Lecture - Optical Flow

Lecture - Optical Flow - ComputerVision Optical Flow Some...

Info iconThis preview shows pages 1–10. Sign up to view the full content.

View Full Document Right Arrow Icon
Computer Vision  Optical Flow Some slides from K. H. Shafique [http://www.cs.ucf.edu/courses/cap6411/cap5415/] and T. Darrell
Background image of page 1

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

View Full DocumentRight Arrow Icon
Bahadir K. Gunturk EE 7730 - Image Analysis II 2 Correspondence Which pixel went where? Time: t Time: t + dt
Background image of page 2
Bahadir K. Gunturk EE 7730 - Image Analysis II 3 Motion Field vs. Optical Flow Scene flow: 3D velocities of scene points. Motion field: 2D projection of scene flow. Optical flow: Approximation of motion field derived from apparent motion of brightness patterns in image.
Background image of page 3

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

View Full DocumentRight Arrow Icon
Bahadir K. Gunturk EE 7730 - Image Analysis II 4 Motion Field vs. Optical Flow Consider perfectly uniform sphere rotating in front of camera. Motion field follows surface points. Optical flow is zero since motion is not visible. Now consider stationary sphere with moving light source. Motion field is zero. But optical flow results from changing shading. But, in general, optical flow is a reliable indicator of motion field.
Background image of page 4
Bahadir K. Gunturk EE 7730 - Image Analysis II 5 Applications Object tracking Video compression Structure from motion Segmentation Correct for camera jitter (stabilization) Combining overlapping images (panoramic image construction)
Background image of page 5

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

View Full DocumentRight Arrow Icon
Bahadir K. Gunturk EE 7730 - Image Analysis II 6 Optical Flow Problem How to estimate pixel motion from one image to another? H I
Background image of page 6
Bahadir K. Gunturk EE 7730 - Image Analysis II 7 Computing Optical Flow Assumption 1: Brightness is constant. Assumption 2: Motion is small. ( , ) ( , ) H x y I x u y v = + + (from Taylor series expansion)
Background image of page 7

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

View Full DocumentRight Arrow Icon
Bahadir K. Gunturk EE 7730 - Image Analysis II 8 Computing Optical Flow Combine t I 0 t x y I I u I v = + + In the limit as u and v goes to zero, the equation becomes exact (optical flow equation)
Background image of page 8
Bahadir K. Gunturk EE 7730 - Image Analysis II 9 Computing Optical Flow At each pixel, we have one equation, two unknowns.
Background image of page 9

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

View Full DocumentRight Arrow Icon
Image of page 10
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/28/2011 for the course EE 4780 taught by Professor Staff during the Spring '08 term at LSU.

Page1 / 34

Lecture - Optical Flow - ComputerVision Optical Flow Some...

This preview shows document pages 1 - 10. Sign up to view the full document.

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