Spatial histograms for head tracking
Download
1 / 29

Spatial Histograms for Head Tracking - PowerPoint PPT Presentation


  • 116 Views
  • Uploaded on

Spatial Histograms for Head Tracking. Sriram Rangarajan Department of Electrical and Computer Engineering, Clemson University, Clemson, SC 29634. Overview of tracker. Intensity Gradients (works on the boundary of the ellipse). Modules that are complementary to gradients : Color histograms

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

PowerPoint Slideshow about 'Spatial Histograms for Head Tracking' - madeleine


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
Spatial histograms for head tracking

Spatial Histograms for Head Tracking

Sriram Rangarajan

Department of Electrical and Computer Engineering,

Clemson University,

Clemson, SC 29634


Overview of tracker
Overview of tracker

Intensity Gradients (works on the boundary of the ellipse)

Modules that are complementary to gradients :

Color histograms

Spatiograms

Co-occurrence matrices

Log-Gabor histograms

Haar histograms

Edge-orientation histograms

Complementary module (works inside the ellipse)


Gradient module
Gradient module

Likelihood score

Gradient score

Normal to points on ellipse

[Stan Birchfield, 1998]


Overview of modules used
Overview of modules used

Target

histogram

(from

current frame)

Model

histogram

(from first

frame)

Similarity measure

Likelihood score from module

Convert to percentage score, combine with intensity gradient module likelihood and update “state”.


Similarity measure between model and target histograms
Similarity measure between model and target histograms

Histogram intersection [Swain & Ballard1991]

Likelihood normalization



Color histograms
Color Histograms

  • Ignore spatial information (most cases)

  • Computationally efficient, simple, robust and invariant to any one-to-one spatial transformations


Computing color histograms
Computing color histograms

Pixels in a bin

Number of bins for channel C1

Index for color channel

Single color channel of image


Spatiograms
Spatiograms

  • Higher-order histograms that capture spatial information globally

  • Captures both values of pixels and a limited amount of their spatial relationship

  • Bins are weighted by mean and covariance of pixels contributing to it

[Birchfield and Rangarajan, CVPR 2005]


Spatiograms and histograms
Spatiograms and histograms

A histogram

(no spatial information)

A histogram

(no spatial information)

A histogram

(no spatial information)

Σ

Σ

Σ

A spatiogram

(some spatial

Information)

A spatiogram

(some spatial

Information)

A spatiogram

(some spatial

Information)

µ

µ

µ


An illustrative example
An illustrative example

Three poses of a head

Image generated from histogram

Image generated from spatiogram


Co occurrence matrices
Co-occurrence matrices

  • Used for texture analysis

  • Captures the local spatial relationships between colors (or gray levels)

  • Normally used for gray-level images

No. of pixel pairs with value (x,y)


Co occurrence matrices1
Co-occurrence matrices

Local spatial relationships

(C)

10

11

13

10

11

10

10

13

10

10

13

10

11

11

13

10

11

13

Co-occurrence matrix

Image

Color values (C)


Texture histograms
Texture histograms

=

*

Filter bank

Histogram

Image

(Haar Wavelets

or

Log-Gabor filters)


Haar histograms
Haar histograms

  • Histogram of image after convolving with 3-level Haar pyramid:

Haar histogram (at scale S and orientation O.)

Image obtained by convolving with Haar pyramid at scale S and orientation O


Log gabor histograms
Log-Gabor histograms

  • Similar to Haar histograms, but uses a bank of log-Gabor filters.

Log-Gabor histogram

Image obtained by convolving with filter bank at scale S and orientation O


Edge orientation histograms
Edge-orientation histograms

  • Obtained from gradient information

  • Complete reliance on spatial information

  • Histogram bin is decided by orientation of a pixel


Computing edge orientation histograms
Computing edge-orientation histograms

Difference of Gaussian kernel (DoG)

=

*

Image

Edge-orientation Histogram


Edge orientation histograms1
Edge-orientation histograms

  • Computed from gradient images obtained by convolving image with Difference of Gaussian (DoG) kernel in x and y

  • Orientation for pixel along vertical direction is 0


Results log gabor histograms
Results: log-Gabor histograms

Legend:

log-Gaborhistogram

colorhistogram


Results haar histograms
Results: Haar histograms

Legend:

Haarhistogram

colorhistogram


Results edge orientation histograms
Results: Edge-orientation histograms

Legend:

Edge-orientationhistogram

colorhistogram


Results spatiograms
Results: Spatiograms

Legend:

spatiograms

colorhistogram


Results co occurrence matrices
Results: Co-occurrence matrices

Legend:

Co-occurrence

matrices

colorhistogram





Conclusion
Conclusion

  • Limited amount of spatial information drastically improves tracking results

  • Color information also important:

    • With only spatial information: tracker is distracted by cluttered background

    • With only color: tracker is distracted by skin-colored background

  • Global spatial information is the most effective (spatiograms)



ad