计算机视觉资源

Camera Calibration Links to toolboxes (mostly MATLAB) for camera calibration.

Paul Debevec. Modeling and Rendering Architecture from Photographs.

Marc Pollefeys, Tutorial on 3D Modeling from Images,, ECCV 2000,

Available here:  notes (12.1MB pdf)

Richard Szeliski NIPS 2004 Tutorial on Acquiring Detailed 3D Models From Images and Video,

Available here:  slides (37.6 MB, ppt)

Peter Corke did his thesis work on visual servoing for robot applications and has authored a robotics toolkit and vision toolkit for MATLAB.

local copy of thesis:  Corke thesis (4.36 MB, pdf)
robot toolkit:  robot.zip (568 KB, zip)
vision toolkit:  mv.zip (1.08 MB, zip)

P. D. Kovesi., MATLAB Functions for Computer Vision and Image Analysis.
School of Computer Science & Software Engineering, The University of Western Australia.
Available locally as a zip archive MatlabFns.zip (4.8 MB, updated 21 May 2005)

Philip Torr, among many other contributions, submitted a Structure and motion toolkit in Matlab to the MathSoft File Exhange.
Local copy here: torrsam.zip (2.4 MB, zip).

（1）微软公司的文献：http://research.microsoft.com/research/pubs

（2）微软亚洲研究院：http://research.microsoft.com/asia/，值得关注Harry Shum, Jian Sun, Steven Lin, Long Quan(兼职HKUST)etc.

（3）瑞典隆德大学数学系视觉组：http://www.maths.lth.se/matematiklth/personal/andersp/

  感觉国外搞视觉的好多是数学系出身，大约做计算机视觉对数学要求很高吧。

（4）澳大利亚国立大学：http://users.rsise.anu.edu.au/~hartley/

（5）美国北卡大学：http://www.cs.unc.edu/~marc/

（6）加州大学伯克利分校David A. Forsyth：http://www.cs.berkeley.edu/~daf/

（7）CMU的视觉组：http://www.cs.cmu.edu/~cil/vision.html

著名的有Tomasi, Kanade等，CMU不愧是美国计算机牛校，仅视觉就好猛。

（8）法国INRIA：http://www-sop.inria.fr/odyssee/team/

 由Olivier.Faugeras领衔的牛人众多。

（9）英国牛津的A.Zisserman：http://www.robots.ox.ac.uk/~az/

(10)比利时鲁汶大学的L.Van Gool： www.esat.kuleuven.ac.be/psi/visics/

nature,science上关于计算机视觉的一些原创文献

1、D. Marr; T. Poggio.Cooperative Computation of Stereo Disparity.Science, New Series, Vol. 194, No. 4262. (Oct. 15, 1976), pp. 283-287. 这一篇是marr计算机视觉框架的开创性论文，到目前为止，计算机视觉基本上都在这个框架里做。

2、LONGUET-HIGGINS H C.A computer algorithm for reconstructing a scene from two projections[J].Nature,1981,293:133-135. 这一篇奠定了计算机视觉三维重构的基础，又称"八点算法”，导致计算机视觉三维重构热了20多年。

3、H. Bülthoff*, J. Little & T. Poggio.A parallel algorithm for real-time computation of optical flow.Nature 337, 549 - 553 (09 February 1989)
链接：http://www.nature.com/nature/journal/v337/n6207/abs/337549a0.html，光流实时并行算法的原始创新。

4、Hurlbert, A., and Poggio, T. 1986. Visual information: Do computers need attention?Nature 321(12).

5、Dov Sagi* & Bela Julesz.Enhanced detection in the aperture of focal attention during simple discrimination tasks.Nature 321, 693 - 695 (12 June 1986)

6、Gad Geiger; Tomaso Poggio.Science, New Series, Vol. 190, No. 4213. (Oct. 31, 1975), pp. 479-480.

7.Gad Geiger; Tomaso Poggio.The Müller-Lyer Figure and the Fly.Science, New Series, Vol. 190, No. 4213. (Oct. 31, 1975), pp. 479-480.
8.P. Sinha and T. Poggio.Role of Learning in Three-dimensional Form Perception," . Nature, Vol. 384, No. 6608, 460-463, 1996.
9.Hubel DH,Wiesel TN.Cells sensitive to binocular depth in area 18 of the macaque monkey cortex.Nature,1970,225∶41～42 
10.Livingstone M and Hubel D.Segregation of form,color,movement and depth:Anatomy,physiology and perception.Science,1988,240∶740～-749.
被引用1372次，关于眼睛立体视觉机制的原创论文。
11.Poggio T. Computational Vision and Regularization Theory[J]. Nature(Lond), 1985, (3): 314～319.
12.T. Poggio; F. Girosi.Regularization Algorithms for Learning that are Equivalent to Multilayer
Networks.Science, New Series, Vol. 247, No. 4945. (Feb. 23, 1990), pp. 978-982. 关于等同于多层神经网络的正则化算法，可以参考的一篇2001年光学学报文章-----贾财潮; 戚飞虎等.从二维视图识别三维目标的多网络融合方法.光学学报，2001
13.Poggio T, Edelman S. A network that learns to recognize three-dimensional objects .Nature, 1990, 343(6255) :263~266.

14.H. K. Nishihara & T. Poggio.HIDDEN CUES IN RANDOM LINE STEREOGRAMS. Nature, 300, 347-349,1982.

15. W. Vanduffel et. alExtracting the third dimension from motion Differences in Human and monkey intraparietal cortex.Extracting 3D from motion: Differences in human and monkey intraparietal cortex. Science, 298, 413–415 被引用136次。比较了猴子和人是怎样用双眼线索来的到一个移动物体的三维结构的。这个小组用功能核磁共振成像手段，在人和猴子在观看连接的线旋转形成三维形状物体时，分别跟踪了大脑颞叶、枕叶和顶叶部的反应。他们发现，人和猴子的颞叶和枕叶两个部位的反应非常相似，但是人在顶叶皮层中表现出额外的活动，这可能是随人类形成了使用精密工具等技巧演化而来的(引自化石网作者的精彩评述：http://www.uua.cn/Discovery/show-7396-1.html）