UD CISC 689 - Motion Computing in Image Analysis (36 pages)

Previewing pages 1, 2, 17, 18, 19, 35, 36 of 36 page document View the full content.
View Full Document

Motion Computing in Image Analysis



Previewing pages 1, 2, 17, 18, 19, 35, 36 of actual document.

View the full content.
View Full Document
View Full Document

Motion Computing in Image Analysis

46 views

Other


Pages:
36
School:
University of Delaware
Course:
Cisc 689 - Topics: Artificial Intelligence: MACHINE LEARNING

Unformatted text preview:

Motion Computing in Image Analysis Mani V Thomas CISC 489 689 Roadmap Optic Flow Constraint Optic Flow Computation Gradient Based Approach Feature Based Approach Estimation Criterion Block Matching algorithms Conclusion Some slides and illustrations are from M Pollefeys and M Shah Importance of Visual Motion Apparent motion of objects on the image plane is a strong cue to understand structure and 3D motion Biological visual systems infer properties of the 3D world via motion Two sub problems of motion Problem of correspondence estimation Which elements of a frame correspond to which elements of the next frame Problem of reconstruction Given the correspondence and the camera s intrinsic parameters can we infer 3D motion and or structure Courtesy E Trucco and A Verri Introductory techniques for 3D Computer Vision Apparent Motion Apparent motion of objects on the image plane Caution required Consider a perfectly uniform sphere that is rotating but no change in the light direction Perfectly uniform sphere that is stationary but the light is changing Optic flow is zero Optic flow exists Hope apparent motion is very close to the actual motion Courtesy E Trucco and A Verri Introductory techniques for 3D Computer Vision Optic Flow Computation Two strategies for computing motion Differential Methods Spatio temporal derivatives for estimation of flow at every position Multi scale analysis required if motion not constrained within a small range Dense flow measurements Matching Methods Feature extraction Image edges corners Feature Block Matching and error minimization Sparse flow measurements Courtesy E Trucco and A Verri Introductory techniques for 3D Computer Vision Optic Flow Computation Image Brightness Constancy assumption Let E be the image intensity as captured E E E by x the E x ycamera y t t E x y t x y t x t Using Taylor series to expand E y E x x y y t t E x y t E x E y E Lt Lt t 0 t t 0 x t y t t E dx E dy E dE of moving 0objects Apparent brightness x dt y dt t dt



View Full Document

Access the best Study Guides, Lecture Notes and Practice Exams

Loading Unlocking...
Login

Join to view Motion Computing in Image Analysis and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Motion Computing in Image Analysis and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?