没有合适的资源?快使用搜索试试~ 我知道了~
首页Visual Object Recognition - Kristen Grauman, Bastian Leibe
Visual Object Recognition (Synthesis Lectures on Artificial Intelligence and Machine Learning) [Kristen Grauman, Bastian Leibe]
资源详情
资源评论
资源推荐
Visual Object Recogniti on
Kristen Grauman
University of Texas at Austin
Bastian Leibe
RWTH Aachen University
SYNTHESIS LECTURES ON COMPUTER
V
ISION # 1
Abstract
The visual recognition problem is central to computer vision research. From
robotics to information retrieval, many desir ed applications demand the ability to iden-
tify and localize categories, places, and objects. This tutorial overviews computer vision
algorithms for visual object recognition and image classification. We introduce primary
representations and learning approaches, with an emphasis on recent advances in the
field. The target audience consists of researchers or students working in AI, robotics,
or vision w ho would like to understand what methods and representations are available
for these problems. This lecture summarizes what is and isn’t possible to do reliably
today, and overviews key concepts that could be employed in systems requiring visual
categorization.
Keywords: More specifically, the topics we cover in detail within the above are:
global representations versus local descriptors; detection and description of local invari-
ant features; efficient algorithms for matching local features, including tree-based and
hashing-based search algorithms; visual vocabularies and bags-of-words; metho ds to ver-
ify geometric consistency according to parameterized geometric transformations; deal-
ing with outliers in correspondences, including RANSAC and the Generalized Hough
transform; window-based descriptors, including histograms of oriented gradients and
rectangular features; part-based models, including star grap h m odels and fully con-
nected constellations; pyramid match kernels; detection via slid ing windows; Hough
voting; Generalized distance transform; the Implicit Shape Model; and the Deformable
Part-based Model.
v
Contents
Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . v
1
Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
. . . . . . . . . . . . . . . . . . . . . . . . . 1
1.1 Overview. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .1
1.2 Challenges . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.3 The State of the Art . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2
Overview: Recognition of Specific Objects . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.1 Global Image Representations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.2 Local Feature Representations. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
3
Local Features: Detection and Description. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
3.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
3.2 Detection of Interest Points and Regions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
3.2.1 Keypoint Localization 13
3.2.2 Scale Invariant Region Detection 15
3.2.3 Affine Covariant Region Detection 21
3.2.4 Orientation Normalization 23
3.2.5 Summary of Local Detectors 23
3.3 Local Descriptors . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
3.3.1 The SIFT Descriptor 24
3.3.2 The SURF Detector/Descriptor 25
3.4 Concluding Remarks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
4
Matching Local Features . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
. . . . . . . . . . . . . . . . . . . . . 29
4.1 Efficient Similarity Search . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
4.1.1 Tree-based Algorithms 30
4.1.2 Hashing-based Algorithms and Binary Codes 33
剩余171页未读,继续阅读
a446123571
- 粉丝: 1
- 资源: 7
上传资源 快速赚钱
- 我的内容管理 收起
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
会员权益专享
最新资源
- zigbee-cluster-library-specification
- JSBSim Reference Manual
- c++校园超市商品信息管理系统课程设计说明书(含源代码) (2).pdf
- 建筑供配电系统相关课件.pptx
- 企业管理规章制度及管理模式.doc
- vb打开摄像头.doc
- 云计算-可信计算中认证协议改进方案.pdf
- [详细完整版]单片机编程4.ppt
- c语言常用算法.pdf
- c++经典程序代码大全.pdf
- 单片机数字时钟资料.doc
- 11项目管理前沿1.0.pptx
- 基于ssm的“魅力”繁峙宣传网站的设计与实现论文.doc
- 智慧交通综合解决方案.pptx
- 建筑防潮设计-PowerPointPresentati.pptx
- SPC统计过程控制程序.pptx
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功
评论0