计算机视觉：算法与应用概览

4星 · 超过85%的资源需积分: 10 29 浏览量更新于2024-07-21 收藏 22.97MB PDF 举报

"《计算机视觉_算法与应用》是一本图像处理的经典著作，作者Richard Szeliski。这本书涵盖了计算机视觉领域的多个核心主题，包括图像形成、图像处理、特征检测与匹配、分割、基于特征的对齐、结构从运动、稠密运动估计、图像拼接、计算摄影、立体对应、3D形状与外观建模、基于图像的渲染以及识别等。" 本文将深入探讨计算机视觉领域的一些关键知识点。 1. **图像形成**：这是理解计算机视觉的第一步，它涉及光如何与物体相互作用并形成图像。这部分内容会讨论光学成像原理，包括相机模型、曝光控制、像素阵列和色彩理论。 2. **图像处理**：这部分讲解了如何对数字图像进行操作以提取有用信息或改善图像质量。内容可能包括滤波、增强、噪声去除、直方图均衡化等技术。 3. **特征检测与匹配**：特征是图像中的重要点、线或区域，它们在视觉识别中起到关键作用。特征检测包括角点检测、边缘检测等，而特征匹配则是找出不同图像间的相似特征，常用于图像配准和三维重建。 4. **分割**：图像分割是将图像分成具有不同属性的区域，有助于识别物体和理解场景。方法包括阈值分割、区域生长、水平集、聚类等。 5. **基于特征的对齐**：通过匹配特征来对图像进行精确对齐，这对于比较和融合多视角图像至关重要，例如在全景图像创建中。 6. **结构从运动**：通过分析物体在不同时间的二维投影，恢复其三维结构。这涉及到光流估计、运动分析和几何解算。 7. **稠密运动估计**：不仅关注特征点的运动，而是估计图像中每个像素的运动，常用于视频分析和运动重建。 8. **图像拼接**：利用图像对齐和无缝拼接技术，可以创建广角或全景图像，扩展视觉视野。 9. **计算摄影**：利用计算机技术改变或增强传统摄影的视觉效果，如高动态范围（HDR）图像、光照建模等。 10. **立体对应**：在两个或多个视图中寻找对应点，以计算深度信息，是实现3D视觉和深度感知的关键。 11. **3D形状与外观建模**：通过图像数据重建物体的三维几何形状和表面属性，应用于虚拟现实、动画和产品设计等领域。 12. **基于图像的渲染**：利用一组图像作为输入，生成新的视图，用于虚拟漫游和图像合成。 13. **识别**：识别图像中的对象、场景、行为等，是计算机视觉的最终目标之一，涉及模式识别、机器学习和深度学习技术。以上各章节详细介绍了计算机视觉的核心算法和应用，为读者提供了深入了解和实践该领域的坚实基础。书中可能还包含实际案例、实验和练习，帮助读者将理论知识转化为实际技能。

xvi Computer Vision: Algorithms and Applications (September 25, 2009 draft)

The book is also suitable for teaching graduate-level courses in computer vision (by delving into

the more demanding application and algorithmic areas), and as a general reference to fundamental

techniques and recent research literature. To this end, I have attempted wherever possible to at least

cite the newest research in each sub-ﬁeld, even if the technical details are too complex to cover in

the book itself.

In teaching our courses, we have found it useful for the students to attempt a number of small

implementation projects, which often build on one another, in order to get them used to working

with real-world images and the challenges that these present. The students are then asked to choose

an individual topic for each of their small group ﬁnal projects. (Sometimes these projects even turn

into conference papers!) The exercises at the end of each chapter contain numerous suggestions

for both smaller mid-term projects, as well as more open-ended problems whose solution is still

an active research area. Wherever possible, I encourage students to try their algorithms on their

own personal photographs, since this better motivates them, often leads to creative variants on the

problems, and better acquaints them with the variety and complexity of real-world imagery.

