16
Background Problem Definition Methodology Extraction and Tracking of a body Skeleton from Multiple views Master’s thesis proposal Alexander Pinzon Fernandez August 31, 2009 Alexander Pinzon Fernandez Bioingenium Research Group

Presentation en seminarioiii

Embed Size (px)

DESCRIPTION

 

Citation preview

Page 1: Presentation en seminarioiii

BackgroundProblem Definition

Methodology

Extraction and Tracking of a body Skeletonfrom Multiple viewsMaster’s thesis proposal

Alexander Pinzon Fernandez

August 31, 2009

Alexander Pinzon Fernandez Bioingenium Research Group

Page 2: Presentation en seminarioiii

BackgroundProblem Definition

Methodology

Outline

1 BackgroundBackground

2 Problem DefinitionProblemObjectives

3 MethodologyMethodology

Alexander Pinzon Fernandez Bioingenium Research Group

Page 3: Presentation en seminarioiii

BackgroundProblem Definition

MethodologyBackground

Outline

1 BackgroundBackground

2 Problem DefinitionProblemObjectives

3 MethodologyMethodology

Alexander Pinzon Fernandez Bioingenium Research Group

Page 4: Presentation en seminarioiii

BackgroundProblem Definition

MethodologyBackground

Background

The study of the human body has been of interest in several areas.For example anatomy, engineering and arts.The movement record has been used to solve different problems.

Diagnosis of gait disorders.Motion capture for computer character animation [3].

Advanced ergonomics analysis and design.Alexander Pinzon Fernandez Bioingenium Research Group

Page 5: Presentation en seminarioiii

BackgroundProblem Definition

Methodology

ProblemObjectives

Outline

1 BackgroundBackground

2 Problem DefinitionProblemObjectives

3 MethodologyMethodology

Alexander Pinzon Fernandez Bioingenium Research Group

Page 6: Presentation en seminarioiii

BackgroundProblem Definition

Methodology

ProblemObjectives

Problem Definition

Most traditional motion tracking methods are based on opticalsystems and present the following disadvantages:• The use of markers attached to the body ALTER the movementgesture.• The need of experts to place the markers because they must belocated in specific anthropometric points.

Alexander Pinzon Fernandez Bioingenium Research Group

Page 7: Presentation en seminarioiii

BackgroundProblem Definition

Methodology

ProblemObjectives

Problem Definition

The stereo systems that perform a three-dimensionalreconstruction MUST handle large volumes of data of the bodygeometry. This process requires high-performance machinesCost between 60,000 and 130,000 dollars (Data for 2009)

Qualisys AB , Sweden. 8 Oqus cameras: 100.000 USDSports Motion, Inc . USA, California. 8 DV Cameras: 60.000USDBTS Spa, Italy. 10 infrared cameras Smart-DDigital: 132.000USD

Alexander Pinzon Fernandez Bioingenium Research Group

Page 8: Presentation en seminarioiii

BackgroundProblem Definition

Methodology

ProblemObjectives

Description Project

To develop a method to extract the skeleton of an articulated body,under the following conditions:• No body model.• Not having a model is an advantage because it is possible toextract and track the articulated skeleton of any body.

• The extracted skeleton is a synthesized representation of thebody geometry.• Once the skeleton is extracted, it is followed for each frame of thevideo

Alexander Pinzon Fernandez Bioingenium Research Group

Page 9: Presentation en seminarioiii

BackgroundProblem Definition

Methodology

ProblemObjectives

Outline

1 BackgroundBackground

2 Problem DefinitionProblemObjectives

3 MethodologyMethodology

Alexander Pinzon Fernandez Bioingenium Research Group

Page 10: Presentation en seminarioiii

BackgroundProblem Definition

Methodology

ProblemObjectives

Objectives

Overall Objective: To develop a method for motion tracking of thehuman body in 3D.

Specific Objectives:1. To implement a video-camera based system to capture a bodymotion, and implement the Σ−∆ Sigma-Delta method to extractthe silhouette of the body from videos.2. To propose a method for extracting body markers whichcorrespond to the fundamental body relations.3. To propose a method to track the skeleton in each video-frameand validate the results.4. To develop a system to visualize the body movement togetherwith the estimated skeleton.

Alexander Pinzon Fernandez Bioingenium Research Group

Page 11: Presentation en seminarioiii

BackgroundProblem Definition

MethodologyMethodology

Outline

1 BackgroundBackground

2 Problem DefinitionProblemObjectives

3 MethodologyMethodology

Alexander Pinzon Fernandez Bioingenium Research Group

Page 12: Presentation en seminarioiii

BackgroundProblem Definition

MethodologyMethodology

MethodologySkeleton Extraction and Motion Tracking

• Data acquisition.• Silhouette Segmentation.• 3D Reconstruction from the data.• Skeleton extraction of the reconstructed three-dimensional object.

Alexander Pinzon Fernandez Bioingenium Research Group

Page 13: Presentation en seminarioiii

BackgroundProblem Definition

MethodologyMethodology

Data Acquisition and SegmentationObjective: To implement a video-cameras based system to capture a body motion

Video Capture system (named optical system) is divided into twoproblems, Camera Calibration and Synchronized Multicamera[1].The image segmentation of this videos is realized with a set ofmethods for dividing an image into regions, given certaincharacteristics[2].

Alexander Pinzon Fernandez Bioingenium Research Group

Page 14: Presentation en seminarioiii

BackgroundProblem Definition

MethodologyMethodology

Three Dimensional ReconstructionObjective: To propose a method for extracting markers of the body fundamental relationsusing the videos.

3D Reconstruction steps:Shape from silhouette

Visuall Hull

Find characteristic points

Extract characteristic points using visual attention model

Stereoscopic reconstruction

Surface reconstruction with the photometric method calledstereo pair, using shape and characteristic points

Alexander Pinzon Fernandez Bioingenium Research Group

Page 15: Presentation en seminarioiii

BackgroundProblem Definition

MethodologyMethodology

Skeleton Extraction

Skeleton extraction is the process of synthesizing and representing abody in a 1D structureBased on medial axis concept.Validation:• Centered skeleton is its centeredness within the object• Homotopic skeleton have the same number of connectedcomponents, tunnels, and cavities.

Alexander Pinzon Fernandez Bioingenium Research Group

Page 16: Presentation en seminarioiii

BackgroundProblem Definition

MethodologyMethodology

Bibliography

G.K.M. Cheung, S. Baker, and T. Kanade.Visual hull alignment and refinement across time: a 3d reconstruction algorithmcombining shape-from-silhouette with stereo.In Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEEComputer Society Conference on, volume 2, pages II–375–82 vol.2, June 2003.

Ning Jin and F. Mokhtarian.Image-based shape model for view-invariant human motion recognition.In Advanced Video and Signal Based Surveillance, pages 336–341, Sept. 2007.

Fabio Remondino.3-d reconstruction of static human body shape from image sequence.Computer Vision and Image Understanding, 93:65–85, 2004.

Alexander Pinzon Fernandez Bioingenium Research Group