CS223B-L12-Segmentation

CS223B-L12-Segmentation - Stanford CS223B Computer Vision,...

Info iconThis preview shows pages 1–14. Sign up to view the full content.

View Full Document Right Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Stanford CS223B Computer Vision, Winter 2008/09 Lecture 12 Segmentation and Grouping Professor Sebastian Thrun CAs: Ethan Dreyfuss, Young Min Kim, Alex Teichman
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
* Pictures from Mean Shift: A Robust Approach toward Feature Space Analysis, by D. Comaniciu and P. Meer http://www.caip.rutgers.edu/~comanici/MSPAMI/msPamiResults.htm *
Background image of page 2
Sebastian Thrun Stanford University CS223B Computer Vision Intro: Segmentation and Grouping Motivation: for recognition? for compression Relationship of sequence/ set of tokens Always for a goal or application Currently, no real theory Segmentation breaks an image into groups over space and/or time Tokens are The things that are grouped (pixels, points, surface elements, flow, etc.) top down segmentation tokens grouped because they lie on the same object bottom up segmentation tokens belong together because of some local affinity measure Bottom up/Top Down need not be mutually exclusive
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Outline Segmentation Challenges Segmentation by Clustering Segmentation by Graph Cuts Segmentation by Spectral Clustering Active Contours and Snakes
Background image of page 4
Sebastian Thrun Stanford University CS223B Computer Vision Biological: For humans at least, Gestalt psychology identifies several properties that result In grouping/segmentation:
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Biological: For humans at least, Gestalt psychology identifies several properties that result In grouping/segmentation:
Background image of page 6
Sebastian Thrun Stanford University CS223B Computer Vision Groupings by Invisible Completions * Images from Steve Lehar’s Gestalt papers: http://cns-alumni.bu.edu/pub/slehar/Lehar.html Stressing the invisible groupings:
Background image of page 7

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Groupings by Invisible Completions * Images from Steve Lehar’s Gestalt papers: http://cns-alumni.bu.edu/pub/slehar/Lehar.html
Background image of page 8
Sebastian Thrun Stanford University CS223B Computer Vision Why do these tokens belong together? Here, the 3D nature of grouping is apparent:
Background image of page 9

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision And the famous invisible dog eating under a tree:
Background image of page 10
Sebastian Thrun Stanford University CS223B Computer Vision A Final Segmentation Challenge
Background image of page 11

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Sebastian Thrun Stanford University CS223B Computer Vision Outline Segmentation Challenges Segmentation by Clustering Segmentation by Graph Cuts Segmentation by Spectral Clustering Active Contours and Snakes
Background image of page 12
Sebastian Thrun Stanford University CS223B Computer Vision Segmentation as clustering Cluster together (pixels, tokens, etc.) that belong together Agglomerative clustering attach closest to cluster it is closest to repeat Divisive clustering split cluster along best boundary repeat Point-Cluster distance single-link clustering complete-link clustering group-average clustering Dendrograms yield a picture of output as clustering process continues * From Marc Pollefeys COMP 256 2003
Background image of page 13

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 14
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 01/24/2010 for the course CS 223B taught by Professor Thrun,s during the Winter '09 term at Stanford.

Page1 / 76

CS223B-L12-Segmentation - Stanford CS223B Computer Vision,...

This preview shows document pages 1 - 14. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online