In formulating and solving computer vision problems, I have often found it useful to draw

inspiration from three different high-level approaches:

1. Scientiﬁc: build detailed models of the image formation process and develop mathematical

techniques to invert these in order to recover the quantities of interest (where necessary,

making simplifying assumption to make the mathematics more tractable).

2. Statistical: use probabilistic models to quantify the (prior) likelihood of your unknowns and

the noisy measurement processes that produce the input images, then infer the best possible

estimates of your desired quantities and analyze their resulting uncertainties. The inference

algorithms used are often closely related to the optimization techniques used to invert the

(scientiﬁc) image formation processes.

3. Engineering: develop techniques that are simple to describe and implement, but that are

also known to work well in practice. Test these techniques to understand their limitation and

failure modes, as well as their expected computational costs (run-time performance).

These three approaches build on each other and are used throughout the book.

My personal research and development philosophy (and hence the exercises in the book) have

a strong emphasis on testing algorithms. It’s too easy in computer vision to develop an algorithm

that does something plausible on a few images rather than something correct. The best way to

validate your algorithms is to use a three part strategy.

First, test your algorithm on clean synthetic data, for which the exact results are known. Sec-

ond, add noise to data, and evaluate how the performance degrades as a function of noise level.

Finally, test the algorithm on real-world data, preferably drawn from a widely variable source,

Preface xvii

such as photos found on the Internet. Only then can you truly know if your algorithm can deal

with real-world complexity (i.e., images that do not ﬁt some simpliﬁed model or assumptions).

In order to help students in this process, this books comes with a large amount of supple-

mentary material, which can be found on the book Web site http://research.microsoft.

com/

szeliski/Book [ Note: ﬁx URL if necessary ]. This material, which is described in Ap-

pendix C, includes:

• Pointers to commonly used data sets for the problems, which can be found on the Inter-

net. [ Note: (aspirational): actual datasets and results that I have run through algorithms

described in the book and/or exercises ]

• Pointers to software libraries, which can help students get started with basic tasks such as

reading/writing images or creating and manipulating images. Some of these libraries also

contain implementations of a wide variety of computer vision algorithms, which can enable

you to tackle more ambitious projects (with your instructor’s consent, of course :-).

• Slide sets corresponding to the material covered in this book. (Until these sets are ready, your

best bet is to look at the slides from the courses we have taught at the University of Washing-

ton, such as http://www.cs.washington.edu/education/courses/cse576/08sp/.

In the meantime, I will provide the images and ﬁgures used in the book.)

• A BibTeX bibliography of the papers cited in this book.

The latter two resources may be of more interest to instructors and researchers publishing new

papers in this ﬁeld, but they will probably come in handy even with regular students.

Acknowledgements

I would like to gratefully acknowledge all of the people whose passion for research and inquiry as

well as encouragement have helped me write this book.

Steve Zucker at McGill University ﬁrst introduced me to computer vision, taught all of his

students to question and debate research results and techniques, and encouraged me to pursue a

graduate career in this area.

Takeo Kanade and Geoff Hinton, my Ph. D. thesis advisors at Carnegie Mellon University,

taught me the fundamentals of good research, writing, and presentation. They ﬁred up my interest

in visual processing, 3D modeling, and statistical methods, while Larry Matthies introduced me to

Kalman ﬁltering and stereo matching.

Demetri Terzopoulos was my mentor at my ﬁrst industrial research job and taught me the ropes

of successful publishing. Yvan Leclerc and Pascal Fua, colleagues from my brief interlude at SRI

International, gave me new perspectives on alternative approaches to computer vision.

xviii Computer Vision: Algorithms and Applications (September 25, 2009 draft)

During my six years of research at Digital Equipment Corporation’s Cambridge Research Lab,

I was fortunate to work with a great set of colleagues, including Ingrid Carlbom, Gudrun Klinker,

Keith Waters, Richard Weiss, and St

ephane Lavall

ee, as well as to supervise the ﬁrst of a long string

of outstanding summer interns, including David Tonnessen, Sing Bing Kang, James Coughlan, and

Harry Shum. This is also where I began my long-term collaboration with Daniel Scharstein (now

at Middlebury College).

