+ All Categories
Home > Documents > Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Date post: 22-Feb-2016
Category:
Upload: pilar
View: 25 times
Download: 0 times
Share this document with a friend
Description:
Silhouette-based Object Phenotype Recognition using 3D Shape Priors. Yu Chen 1 Tae- Kyun Kim 2 Roberto Cipolla 1 University of Cambridge, Cambridge, UK 1 Imperial College, London, UK 2. Problem Description. Task: To identify the phenotype class of deformable objects. - PowerPoint PPT Presentation
Popular Tags:
19
Silhouette-based Object Phenotype Recognition using 3D Shape Priors Yu Chen 1 Tae-Kyun Kim 2 Roberto Cipolla 1 University of Cambridge, Cambridge, UK 1 Imperial College, London, UK 2
Transcript
Page 1: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Yu Chen1 Tae-Kyun Kim2 Roberto Cipolla1

 University of Cambridge, Cambridge, UK1 Imperial College, London, UK2 

Page 2: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Problem Description

Task: To identify the phenotype class of deformable objects.

Given a gallery of canonical-posed silhouettes in different phenotype classes.

Can we find out

?

Page 3: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Problem DescriptionMotivation:

– Pose recognition is widely investigated;– Phenotype recognition is somehow overlooked;– Applications?

Difficulty: – Pose and camera viewpoint variations are more

dominant than the phenotype variation.

Page 4: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Problem Description 2D approaches hardly work in this

case.

Our strategy: make use of the 3D shape prior of deformable objects.

Shall we use a purely generative approach?

No! Too expensive to perform for a recognition task!

Page 5: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Solution: Two-Stage Model Main Ideas:

Discriminative + Generative Two stages:1. Hypothesising

– Discriminative;– Using random forests;

2. Shape Synthesis and Verification– Generative;– Synthesising 3D shapes

using shape priors;– Silhouette verification.

Recognition by a model selection process.

Page 6: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

• Use 3 RFs to quickly hypothesize phenotype, pose, and camera parameters.

• Learned on synthetic silhouettes generated by the shape priors.

Parameter Hypothesizing

FA: Pose classifier

FC: Camera pose classifier

FS: Phenotype classifier

(canonical pose)

Page 7: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Examples of Tree Classifiers

The phenotype classifier

The pose classifier

Page 8: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Training RF Classifiers Random Features:

– Rectangle pairs with random sizes and locations.

– Difference of mean intensity values[Shotton et al. 09]

– Feature error compensation for phenotype classifier;

Criteria Function:– Similarity-aware diversity

index.

Page 9: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Shape Synthesis and Verification

Generate 3D shapes V – From candidate parameters

given by RFs.– Use GPLVM shape priors

[Chen et al.’10].

Compare the projection of V with the query silhouette Sq.

– Oriented Chamfer matching (OCM). [Stenger et al’03]

Page 10: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

ExperimentsTesting data:

– Manually segmented silhouettes;

Current Datasets– Human jumping jack

(13 instances, 170 images);– Human walking

(16 instances, 184 images);– Shark swimming

(13 instances, 168 images).Phenotype Categorisation

Page 11: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Comparative Approaches:

Learn a single RF phenotype classifier; Histogram of Shape Context (HoSC)

– [Agarwal and Triggs, 2006] Inner-Distance Shape Context (IDSC)

– [Ling and Jacob, 2007] 2D Oriented Chamfer matching (OCM)

– [Stenger et al. 2006] Mixture of Experts for the shape reconstruction

– [Sigal et al. 2007].– Modified into a recognition algorithm

Page 12: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Comparative Approaches: Internal comparisons:

– Proposed method with both feature error modelling and similarity-aware criteria function (G+D);

– Proposed method w.o feature error modelling (G+D–E);

– Proposed method w.o similarity-aware criteria function (G+D–S)

Using standard diversity index instead.

Page 13: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Recognition Performance Cross-validation by splitting the dataset instances. 5 phenotype categories for every test. Selecting one instance from each category.

Page 14: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Recognition Performance How the parameters of RFs affect the

performance?– Max Tree Depth dmax

– Tree Number NT

Page 15: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Qualitative Results of SVR Left: Input image/silhouette; Centre: Using RF-hypothesizes;Right: Using the optimisation-based approach.

Page 16: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Qualitative Results of SVR

Page 17: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Take-Home MessagesPhenotype recognition is difficult but still

possible;

Combing discriminative and generative cues can greatly speed up the inference;

A divide-and-conquer strategy can help improve the recognition rate.

Page 18: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

Future WorkExplore the application on more

complicated poses and more categories.– E.g. Boxing, gardening, other sports, etc.

Data collection;

Automate the silhouette extraction.– E.g. Kinect.

Page 19: Silhouette-based Object Phenotype Recognition using 3D Shape Priors

The End

Questions?


Recommended