1 / 25

Computer Vision

Computer Vision. Michael Isard and Dimitris Metaxas. Some Leading Questions. Shape and Motion Analysis based on Images Scene based and Object based approaches Coupling of low level shape/motion parameters with their semantic interpretation. Scene-based Approaches.

Download Presentation

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. Computer Vision Michael Isard and Dimitris Metaxas

  2. Some Leading Questions • Shape and Motion Analysis based on Images • Scene based and Object based approaches • Coupling of low level shape/motion parameters with their semantic interpretation

  3. Scene-based Approaches • No need for explicit models • Used for camera calibration, pose estimation or image stabilization • Use rigid scene assumptions or optic flow, no use of object shape • A lot of progress has been done already • Limited when multiple motions occur

  4. Object-based analysis • Used for accurate shape/motion analysis and for robustness • Coupling of shape and motion models • Need good shape models • Success with simple shapes, eg. Manmade objects, humans with tight clothes, jointed structures

  5. Object-based analysis • Need good shape models • How do we model humans wearing clothes? • Stability and robustness of shape representation • what is the correct scale for shape representation • 2D or 3D shape?

  6. Shape and Motion • How important is shape for motion? • Facial and Human tracking shape is necessary. • Occlusion and lighting changes

  7. Shading and Motion • One of the still unsolved problems • Most methods still assume optical flow assumption • how to filter out lighting effects? • Relfections? • Multiple lights?

  8. Grouping and Initialization • Most methods assume manual initialization: Where do you place your model? • Based on a single image while it may be best based on multiple images • Related to segmentation and grouping methods as well to higher level knowledge

  9. Grouping and Initialization • 2D information and view-based or appearance based methods mostly • No need necessarily to be based on 3D shape which is very costly • no general algorithms despite some generic methods • Need to address: Light, occlusion, texture, grouping of parts for articulated objects

  10. Segmentation • The grouping and assignment of features to an object or parts of an object • Still the bottleneck in most vision algorithms • Initially based on heuristics • Recently we have realized that statistical methods are superior eg Markov Random Fields

  11. Experimental 1 Original Image (MRI Lung data)

  12. The Gibbs filter Estimation of Boundary

  13. Deformable model fitting

  14. Redo Gibbs Estimation

  15. Cycling Iteration 1 Iteration 2 Iteration 3

  16. Visible Human Data Original MRI image of Eyeball and Muscle in Human Head Eye-ball Muscle

  17. Image Acquisition for 3D Motion Information Tag plane (dark) and image plane orientation Possible tag motion in image plane Representative images

  18. Statistics and Learning • Learning methods for statistical methods are more robust than intuitive statistics • Influenced by success in other fields like speech recognition • However the problem is 4D and there is no explicit ordering within the signal

  19. Statistics and Learning • Learning is a limitation since it depends on many examples • Need new methods to approximate the distributions on appearance of natural scenes to reduce the complexity of the problem • Need to still be able to discriminate objects

  20. Statistics and Learning • How do we develop statistical methods for coupling the low level shape/motion parametes with their semantic interpretation?

  21. Multiple Scales • Shape and motion identification is dependent on the scale at which we do the processing • Recognize gross shape of an object • Recognize human intent • Recognition of human motion

  22. Multiple Scales • How do scales interact? • Need some kind of statistical theory that takes into account multiple scales

  23. Ligthing • Still an open problem • Most algorithms use aLambertian model • How do we cancel lighting artifacts, shadows, reflections, color constancy • shape from shading

  24. Multiple Cues • How do we integrate multiple cues? • Optical flow, edges, features? • No principled theory • Need some theory to selectively use the right cues in a local fashion • Need more research on understanding the robustness of each of these cues • Need to get robustness by combining cues

  25. Summary • Have gone a long way compared to the 70s and 80s. • But still the working algorithms deal with simple shapes, lighting conditions and are domain specific • Need research in all dimensions and also especially on theories that will span a wide variety of objects/motions

More Related