1 / 27

Advance Computer Vision

Advance Computer Vision. Lectures 01 Roger S. Gaborski. Course Overview. This is a very interactive class We will use the same textbook from Introduction to Computer Vision, journal publications and also Internet sources, including viewing videos from the site:

hertz
Télécharger la présentation

Advance Computer Vision

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Advance Computer Vision Lectures 01 Roger S. Gaborski

  2. Course Overview • This is a very interactive class • We will use the same textbook from Introduction to Computer Vision, journal publications and also Internet sources, including viewing videos from the site: http://videolectures.net/Top/Computer_Science/Computer_Vision • Your background from Introduction to Computer Vision will provide a solid foundation

  3. There is a central ‘theme project’ for the course – scenecategorization • The project will be divided into a number of sub-projects • Course activities • Lectures • Class discussions • A few videos • Homework • MAJOR Project

  4. Divide main course project into sub-projects • Through class discussions determine important sub-projects (tasks) • Form groups based on student interest that will focus on sub-projects • Groups will focus on different approaches • Starting week 5, report weekly on progress • Integrate sub-projects into overall project

  5. Grading • Homework 25% • Class discussions 25% • Final Project50%

  6. Class Location • Effective Thursday, class will move to Rm 70-3400 (my lab)

  7. Features • Match corresponding feature points in images • In video, two temporally adjacent frames • In still images, two different images of the same scene • Or two different images of similar scene

  8. Issues • Lighting variations • View point • Scale • Rotation

  9. NEED TO FIND CORRESPONDENCE BETWEEN FEATURE POINTS IN TWO DIFFERENT IMAGES • Cannot match individual pixels • Need to use a window containing many pixels (5x5, 7x7, 21x21, etc)

  10. Matching on a continuum like texture and edges not very robust • Many edges (and parts of edges) will match • At the very least: • Need to find interest points • Extract patches around interest points • Match patches

  11. Feature Points / Correspondence • Points should be extracted consistently over different views • Points should be invariant to scaling, rotation, changes in illumination • Information in the neighborhood of the point should be unique so that it can be matched

  12. Select Window RegionMatch Region in Second Image Calculate difference between the two patches WindowMatching_ACV.m

  13. Convert to Grayscale

  14. Randomly Select Patch patch = I(80:110,200:230); For Demonstration Use Only Strip Containing Patch

  15. Error=Absolute Difference Between Patch and Strip

  16. Normalized Cross Correlation (Refer to equation on page p313)Also MATLAB docs • w is template • w is average value of elements in template • f is the image • f is the average of the image where f and w overlap • Denominator normalizes resulting in an output range of -1, +1 • High value for absolute value of output is a good match

  17. MATLAB Cross Correlation Function g = normxcorr2(template, f)

  18. Find Max Value in |g| d = abs(g); [ypeak, xpeak] = find(d == max(d(:))); %Adjust location by size of template ypeak = ypeak-(size(patch,1)-1)/2; xpeak = xpeak-(size(patch,2)-1)/2; fprintf('\n Center of Patch: ypeak is %d and xpeak is %d \n\n\n', ypeak, xpeak); figure, imshow(Igray) hold on plot(xpeak, ypeak, 'ro')

  19. Red – strongest response Green – second strongest response

  20. HW#1- Slides 12-17Due Thursday: rsg.advcv@gmail.com • Read in Purple Flower Image • Select a 31x31 patch • Extract image strip that contains patch • Calculate Error=Absolute Difference Between Patch and Strip and plot • Repeat using Normalized Cross Correlation on whole image • Plot max location on image • Email code, results and writeup to:rsg.advcv@gmail.com • You should work in teams of 2- list both names on report • WindowMatching_ACV.m

  21. But How Do We Select Points? • Junctions or Corners • Stable over changes in viewpoint

  22. Feature Points?

  23. Subtract First Window from Second Window

  24. Moravec’s Corner Detector • Overview: • Select window size • Shift window over image region • If window over uniform region, shifts in all directions will result in small changes • If window over edge, shifts along edge will results in small changes, but shifts across edge will result in large changes • along edge – no change • Perpendicular to edge – large change • If window over corner, than shifts in all directions will result will result in large changes • Detect corner by finding regions that have large changes in all directions

  25. Subtract First Window from Second Window Window moved vertically, no change Window moved horizontally, no change Window moved in either direction, large change

  26. Presentation:Outline of Paper: “How many pixels make an image?”Antonio Torralba

More Related