At Microsoft Research, I’ve had the outstanding fortune to work with some of the world’s best

researchers in computer vision and computer graphics, including Michael Cohen, Hugues Hoppe,

Stephen Gortler, Steve Shafer, Matthew Turk, Harry Shum, Phil Torr, Antonio Criminisi, Ramin

Zabih, Shai Avidan, Sing Bing Kang, Matt Uyttendaele, Larry Zitnick, Richard Hartley, Simon

Winder, Drew Steedly, Dani Lischinski, Matthew Brown, Simon Baker, Eric Stollnitz, Johannes

Kopf, and Michael Goesele. I was also lucky to have as interns such great students as Polina

Golland, Simon Baker, Mei Han, Arno Sch

odl, Ron Dror, Ashley Eden, Jinxiang Chai, Rahul

Swaminathan, Yanghai Tsin, Sam Hasinoff, Anat Levin, Matthew Brown, Vaibhav Vaish, Jan-

Michael Frahm, James Diebel, Ce Liu, Josef Sivic, Neel Joshi, Sudipta Sinha, Zeev Farbman,

Rahul Garg, and Tim Cho.

While working at Microsoft, I’ve also had the opportunity to collaborate with wonderful col-

leagues at the University of Washington, where I hold an Afﬁliate Professor appointment. I’m

indebted to David Salesin, who ﬁrst encouraged me to get involved with the research going on at

UW, my long-time collaborators Brian Curless, Steve Seitz, Maneesh Agrawala, Sameer Agarwal,

and Yasu Furukawa, as well as the student’s I’ve had the privilege to supervise and interact with,

including Fr

ederic Pighin, Yung-Yu Chuang, Colin Zheng, Aseem Agarwala, Noah Snavely, Rahul

Garg, and Ryan Kaminsky. In particular, as I mentioned at the beginning of this preface, this book

owes its inception to the vision course that Steve Seitz invited me to co-teach, as well as to Steve’s

encouragement, course notes, and editorial input.

I’m also grateful to the many other computer vision researchers who have given me so many

constructive suggestions about the book, including Sing Bing Kang, Daniel Scharstein, Simon

Baker, Bill Freeman, Richard Hartley, Svetlana Lazebnik, Alyosha Efros, Bill Triggs, Noah Snavely,

Bruce Maxwell, Jana Ko

seck

a, Matthew Turk, Eero Simoncelli, Tomaso Poggio, Theo Pavlidis,

Baba Vemuri, Nando de Freitas, Chuck Dyer, Song Yi, Falk Schubert, Roman Pﬂugfelder, Sammy

Rogmans, Klaus Strobel, Shanmuganathan, Ronald Mallet, and add your name here. [ Note: See

LaTeX source (commented out) for list of other potential per-chapter reviewers. ]

If you have any suggestions for improving the book, please send me an e-mail, as I would like to

keep the book as accurate, informative, and timely as possible. Keith Price’s Annotated Computer

Vision Bibliography

has proven invaluable in tracking down references and ﬁnding related work.

http://iris.usc.edu/Vision-Notes/bibliography/contents.html

剩余865页未读，继续阅读

dslgyx

粉丝: 2
资源: 6

计算机视觉：算法与应用概览

计算机视觉：算法与应用概览

计算机视觉：算法与应用解析

计算机视觉：算法与应用详解

计算机视觉_算法与应用_英文原版.zip

计算机视觉_算法与应用（Computer Vision Algorithms and Applications）

计算机视觉 - 算法与应用_中文

计算机视觉 - 算法与应用_英文

计算机视觉——算法与应用

计算机视觉-算法与应用.pdf

计算机视觉：算法与应用【中文】

最新资源