Shadow resistant video tracking
This presentation is the property of its rightful owner.
Sponsored Links
1 / 22

Shadow Resistant Video Tracking PowerPoint PPT Presentation


  • 82 Views
  • Uploaded on
  • Presentation posted in: General

Shadow Resistant Video Tracking. Hao Jiang and Mark S. Drew School of Computing Science Simon Fraser University Vancouver, BC, Canada. Problem Statement. We want to realize this!. Traditional Contour Tracking based on motions. Outline.

Download Presentation

Shadow Resistant Video Tracking

An Image/Link below is provided (as is) to download presentation

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


Shadow resistant video tracking

Shadow Resistant Video Tracking

Hao Jiang and Mark S. Drew

School of Computing Science

Simon Fraser University

Vancouver, BC, Canada


Problem statement

Problem Statement

We want to realize this!

Traditional Contour

Tracking based on

motions


Outline

Outline

  • We present an invariant image model. We study how to project an image to an invariant space, such that the shadow can be greatly attenuated.

  • We present two new external forces to the snake model and present an chordal snake model to deal with object tracking in cluttering environment.

    • The first external force is based on predictive contour

    • The chordal constraint based on a new shape descriptor

  • Results and conclusion


Invariant image

Invariant Image

n

Planckian Lighting

ai

x

Lambertian Surface

For narrow band

Sensors:

The responses:


Shadow resistant video tracking

ref-2

Considering 3-sensor cameras, = R, = G, = B

Let r=log(R/G) , b=log(B/G)

We get,

b

ref-1

The slope is

determined by the

camera sensors

Lighting

Material

r


Invariant image generation

Invariant Image Generation

(log(r/g), log(b/g))

Projection

(r,g,b)

b

Invariant Image

Generation

Camera

characteristic

orientation

o

r


Camera calibration

Camera Calibration

Take image of

one scene under

different lightings

Shift the center of

the log-log ratios

corresponding

to each

material to the origin

Stack the log-ratio

vectors of each material

into a matrix A

and do SVD A=UDV’

Camera Orientation=

V(:,1)

Characteristic Orientation of Canon ES60


For real image

For Real Image

Original image Invariant image


Inertia snake tracking i

Inertia Snake Tracking I

  • A predictive contour constraint

Inertia Term

If we choose quadratic norm for E(.,.) the Eular Equation,

By introducing a artificial parameter t, the equation can be

solved by PDE


A chordal constraint

A Chordal Constraint

  • Now we further introduce a second constraint to maintain the solidness of the shape of the contour by maintaining the value of a shape descriptor.

  • The shape discriptor is defined as

    d(s, )=||X(s)-X(s+ )||

    where s in is the normalized length from one point on the contour. Apparently, d(x, ) is periodic for both s and .

s

1

1

0


The shape descriptor

The Shape descriptor

s

1

0

1

The similarity of contour X and Y is,

In frequency domain


The chordal snake

The Chordal Snake

Here we use a simple version d(s)=||X(s)-X(s+1/2)||

The variational problem is

Where Y(s) is an accessory contour, d(s) is the calculated from

last video frame. The corresponding reaction-diffusion PDE is:


The chordal snake1

The Chordal Snake

Now we set Y0(s)= X0(s+1/2), D0(s)= C0(s+1/2). It is not difficult

to prove the following Lemma and theorem.

Lemma: If Y(s,t1)= X(s+1/2,t1), D(s,t1)= C(s+1/2,t1) then

Y(s,t)= X(s+1/2,t) for any t>= t1

Theorem: Given the initial conditions of Y0(s)= X0(s+1/2),

D0(s)= C0(s+1/2), we have,

Predictive Constraint

Shape descriptor constraint


Chordal snake tracking ii

Chordal Snake Tracking II

Chordal constraint

Predictive contour

Features

Smoothed

predictive contour

Previous contour

Real object boundary

Initial contour


The system

The System

Motion

Detection

Affine Motion

Estimation

Fn

Motion

Map

Fn-1

Invariant

Image

warping

GVF

Invariant

Image

Motion

Detection

Cn-1

Contour

Prediction

External Force

Init Contour

Pred Contour

Chordal Model

Cn

Inertia Snake Tracking


An example

An Example

Initial Contour

Prediction Contour


Experiment result

Experiment Result

Two successive frames

Motion map in original color space Motion map in invariant color space


Experiment result1

Experiment Result

Two successive frames

Motion map in original color space Motion map in invariant color space


Traditional snake model

Traditional Snake Model

Frame 1 Frame 2 Frame 3

Frame 4 Frame 5 Frame 6

Frame 7 Frame 8 Frame 9


Tracking result

Tracking Result

Ball Sequence Hand Sequence Baby Sequence


Conclusion

Conclusion

  • We present scheme to get shadow invariant image.

  • We present a much more robust snake model.

  • The proposed method can work well even though there is strong distracting shadows

  • Current framework can be easily extended to the cases when the object is passing casting shadows

  • Future Work

    • Study scheme to deal with tracking in high dynamic range environment

    • Study shadow resistant method for active appear model


Shadow resistant video tracking

Thank You!

Q&A


  • Login