧(4.4)子程序与扩展子程序.ppt
- 清华大学出版社:《现代微机原理及接口技术》课程教学课件(PPT讲稿)第四章 程序设计技巧(4.1-4.2-4.3).ppt
- 清华大学出版社:《现代微机原理及接口技术》课程教学课件(PPT讲稿)硬指令和伪指令.ppt
- 清华大学出版社:《现代微机原理及接口技术》课程教学课件(PPT讲稿)第三章(3.2.5)控制转移类指令.ppt
- 清华大学出版社:《现代微机原理及接口技术》课程教学课件(PPT讲稿)第三章(3.2.3)位操作类指令.ppt
- 清华大学出版社:《现代微机原理及接口技术》课程教学课件(PPT讲稿)第三章(3.2.2)算术运算类指令.ppt
- 清华大学出版社:《现代微机原理及接口技术》课程教学课件(PPT讲稿)第三章(3.2)数据传送类指令.ppt
- 清华大学出版社:《现代微机原理及接口技术》课程教学课件(PPT讲稿)第三章(3.1)16位汇编程序设计概述.ppt
- 清华大学出版社:《现代微机原理及接口技术》课程教学课件(PPT讲稿)第11章 人机交互接口.ppt
- 清华大学出版社:《现代微机原理及接口技术》课程教学课件(PPT讲稿)第10章 数/模、模/数转换接口.ppt
- 清华大学出版社:《现代微机原理及接口技术》课程教学课件(PPT讲稿)第9章 常用可编程接口芯片及应用.ppt
- 清华大学出版社:《现代微机原理及接口技术》课程教学课件(PPT讲稿)第8章 DMA控制器及其应用.ppt
- 清华大学出版社:《现代微机原理及接口技术》课程教学课件(PPT讲稿)第7章 中断系统和中断控制器.ppt
- 《文献检索》课程教学资源(PPT讲稿)工具书检索与利用.ppt
- 西安电子科技大学:《信息管理学》课程教学资源(PPT课件讲稿)第5章 信息系统.ppt
- 信息描述绪论(PPT课件讲稿)information description.ppt
- 《系统工程》课程教学资源(PPT课件讲稿)第三章系统模型与模型化.ppt
- 海南大学:《管理信息系统》课程教学资源(PPT课件讲稿)第十章 决策支持系统(主讲:陈明锐).ppt
- 《管理信息系统》课程教学资源(PPT课件讲稿)第2章 信息管理的基本原理.ppt
- 《地理信息系统原理与方法》课程教学资源(PPT课件讲稿)空间数据管理.ppt
- 《管理信息系统》课程教学资源(PPT课件讲稿)第十二章 电子商务.ppt
- 《信息检索与利用》课程教学资源(PPT课件讲稿)第二章 信息检索基础知识.ppt
- 《信息系统》课程教学资源(PPT课件)第七章 信息系统的安全与运行管理.ppt
- 北京师范大学:《管理信息系统》课程PPT教学课件(教育方向)第6讲 管理信息系统的项目管理.ppsx
- 《管理信息系统的系统》课程教学资源(PPT课件讲稿)第八章 系统实施.ppt
- 北京师范大学:《管理信息系统》课程PPT教学课件(教育方向)第1讲 管理信息系统概念(主讲:马秀麟).ppsx
- 大连民族大学(大连民族学院):《工程管理信息系统》课程教学资源(PPT课件讲稿)第三章 系统规划.ppt
- 北京师范大学:《管理信息系统》课程PPT教学课件(教育方向)第2讲 管理信息系统的技术基础.ppsx
- 上海海事大学:《Management Information System》课程PPT教学课件(英文)Chapter 1 Business Information Systems in Your Career.ppt
- 北京大学:传统图书馆数字图书馆复合图书馆及其发展(PPT讲稿,信息管理系:刘兹恒).ppt
- 海南大学:《管理信息系统》课程教学资源(PPT课件讲稿)第三章 管理信息系统的技术基础.ppt
- 海南大学:《管理信息系统》课程教学资源(PPT课件讲稿)第六章 管理信息系统的系统设计.ppt
- 西安电子科技大学:《信息管理学》课程教学资源(PPT课件讲稿)第1章 绪论(主讲:赵捧未).ppt