1. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Monday, 01 December 2003 William H. Hsu Department of Computing and Information Sciences, KSU http://www.kddresearch.org http://www.cis.ksu.edu/~bhsu Readings: Chapter 24, Russell and Norvig Computer Vision 1 of 2 Lecture 39

2. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Lecture Outline Read Chapter 24, Russell and Norvig Reference: Robot Vision, B. K. P. Horn The Vision Problem –Early vs. late vision –Marr’s 2 ½ - D sketch –Waltz diagrams Shape from Shading –Ikeuchi-Horn method –Subproblems: edge detection, segmentation Optical Flow

3. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Terminology Vision Problem –Early vs. late vision –Marr’s 2 ½ - D sketch –Waltz diagrams Shape from Shading –Ikeuchi-Horn method –Subproblems: edge detection, segmentation Optical Flow

4. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Summary Points Reference: Robot Vision, B. K. P. Horn The Vision Problem –Early vs. late vision –Marr’s 2 ½ - D sketch –Waltz diagrams Shape from Shading –Ikeuchi-Horn method –Subproblems: edge detection, segmentation Optical Flow Next Week –Natural Language Processing survey –Final exam review

5. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Lecture Outline Read Chapter 24, Russell and Norvig References –Robot Vision, B. K. P. Horn –Courses: http://www.palantir.swarthmore.edu/~maxwell/visionCourses.htmhttp://www.palantir.swarthmore.edu/~maxwell/visionCourses.htm –UCB CS 280: http://www.cs.berkeley.edu/~efros/cs280/http://www.cs.berkeley.edu/~efros/cs280/ The Vision Problem –Early vs. late vision –Marr’s 2 ½ - D sketch –Waltz diagrams Shape from Shading –Ikeuchi-Horn method –Subproblems: edge detection, segmentation Optical Flow

6. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision) Line Drawing Interpretation

7. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision) Line Labeling [1]: Solid Polyhedra and Other Shapes Waltz, others

8. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision) Line Labeling [2]: Junctions Junctions occur at tangent discontinuities False T-junctions

9. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Adapted from slides © 1999 T. Leung, UC Berkeley (CS 280 Computer Vision) Orientation and Texture Discrimination (Textons) [1]

10. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision) Orientation and Texture Discrimination (Textons) [2]

11. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision) Segmentation (Grouping) [1]: Definition

12. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision) Segmentation (Grouping) [2]: Physical Factors

13. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision) Edge Detection [1]: Convolutional Filters and Gaussian Smoothing

14. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision) Edge Detection [2]: Difference of Gaussian

15. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision) Binocular Stereo [1]: Stereo Correspondence – Properties

16. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision) Binocular Stereo [2]: Stereo Correspondence – Open Problems

17. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Adapted from slides © 1999 J. Malik, UC Berkeley (CS 280 Computer Vision) Optical Flow

18. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Terminology Vision Problem –Early vs. late vision –Marr’s 2 ½ - D sketch –Waltz diagrams Shape from Shading –Ikeuchi-Horn method –Subproblems: edge detection, segmentation Optical Flow

19. Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Summary Points References –Robot Vision, B. K. P. Horn –http://www.palantir.swarthmore.edu/~maxwell/visionCourses.htmhttp://www.palantir.swarthmore.edu/~maxwell/visionCourses.htm The Vision Problem –Early vs. late vision –Marr’s 2 ½ - D sketch –Waltz diagrams Shape from Shading –Ikeuchi-Horn method –Subproblems: edge detection, segmentation Optical Flow Next Week –Natural Language Processing (NLP) survey –Final review