Applications to Machine Vision
author:
Andrew Blake,
Microsoft Research
Description
This presentation describes novel approaches to spatial inference
problems in vision and image processing. Markov random field models are
described for image restoration, foreground segmentation, graph cutting
and stereo matching.
You might be experiencing some problems with Your Video player.
| Slides | |
| 0:00 | Markov Random Field Models and Optimization in image processing and vision |
| 1:07 | Spatial inference problems in vision and Spatial inference problems in vision and |
| 5:18 | Segmentation |
| 10:04 | Simple segmentation --- Ising prior |
| 12:18 | Segmentation artefacts --- Ising prior |
| 12:20 | Simple segmentation --- Ising prior |
| 12:38 | Segmentation artefacts --- Ising prior |
| 13:33 | Simple segmentation --- Ising prior |
| 15:37 | Segmentation artefacts --- Ising prior |
| 15:39 | Boykov-Jolly contrast-sensitive segmentation |
| 18:25 | GrabCut: partially supervised inference |
| 23:15 | Optimizing Markov Random Fields |
| 26:05 | Graph Cut engine for Markov segmentation |
| 33:49 | Ford-Fulkerson Min-cut/Max Flow |
| 36:12 | Example: optimization as graph cut problem |
| 38:38 | Example: graph cut optimization – min cut/max flow |
| 38:48 | Ford-Fulkerson Min-cut/Max Flow |
| 40:03 | Example: optimization as graph cut problem |
| 40:13 | Example: graph cut optimization – min cut/max flow |
| 44:14 | Augmenting flow |
| 46:04 | Graph cut – regularity (submodularity) |
| 49:13 | Regularity: achieving canonical form (1) |
| 49:52 | Regularity: achieving canonical form (2) |
| 51:09 | Graph cut – regularity (submodularity) |
| 53:21 | Dynamic graph cut – Markov editing. |
| 54:45 | Dynamic graph cuts (1) |
| 54:49 | Dynamic graph cuts (2) |
| 54:50 | Dynamic graph cuts (3) |
| 55:05 | Dynamic graph cuts (4) |
| 55:39 | Stereo webcam |
| 57:12 | Live Stereo Segmentation |
| 58:00 | Background substitution |
Lecture rating
| People found this lecture: | ||
| Worth seeing | ||
| because it is: | ||
| Valuable and informative | ||
| Well presented | ||
| Easily understandable | ||
| Acceptably recorded | ||
| You need to login to cast your vote. | ||
Report a problem or upload files
If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Related content
Visitors who watched this lecture also watched...
  2 comments
|
|||
Download slides:
Link this page
Would you like to put a link to this lecture on your homepage?Go ahead! Copy the HTML snippet !
