processamento de imagem e visão

Instructors:

Jorge Salvador Marques	Lectures	email: jsm at isr.ist.utl.pt
João Paulo Costeira	Lab	email: jpc at isr.ist.utl.pt

Doubt sessions:

· Jorge Salvador Marques – monday (15h30-17h) and friday (14h-15h30) at north tower, 7th floor.

Students wishing to attend the doubt sessions should send an email message the day before the session, until 7p.m.

Goal

This course addresses the following question: 

how to extract meaningful information from images and video?

This is a key question in many contexts for example when we wish to equip a robot with sensing capabilities, when we wish to learn 3D models from multiple images, when we want to search for similar images in a large database or when we wish to perform the analysis of medical images to detect abnormal tissues.

Some of these problems are discussed in the course e.g., image enhancement, object segmentation, object recognition, motion analysis and 3D reconstruction, The course also provides a hands on approach to computer vision by involving the students in a challenging project.

Syllabus

	Chapter RS
1. Introduction Course presentation, geometric transformations, image formation.	1,2
2. Image processing Linear filtering, median filtering, pyramids.	3
3. Image restoration Aquisition model, probabilistic model, Markov random fields	-
4. Feature detection and matching Points, edges, lines	4
5. Segmentation Active contours, split and merge, graph cuts.	5
6. Motion analysis Image alignment, Lucas-Kanade method.	6,8
7. Recognition Face recognition instance recognition, category recognition	14
8. Video surveillance Motion segmentation, object tracking.	-
9. Structure from motion Two frame structure from motion, Factorization, bundle adjustment.	7

Text books & problems

• Richard Szeliski, Computer Vision: Algorithms and Applications, draft, 2009

(http://research.microsoft.com/en-us/um/people/szeliski/Book/)

• J. Marques, course notes 2006 [pdf] and slides . 0 1 2 3 4 5 6 7 8

• J. Marques, exercises of PIV, incomplete draft, 2009 [pdf]

Grading

Grading is based on a project (50%) and a written exam (50%).

Grading 2009/10

Previous exams:

exam1 0910 (solution)

Important dates:

project: software delivery: until 18 December.

report delivery: until 4 January

project discussion: until 6 de Janeiro

exams: 21 January at 9:00 and 5 February at 13:00 for all the courses

Suggested readings

Methods

C. Veenman, M. Reinders, E. Backer, Resolving motion correspondence for densely moving points, PAMI, 54-72, 2001. point tracking

E. Shechtman M. Irani, Matching local self-similarities across Images and videos, CVPR, 2007. Self-similarity

D. Lowe , Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 2004 SIFT features

K. Mikolajczyk, C. Schmid, Performance evaluation of local descriptors, IEEE Transactions on Pattern Analysis and Machine, 2005 image features

J. Pluim, J. Maintz, M. Viergever , Mutual-information-based registration of medical images: a survey, IEEE Transactions on Medical Imaging, 2003. alignment

W. Philips, A. Pižurica, J. Roerdink, E. Vansteenkiste, A. Wink, A Review of Wavelet Denoising in MRI and Ultrasound Brain Imaging, Current Medical Imaging Reviews, 247-260, 2006. denoising

S. Minut, G. Stockman: Interpolation snakes for border detection in ultrasound images, VISAPP, 297-305, 2006. elastic contours

R. Szeliski, Image Alignment and Stitching: a Tutorial, Technical Report, Microsoft, 2006. mosaicing

Applications

P. Viola, Jones, Robust real-time face detection, Int. J. Computer Vision, 137-154, 2004. face detection

Iddo Drori Daniel Cohen-Or Hezy Yeshurun, Fragment based image completion, ACM Transactions on Graphics (TOG), 2003, image completion

A. Yilmaz, O. Javed, M. Shah, Object tracking a survey, ACM Computing Surveys (CSUR), 2006 object tracking

L. Fei-Fei, R. Fergus, A. Torralba, Recognizing and Learning Object Categories, Awarded the Best Short Course Prize at ICCV 2005. http://people.csail.mit.edu/torralba/shortCourseRLOC/ object recognition

S. Park, M. Trivedi, Multi-person interaction and activity analysis: a synergistic track- and body-level analysis framework, Machine Vision and Applications, activity recognition

M. Kristan, J. Pers, M. Perse, S. Kovacic, Closed-world tracking of multiple interacting

targets for indoor-sports applications, CVIU, 2008 sports