资源描述
,单击此处编辑母版标题样式,单击此处编辑母版文本样式,第二级,第三级,第四级,第五级,*,/47,计算机视觉,Computer Vision,艾海舟,200,5,年,5,月,16,日,Outline,助教,教材与参考书,Web sites,FTP sources,Tools(Intel,OpenCV,IPL,),Demo,相关学科与相关课程的联系,Overview,Introduction,:,Forsyths introduction on CV,教材,英文影印版:,DA Forsyth,and J.Ponce,Computer Vision:A Modern Approach,Prentice Hall.1st edition(August 14,2002);,Contents,http:/www.cs.berkeley.edu/daf/book.html,清华大学出版社,中文翻译版:林学言,王宏 等,,计算机视觉:一种现代的方法,,,2004,年,6,月;,电子工业出版社,参考书,马颂德,张正友,,计算机视觉,,科学出版社,北京,,1998,。,R.Jain,R.,Kasturi,and B.G.,Schunck,Machine Vision,McGraw-Hill companies,Inc.,机械工业出版社,,2003.8,。,L.G.Shapiro and G.C.Stockman,Computer Vision,Prentice Hall Inc,2001.,M.,Sonka,V.,Hlavac,and R.Boyle,Image processing,analysis,and machine vision,Chapman&Hall Computing,London,2nd Edition,Brooks/Cole Publishing,2002.(,影印,),图像处理、分析与机器视觉,人民邮电出版社,M.,Sonka,V.,Hlavac,and R.Boyle,(,艾海舟、武勃 等译,),图像处理、分析与机器视觉,,人民邮电出版社,2003.9,。,目录,Web sites,Google,search computer vision,Computer vision homepage,Computer vision online,Computer vision source codes,Computer vision test data,Computer vision.,Paper search http:/,FTP source,我的课程网站,ftp:,User:,内容,数字图象处理(本科生课),计算机视觉专题(图像与视觉计算)(研究生课),-,计算机视觉的资料见,books,专家系统(研究生课,已停),Tools,Intel,OpenCV,IPL,Camera calibration(Zhang,Zhengyous,method),Face detection(a variation of Violas),Motion analysis and object tracking,Optical flow,Lucas-,Kanade,algorithm,Estimators,Kalman,Condensation,.,demo,Face detection,Object contour tracking,Motion object detection and tracking,ASM/AAM shape modeling,Perceptual interface:smart room,Visual surveillance,Robotics vision,3D modeling,face animation,相关学科与相关课程的联系,数字图象处理,计算机视觉,模式识别,机器视觉,计算机图形学,线性代数,集合论,高级语言程序设计,数据结构,先后顺序,重叠量反应相关程度,基础知识,计算机视觉专题,(,图,象与视觉计算),高等代数,最优化方法,。,信号与系统,计算几何,Overview(1),计算机视觉的几何学基础,摄像机模型,单摄像机,(pinhole model/perspective transformation),双摄像机,(,epipolar,geometry:fundamental matrix/essential matrix),三摄像机及更多,(multi-view geometry),运动估计,对应点问题(,correspondence problem,),光流计算方法,刚体运动参数估计(,minimal projective reconstruction,),2-view,7 points in correspondence;(,Faugeras,),3-view,6 points in correspondence;(,Quan,Long),3-view,8 points with one missing in one of the three view.(,Quan,Long),几何重构(,Geometry reconstruction,),立体视觉,(stereo vision),Shape from X(shading/motion/texture/contour/focus/de-focus/.),Overview(2),计算机视觉的物理学基础,摄像机及其成像过程,视点、光源、空间中光线、表面处的光线,.,明暗,shading,、阴影,shadow,光学,/,色彩,light/color,辐射学,辐照率,radiometry,物体表面特性,漫反射表面(各向同性),Lambertian,surface,BDRF(bi-directional reflectance distribution,fucntion,),Overview(3),计算机视觉的图像模型基础,摄像机模型及其校准,内参数、外参数,图像特征,边缘、角点、轮廓、纹理、形状,图像序列特征,(,运动,),对应点、光流,Overview(4),计算机视觉的信号处理层次,低层视觉处理,单图像:滤波,/,边缘检测,/,纹理,多图像:几何,/,立体,/,从运动恢复仿射或透视结构,affine/perspective structure from motion,中层视觉处理,聚类分割,/,拟合线条、曲线、轮廓,clustering for segmentation,fitting line,基于概率方法的聚类分割,/,拟合,跟踪,tracking,高层视觉处理,匹配,模式分类,/,关联模型识别,pattern classification/aspect graph recognition,应用,距离数据(,range data,),/,图像数据检索,/,基于图像的绘制,Overview(5),计算机视觉的数学基础,摄影几何、微分几何,概率统计与随机过程,数值计算与优化方法,机器学习,计算机视觉的基本的分析工具和数学模型,Signal processing approach:FFT,filtering,wavelets,Subspace approach:PCA,LDA,ICA,Bayesian inference approach:EM,Condensation/SIS/,MCMC,.,Machine learning approach:SVM/Kernel machine,Boosting/,Adaboost,NN/Regression,HMM,BN/DBN,Gibbs,MRF,Overview(6),计算机视觉问题的特点,高维数据的本质维数很低,使得模型化成为可能。,High dimensional image/video data lie in a very low dimensional manifold.,问题的不适定性,缺少约束的逆问题,优化问题,Introduction,Forsyths introduction on CV,
展开阅读全文