Title: Multiple View Based 3D Object Classification Using Ensemble Learning of Local Subspaces (ThBT4.3)
1Multiple View Based 3D Object Classification
Using Ensemble Learning of Local Subspaces
(ThBT4.3)
- Jianing Wu, Kazuhiro Fukui
- lacarte_at_cvlab.cs.tsukuba.ac.jp,
- kfukui_at_cs.tsukuba.ac.jp
- Graduate school of Systems and Information
Engineering - University of Tsukuba (Japan)
2Abstract
- We proposed a statistical method for object
classification based on multi-view. - The proposed method is an extension of MSM.
- Problems of previous works (MSM, KMSM) has been
solved. - We evaluated the classification performance of
the proposed method and previous works.
3Table of Contents
- Backgrounds
- Multi-view classification and problems of
existing methods for nonlinear distribution - The proposed method
- Approximation by local subspaces and ensemble
learning - Experimental results
- Performance comparison using multi-view images of
objects - Summary
4Multi-view Based Object Classification
- Multiple view is more beneficial for object
classification than single. - View based approach does not need 3D model for
classification. - Subspace related methods has been proposed for
multi-view frame work.
5Existing view based approaches
- Mutual Subspace Method (MSM)
- O.Yamaguchi, K.Fukui, K.Maeda Face recognition
using temporal image sequence. Proc.IEEE 3rd
International Conference on Automatic Face and
Gesture Recognition, pp.318-323,1998.
- Pro
- Low computation cost
- Con
- Cannot handle nonlinear distribution
6Multi-view Based Object Classification
- Feature vectors from multi-view input are likely
to have nonlinear distribution.
- Subspace approximation therefore is not accurate.
7Existing view based approaches
- Kernel Mutual Subspace Method (KMSM)
- H.Sakano, N.Mukawa Kernel mutual subspace
method for robust facial image recognition. Proc.
4th International Conference on Knowledge-Based
Intelligent Engineering Systems and Allied
Technologies, Vol.1, pp.245-248, 2000. - Project feature vectors to a high dimensional
space to reduce their nonlinearity. - Pros
- Can handle nonlinear distribution.
- Cons
- Consume more computation time, and this increases
at order N2 as learning data increases. - Some critical parameters need to be optimized
8Motivation of the Proposed Method
- Approximate nonlinear distribution.
- Divide the original distribution, and approximate
each subset. - Achieve comparable classification performance
with KMSM, using less computation. - Perform classification without kernel framework.
9Table of Contents
- Backgrounds
- Multi-view classification and problems of
existing methods for nonlinear distribution - The proposed method
- Approximation by local subspaces and ensemble
learning - Experimental results
- Performance comparison using multi-view images of
objects - Summary
10The Proposed Method
- Divide the nonlinear distribution into several
subsets based on Euclidean distance. - Nonlinearity of each subset is weaker.
- We approximate each subset with local subspace.
11Ensemble Classification
- Division number and dimension of each local
subspace are parameters affect classification
performance. - We construct local subspaces under multiple
combination. - We assume each case as weak classifier and apply
ensemble learning.
12The Proposed Method with Weight
- Each local subspace carries a weight coefficient
based on its classification performance. - This coefficient weights the canonical angle.
- The coefficients are simply the accuracy rate of
each local subspace in preliminary experiments.
13The Proposed Method
14Table of Contents
- Backgrounds
- Multi-view classification and problems of
existing methods for nonlinear distribution - The proposed method
- Approximation by local subspaces and ensemble
learning - Experimental results
- Performance comparison using multi-view images of
objects - Summary
15Classification Experiment
- Compare the classification performance and
computation cost of MSM, KMSM and the proposed
method. - Use multi-view image data set The ETH-80 Image
Set - B.Leibe, B.Schiele Analyzing appearance and
contour based methods for object categorization.
Proc. CVPR'03, Vol.2, pp.409-415, 2003
16Classification Experiment
- The dataset contains 8 classes, 10 objects for
each class.
- 41 points of view for each object
- Feature vector is the resized image (16x16)
17Classification Experiment
- Use 164 images to learn for each class. (generate
dictionary) - Evaluation input is images from an unknown
object. (10 images/points of view) - By exchanging learning data and evaluation data
(leave-one-out), we repeated experiment for 1640
times.
18Classification Experiment
- Classification performance of each method
Method Accuracy Rate() Separability EER()
MSM 69.5 0.34 20
KMSM 87.2 0.41 15
Proposed method 86.5 0.44 14
Proposed method with weight 94.7 0.55 9
19Classification Experiment
- The proposed method improved classification
performance from MSM - The proposed method achieved comparable
performance with KMSM - Classification performance of the proposed method
was improved by introducing weight to each local
subspace
20Classification Experiment
- Computation cost of each method
Method Calculation Time (seconds per input) Order
MSM 0.1 O(n)
Proposed method 0.4 O(n)
Proposed method with weight 0.4 O(n)
KMSM 3.1 O(n2)
21Classification Experiment
- The proposed method consumes less computation
time compared with KMSM - The computation time of the proposed method
increases in order N as learning data increases
22Classification Experiment
- Classification performance of weak classifiers
Proposed method 86.5 0.44 14
23Table of Contents
- Backgrounds
- Multi-view classification and problems of
existing methods for nonlinear distribution - The proposed method
- Approximation by local subspaces and ensemble
learning - Experimental results
- Performance comparison using multi-view images of
objects - Summary
24Summary
- We proposed a method to achieve comparable
performance with KMSM by less calculation. - Classification performance is further improved by
introducing weight to each local subspace - The advantages of the proposed method is shown
with classification experiment of objects.
25Thank You
- Multiple View Based 3D Object Classification
Using Ensemble Learning of Local Subspaces
(ThBT4.3) - Jianing Wu, Kazuhiro Fukui