Computer Vision

Fall 2009

Please note - specifics of this schedule are subject to change.

Lecture slides are posted in the column named “Lectures”.

F&P = Forsyth & Ponce

S&S = Shapiro & Stockman [See Blackboard-> Course Documents]

T&V = Trucco & Verri [See Blackboard-> Course Documents]

Dates	Topic	Reading and references	Of related interest	Lectures	Assignments
Thurs 8/27	Intro				Pset 0: out 8/27, due 9/7 Pset 0 images Part 2 code example solution Solutions given in class on 9/15
Tues 9/1	Features	Linear filters : F&P Chapter 7 sections 7.1, 7.2, 7.5, 7.6 [T&V Chapter 4] [S&S Chapter 5.3]		Linear filters I
Thurs 9/3		Matlab intro		Matlab tutorial (guest lecture, Yong Jae Lee)
Tues 9/8		Linear filters, edges: F&P Ch 8 [S&S Chapter 3]		Linear filters 2	Pset 1: out 9/8, due 9/21 Pset 1 images Seam carving page with video Class results
Thurs 9/10		Edges: F&P Ch 8 Binary images: [S&S Chapter 3]		Edge detection and binary image analysis
Tues 9/15		Texture: F&P 9.1 and 9.3	A Statistical Approach to Texture Classification from Single Images, by Manik Varma and Andrew Zisserman, International Journal of Computer Vision, 2005. When is Scene Identification Just Texture Recognition? by Laura Walker Renninger and Jitendra Malik, Vision Research, 2004. Alyosha Efros’s Texture Synthesis page, with links to non-parametric sampling method and image quilting	Texture
Thurs 9/17	Grouping and Fitting	Segmentation: F&P Ch 14	k-means applet demo Normalized Cuts and Image Segmentation, by Jianbo Shi and Jitendra Malik, PAMI 2000. Ncuts Matlab code Contour and Texture Analysis for Image Segmentation, by Malik et al. IJCV 2001.	Segmentation, clustering
Tues 9/22		Hough transform: F&P 15.1 [S&S pp. 304-310] Excerpt from Ballard & Brown	Hough Transform demo	Hough, voting	Pset 2: out 9/22, due 10/5 Solutions given out in class 10/13
Thurs 9/24		Deformable contours: [T&V p. 108-113] [S&S p. 489-495]		Deformable contours
Tues 9/29		Background modeling and background subtraction Read F&P 14.3, and Stauffer & Grimson paper: Adaptive Background Mixture Models for Real-Time Tracking, CVPR 1999.		Background models (guest lecture by Birgi Tamersoy)
Thurs 10/1	Cameras and Multiple views	Fundamentals of image formation Read F&P Chapter 1		Image formation (guest lecture by Jaechul Kim)
Tues 10/6		Fitting and multiple views: alignment and image warping		Alignment, warping
Thurs 10/8		Robust fitting Midterm review F&P Section 15.5, 15.5.2		Ransac
Tues 10/13	Midterm exam				Pset 3: out 10/13, due 10/27 Class results are posted here Solutions given in class 11/3
Thurs 10/15		Midterm solutions given in class
Tues 10/20	Multiple views	Epipolar geometry and stereo vision F&P sections 10.1.1-10.1.2 F&P sections 11.1-11.3 [T&V selected sections]	Epipolar geometry applet	Epipolar geometry, stereo
Thurs 10/22		Stereopsis, calibration	Video view interpolation, Zitnick et al. Microphone arrays as generalized cameras for integrated audio visual processing, O’Donovan and Duraiswami Body tracking, Demirdjian et al. Fundamental matrix song	Stereopsis, calibration
Tues 10/27		Local invariant features: detection and description Selected pages from: Ch 3: Visual Recognition: Local Features: Detection and Description K. Grauman and B. Leibe [p. 23-39] Local Invariant Feature Detectors: A Survey, T. Tuytelaars and K. Mikolajczyk, 2008. [p. 178-188, 0.216-220, p. 254-255]	Distinctive Image Features from Scale-Invariant Keypoints, David Lowe, IJCV 2004. SIFT demo software from David Lowe Oxford group’s software for interest point detection and descriptors VLFeat SIFT library from Andrea Vedaldi (C, and includes Matlab interfaces)	Invariant local features
Thurs 10/29	Recognition	Image indexing and bag-of-words models Ch 5: Visual Recognition: Visual Vocabularies. K. Grauman and B. Leibe [p. 62-69] Blackboard: bag of words model	Video Google: A Text Retrieval Approach to Object Matching in Videos, by J. Sivic and A. Zisserman, 2003.	Indexing, bag-of-words
Tues 11/3		Intro to recognition issues; Model-based recognition with alignment and voting F&P Sections 18.1, 18.3, 18.5 Pset3 solutions given out in class.	Astrometry.net Object recognition from local scale-invariant features, David Lowe, 1999.	Intro to recognition problem, Alignment-based approach
Thurs 11/5		Part-based models and spatial cues from local features Ch 7: Visual Recognition: Part-based Models. K. Grauman and B. Leibe. [p. 83-97]	Implicit shape model, Leibe et al., 2004. Pyramid match kernel, Grauman & Darrell, 2005. Spatial pyramid match kernel, Lazebnik et al. 2006. LIBPMK : pyramid match toolkit	Part-based models and spatial cues for categories	Pset 4: out 11/5, due 11/24 Solutions given in class 12/1
Tues 11/10		(Face) detection via classification on appearance windows F&P 22.1-22.2, 22.3.1-22.3.2 Rapid Object Detection using a Boosted Cascade of Simple Features, by P. Viola and M. Jones, 2001.	OpenCV Library, includes code for Viola-Jones face detector Automated Visual Recognition of Individual African Penguins, by Burghardt et al., 2004.	Face detection
Thurs 11/12		Support vector machines for object classification F&P 22.5	Histograms of Oriented Gradients for Human Detection, Dalal & Triggs, 2005. Code LIBSVM library for support vector machines Learning Gender with Support Faces, Moghaddam & Yang, 2002.	Classification with support vector machines
Tues 11/17		Shape matching	Face transformer, University of St. Andrews Breaking a visual CAPTCHA, Mori & Malik Matching with shape contexts, code, Belongie et al.	Shape matching
Thurs 11/19	Motion and Tracking	Motion and optical flow T&V 8.3, 8.4		Optical flow
Tues 11/24		Tracking: linear dynamics F&P 17.1-17.2.3, 17.3.1	Censusing bats, Infrared thermal video analysis of bats, Betke et al.	Tracking	Pset 5: out 11/24, due 12/4*
Tues 12/1		Tracking wrapup	Tracking people by learning their appearance, Ramanan et al. Condensation: Conditional Density Propagation for Visual Tracking, Isard and Blake; videos	Tracking, recap
Thurs 12/3	Exam review
12/14 Mon	Final exam 2-5 PM in JGB 2.218