1 / 49

# Motion from normal flow - PowerPoint PPT Presentation

Motion from normal flow . The aperture problem. Depth discontinuities. Optical flow difficulties. Translational Normal Flow. In the case of translation each normal flow vector constrains the location of the FOE to a half-plane. Intersection of half-planes provides FOE.

Related searches for Motion from normal flow

I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.

## PowerPoint Slideshow about 'Motion from normal flow' - lavonne

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

### Motion from normal flow

Depth discontinuities

Optical flow difficulties

• In the case of translation each normal flow vector constrains the location of the FOE to ahalf-plane.

• Intersection of half-planes provides FOE.

• Idea: choose particular directions: patterns defined on the sign of normal flow along particular orientation fields

• positive depth constraint

• 2 classes of orientation fields: copoint vectors and coaxis vectors

with respect to axis (A,B,C)

h passes through FOE and (Af/C, Bf/C), defined by 2 parameters

g passes through AOR and (Af/C, Bf/C), defined by 1 parameter

Positive + positive  positive

Negative + negative negative

Positive + negative don’t know (depends on structure)

translational

rotational

combined

g-vectors: Translation

g-vectors: Rotation

g-vectors: Translation and Rotation

alpha beta gamma

defined by point (r,s)

k passes through FOE and (r,s) defined by 1 parameter

l passes through AOR and (r,s), is defined by 2 parameters

rotational component

(a) (b) (c)

a,b,g vectors

c,d,e: Fitting of a,b,g patterns

g: Separation of (a,b,g) coaxis pattern

h: Separation of (x0, y0) copoint pattern

illusion

• Flow can be accurately estimated in an image patch corresponding to a smooth scene patch,

• But erroneous flow estimates are obtained for image patches corresponding to scene patches containing discontinuities

Image Flow

Scene structure

Discontinuities

3D Motion

• Errors in motion estimates lead to distortion of the scene estimates.

• The distortion is such that the correct motion gives the “smoothest” (least varying) scene structure.

• Scene depth can be estimated from normal flow measurements:

• Wrong 3D motion gives rise to a rugged (unsmooth) depth function (surface).

• The correct 3D motion leads to the “smoothest” estimated depth.

incorrect motion

Inverse depth estimates

• A normal flow measurement:

For an estimate

• The error function to be minimized:

• Estimated normal flow

• The error function to be minimized:

• Global parameters:

• Local parameter:

locally planar patches:

• Given a translation candidate , each local depth can be computed as a linear function of the rotation .

• We obtain a second order function of the rotation; its minimization provides both the rotation and the value of the error function.

Brightness consistency:

Flow:

Planar patch:

• Given a candidate motion, the scene depth can be estimated and further processed to find depth discontinuities.

• Split a region if it corresponds to two depth values separated in space.

• Compute spatio-temporal image derivatives and normal flow.

• Find the direction of translation that minimizes the depth-variability criterion.

• Hierarchical search of the 2D space.

• Iterative minimization.

• Utilize continuity of the solution in time; usually the motion changes slowly over time.

Divide image into small patches

YES

Search in the 2D space of translations

Use the error

NO

Distinguish between two cases

For each candidate 3D motion, using normal flow measurements in each patch, compute depth of the scene.

existence of a discontinuity at the patch

wrong 3D motion

For each image patch

Use the error

Split the patch and repeat the process

The Algorithm

• Comparison of the original sequence and the re-projection of the 3D reconstruction.