Aam based face tracking with temporal matching and face segmentation
1 / 22

AAM based Face Tracking with Temporal Matching and Face Segmentation - PowerPoint PPT Presentation

  • Uploaded on

CVPR 2010. AAM based Face Tracking with Temporal Matching and Face Segmentation. Mingcai Zhou 1 、 Lin Liang 2 、 Jian Sun 2 、 Yangsheng Wang 1. 1 Institute of Automation Chinese Academy of Sciences, Beijing, China. 2 Microsoft Research Asia Beijing, China. Outline. AAM Introduction

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

PowerPoint Slideshow about 'AAM based Face Tracking with Temporal Matching and Face Segmentation' - edan-fuller

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
Aam based face tracking with temporal matching and face segmentation

CVPR 2010

AAM based Face Tracking with Temporal Matching and Face Segmentation

Mingcai Zhou1、 Lin Liang2、 Jian Sun2、Yangsheng Wang1

1Institute of Automation Chinese Academy of Sciences, Beijing, China

2Microsoft Research Asia Beijing, China


  • AAM Introduction

  • Related Work

  • Method and Theory

  • Experiment

Aam introduction
AAM Introduction

  • A statistical model of shape and grey-level appearance

Shape model

Appearance model

Shape model building
Shape Model Building

:mean shape

:shape bases

,shape parameters

learn by PCA

generate mean shape、

shape bases

Texture model building
Texture Model Building

:mean appearance

:appearance bases

:appearance parameters



Mean shape

Shape-free patch

Aam model search
AAM Model Search

  • Find the optimal shape parameters and appearance parameters to minimize the difference between the warped-back appearance and synthesized appearance

map every pixel x in the model coordinate to its corresponding image point

Problems aam tracker
Problems- AAM tracker

  • Difficultly generalize to unseen images

  • Clutterd backgrounds

How to do
How to do?

  • A temporal matching constraint in AAM fitting

    -Enforce an inter-frame local appearance constraint

    between frames

    • Introduce color-based face segmentation as a soft constraint

Related work
Related Work

-feature-based (mismatched local feature)

Integrating multiple visual cues for robust real-time

3d face tracking,W.-K. Liao, D. Fidaleo, and G. G. Medioni. 2007

-intensity-based (fast illumination changes)

Improved face model fitting on video sequences, X. Liu, F.

Wheeler, and P. Tu. 2007

temporal matching constraint

Method and theory
Method and Theory

  • Extend basic AAM to Multi-band AAM

    • The texture(appearance) is a concatenation of three texture band values

      • The intensity (b)

      • X-direction gradient strength (c)

      • Y-direction gradient strength (d)

Temporal matching constraint
Temporal Matching Constraint

  • Select feature points with salient local appearances at previous frame

  • I(t−1) to the Model coordinate and get the appearance A(t-1)

  • Use warping function W(x;pt) maps R(t-1) to a patch R(t) at frame t

Shape parameter initialization
Shape parameter Initialization

Face Motion Direction


Shape parameter initialization1
Shape parameter Initialization

When r reaches the noise level expected in the

correspondences, the algorithm stops

Shape parameter initialization2
Shape parameter Initialization


Motion direction

Previous frame’s shape

Feature matching

Face segmentation constraint
Face Segmentation Constraint

Where are the locations of the selected outline points in the model coordinate

Face segmentation constraint1
Face Segmentation Constraint

-Face Segmentation


Lost frame num


─ Our tracking algorithm accurately localizes the facial

components, such as eyes, brows, noses and mouths,

under illumination changes as well as large expression

and pose variations.

─ Our tracking algorithm runs in real-time. On a

Pentium-43.0G computer, the algorithm’s speed is

about 50 fps for thevideo with 320 × 240 resolution

Future work
Future Work

─ Our tracker cannot robustly track profile views

with large angles

─ The tracker’s ability to handle large occlusion also

needs to be improved