Home >  1 Deformable Template as Active Basis Zhangzhang Si UCLA Department of Statistics Ying Nian Wu, Zhangzhang Si, Chuck Fleming, Song-Ch

1 Deformable Template as Active Basis Zhangzhang Si UCLA Department of Statistics Ying Nian Wu, Zhangzhang Si, Chuck Fleming, Song-Ch


 

1  
 
 

Deformable Template as Active Basis 
 

Zhangzhang Si

UCLA Department of Statistics 

Ying Nian Wu, Zhangzhang Si, Chuck Fleming, Song-Chun Zhu  ICCV07 

��the work in this talk is outdated, see

http://www.stat.ucla.edu/~ywu/AB/ActiveBasisMarkII.html

for the updated results in our IJCV paper)

 


CIVS, Statistics Dept. UCLA

CIVS, Statistics Dept. UCLA 

2  
 
 

Design a deformable template to model a set of images of a certain object category. The template can be learned from example images. 

Motivation


 

3  
 
 

Representation:  generative and deformable models

  1. Sparse coding [Olshausen-Field 96]
  2. Deformable templates [Yuille-Hallinan-Cohen 89]
  3. Active contours  [Kass-Witkin-Terzopoulos 87]
  4. Active appearance [Cootes-Edwards-Taylor 95]
  5. Texton model [Zhu et.al. 02]
 
 

Computation:  learning and pursuit algorithm

1.    Matching pursuit [Mallat and Zhang 93]

2.    HMAX [Riesenhuber-Poggio 99, Mutch-Lowe 06]

3.     Adaboost  [Freund-Shapire 96, Viola-Jones 99] 

Related work


CIVS, Statistics Dept. UCLA

 

 
 

selected from a dictionary of Gabor wavelet elements 

Linear additive image model 

Image reconstruction by matching pursuit. 

4  

Two extensions:

  1. Encoding a single image               Simultaneously encoding a set of images;
  2. Allow each Gabor wavelet element Bi to locally perturb.
 

location 

scale 

orientation


CIVS, Statistics Dept. UCLA

 

5  
 
 

The active basis model 

��Active��: Local perturbation 

When encoding image Im, we use

the perturbed version of Bi

(Gabor elements represented by bar)


CIVS, Statistics Dept. UCLA

CIVS, Statistics Dept. UCLA 

6  
 
 

Deformable template using active basis 

A car template 

An incoming car image: 

(Gabor elements represented by bar)


 

7  
 
 

Deformable template using active basis 

A car template 

Deformed to fit many car instances


CIVS, Statistics Dept. UCLA

 

8  
 
 

Learning the template: pursuing the active basis 

Example images 

B1 

B3 

B2 

# Gabor elements selected 

q(I): background distribution

(all natural images) 

p(I): pursued model to approximate

   the true distribution.


CIVS, Statistics Dept. UCLA

CIVS, Statistics Dept. UCLA 

9  
 
 

Pursuing the active basis 

MLE: 

(Projected on {B1,��,Bn}) 

(orthogonality of {B1,��,Bn})


CIVS, Statistics Dept. UCLA 

10  
 
 

Pursuing the active basis


CIVS, Statistics Dept. UCLA 

11  
 
 

Shared pursuit algorithm


 

12  
 
 

Learning the template: pursuing the active basis 

Car instances 

A car template consisting of  60 Gabor elements


CIVS, Statistics Dept. UCLA

 

 
 

  • 37 training images, listed in the descending order of log-likelihood ratio
  • 4.3 seconds (Core 2 Duo 2.4GHz) , after convolution
 

Experiment 1: learning an active basis model of vehicle 

13  

template


CIVS, Statistics Dept. UCLA

 

14  
 
 

Experiment 2: learning without alignment 

Active basis pursuit + EM 

Given bounding box for the first example for initialization. 

Iterate:

    - Estimate the bounding boxes using current model.

    - Re-learn the model from estimated bounding boxes.


CIVS, Statistics Dept. UCLA

 

15  
 
 

Experiment 3: learning and clustering  

Learning active basis 

EM clustering


CIVS, Statistics Dept. UCLA

 

 
 

Experiment 4: car detection with active basis model 

map of LLR at optimal scale 

Maximum LLR over scale 

  • Scan bounding box over the image at multi-resolutions
  • Compute log-likelihood ratio by combining responses from active basis
 

16  

LLR: log likelihood ratio 

LLR: log likelihood ratio


CIVS, Statistics Dept. UCLA

 

17  
 
 

Experiment 5: head-and-shoulder recognition 

Some positives 

Some negatives 

Negatives include various in-door and out door scenes, with and without human 

Human head and shoulders, roughly aligned 

Features: using the same set of Gabor filters. 

43 training positives, 157 training negatives

88 testing positives,   474 testing negatives


CIVS, Statistics Dept. UCLA

 

18  
 
 

Experiment 5: head-and-shoulder recognition

    comparing with Adaboost 

ROC of sigmoid model is a further improvement of the result presented in the paper.


CIVS, Statistics Dept. UCLA

 

19  
 
 

1.  An active basis model as deformable template.

2.  An active bases pursuit algorithm for fast learning. 

Main contributions 

http://www.stat.ucla.edu/~ywu/ActiveBasis.html 

Download

1)  Training and testing images

2)  Matlab and mex-C source codes that reproduce all the experiments in the paper and powepoint.


CIVS, Statistics Dept. UCLA

Set Home | Add to Favorites

All Rights Reserved Powered by Free Document Search and Download

Copyright © 2011
This site does not host pdf,doc,ppt,xls,rtf,txt files all document are the property of their respective owners. complaint#nuokui.com
TOP