development of a system to reproduce the drainage from tsujun bridge for environment education...

24
Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Upload: liliana-jenness

Post on 29-Mar-2015

214 views

Category:

Documents


2 download

TRANSCRIPT

Page 1: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Development of a system to reproduce the drainage from Tsujun Bridge

for environment education

Hikari TakeharaKumamoto National College of Technology

Page 2: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Background

• Tsujun Bridge– an aqueduct bridge made of stones in Kumamoto, Japan– a representative structure in water environment

surrounding Shiraito plateau– This drains water to remove sediment in its water pipe

The drainage from Tsujun Bridge

– The drainage from Tsujun Bridge is utilized for education of water environment in Kumamoto

Page 3: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Problem and Situation

• Problem– Tsujun Bridge has been given damages whenever it drains

water– The reason Leaking water from Tsujun Bridge

• Situation– A number of the drainage from Tsujun Bridge has

decreased for protecting Tsujun Bridge– We cannot always watch the drainage from Tsujun Bridge

Page 4: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Purpose

• Creating a contents for learning the water environment surrounding Shiraito plateau– at any time– without giving any damages to Tsujun Bridge

• We developed a system which reproduces the drainage scene from Tsujun Bridge using Mixed Reality (MR) technology

Page 5: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Mixed Reality (MR)

• MR technology– Synthesize image of real environment (actually visible

landscape) and image of virtual environment (Computer Graphics: CG)

– Making the image as if there is a teapot on table

image of real environment

image of virtual environment

synthesized image

Page 6: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Overview of system

• Capturing the camera image• Geometric registration• Synthesizing camera image and 3DCG model

Page 7: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Program flow

Camera Calibration

Capturing camera image

Geometric Registration

Synthesizing the CG and camera image

Once

Each frame

Page 8: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Program flow

Camera Calibration

Capturing camera image

Geometric Registration

Synthesizing the CG and camera image

Once

Each frame

Page 9: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Camera Calibration

• Intrinsic parameters which express how a camera projects a real space (object) on the projection plane are obtained

object

projection plane

Camera’sfocus

Page 10: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Camera Calibration

Cameracoordinate

Imagecoordinate

100

0

0

0

0

vfk

ufk

v

u

A

Intrinsic parametersmatrix A

Page 11: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Program flow

Camera Calibration

Capturing camera image

Geometric Registration

Synthesizing the CG and camera image

At once

Each frame

intrinsic parameters

Page 12: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Capturing the camera image

• Capturing the camera image was used with OpenCV

• OpenCV(Open source Computer Vision library)– Library for Computer Vision

Page 13: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Program flow

Camera Calibration

Capturing camera image

Geometric Registration

Synthesizing the CG and camera image

At once

Each frame

intrinsic parameters

camera image

Page 14: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Geometric registration

• Geometric registration– to relate the position and orientation of camera with the coordinate

system (world coordinate system) which is set at will in real environment

– This relation is expressed by extrinsic parameters

Worldcoordinate

C

Cameracoordinate

M

XW

YW

ZW

Projection plane

XC

YC

ZC

Page 15: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Extrinsic parameters

• Extrinsic parameters– expressed as 3x4 matrix using rotation matrix R and translation vector T– This study assumed that the position of camera is fixed and that the

orientation of camera can be changed freely– So, T is not need to be obtained, and R is only need to be obtained

 

Extrinsic parametersmatrix M

Page 16: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Extrinsic parameters

• Extrinsic parameters– R matrix is obtained using Zhang’s method with homography matrix

• Homography matrix H– transforms an image of a plane taken from one perspective into an

image taken from the other perspective– expressed as 3x3 matrix

XC

YC

ZCXC’

YC’

ZC’

vH

u’

v’

A plane

u

 

Page 17: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Homography matrix

• Homography matrix– Obtaining this matrix needs more than 4 corresponding

points between 2 images from each other perspectives

– As the method of obtaining corresponding points, the method based on natural features is adopted

– As the method of extracting natural features, SURF is used

Page 18: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Program flow

Camera Calibration

Capturing camera image

Geometric Registration

Synthesizing the CG and camera image

At once

Each frame

intrinsic parameters

camera image

extrinsic parameters

Page 19: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Synthesizing the CG and camera image

• Camera image and 3DCG model of drainage were synthesized on the basis of the intrinsic and extrinsic parameters using OpenGL

• OpenGL (Open source Graphics Library)– Library for 3D graphics

Intrinsicparameters

Extrinsicparameters

3DCG model of drainage

Camera image

Synthesized image

Page 20: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Result of reproducing drainage scene

Page 21: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Result

• The drainage scene was reproduced to the correct position at the most part.

• An average of execution time– 0.247 [s]

• An average of Estimation error– 6.758 [pixel]

Page 22: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

Conclusion

• In the future– The execution speed of this system will be improve using

other method of obtaining corresponding feature points such as the optical flow

– This system will be available even if the position of camera will be freely

– This system will be operated in actual Tsujun Bridge, and will be utilized for learning water environment

Page 23: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

End

Page 24: Development of a system to reproduce the drainage from Tsujun Bridge for environment education Hikari Takehara Kumamoto National College of Technology

SURF

• SURF (Speeded Up Robust Features)– The method extracts robust feature points for scaling and

rotation of image and describes feature quantity– In following image, the corresponding points is obtained

using SURF