CUDA

Report
Object Oriented Framework for
CUDA based Image Processing
Pritam Prakash Shete, Venkat P. P. K., Dinesh M. Sarode,
Mohini Laghate, S. K. Bose & R. S. Mundada,
Bhabha Atomic Research Centre, Mumbai, India
International Conference on Communication, Information & Computing Technology (ICCICT)
Oct. 19-20,2012, Mumbai, India
Keywords: Object oriented framework, CUDA,
design patterns, image processing
組員名單:
P76004588
P76004423
P76014216
徐華煊
曾郁凱
吳品頡
1
1. Introduction
• Compute Unified Device Architecture (CUDA)
– CUDA is a novel and promising GPU programming frame work from NVIDIA.
– The CUDA has been speedup many computationally intensive graphics as well
as nongraphic
• Essential for a seamless panoramic mosaic
– A pyramidal image blending algorithm
• Our goal
– To show that use of design patterns facilitate extending existing functionality
by adding new classes, rather than modifying an existing classes or
functionality
2
1. Introduction
- Panoramic Mosaic
3
1. Introduction
- Finding Key Point
4
2. Analysis and Design
- Gaussian Blur Operation
5
2. Analysis and Design
- Laplacian Pyramid
 doubles for
the next octave
σ=2*1.6σ=1.6
High frequency
σ=k4*1.6
σ=k3*1.6
k = 2(1/s)
s: Image per octave
s = 3 in this case
σ=k2*1.6
σ=k*1.6
σ=1.6
σ=k-1*1.6
Gaussian filter
D(σ)
L(σ)
L( x, y, )  G( x, y, ) * I ( x, y)
G ( x, y ,  ) 

1
2
2
exp
( x2  y 2 )
2 2
DoG filter
n  1,2,, s
D( x, y, k ( n1) )
 (G( x, y, k  )  G( x, y, k  )) * I ( x, y )
n
( n 1 )
 L( x, y, k n )  L( x, y, k ( n1) )
6
2. Analysis and Design
- Remove Edges Response
7
3. Implementation
- Modules
• Image Blending Library (IBL): They developed framework for
CUDA based image processing.
• This frame work offers 3 modules for an image processing:
1) CPU Module
2) Simple-CUDA Module
3) IO-CUDA Module
8
3. Implementation
- Modules
1) CPU Module
– Using single thread
– Implementation function:
1. Gaussian blur
2. Laplacian pyramid
3. REDUCE operation
4. EXPAND operation
9
3. Implementation
- Modules
2) Simple-CUDA Module
CPU
CPU
Memory
Send Return
image image
GPU
Global
Memory
Process
Image
10
3. Implementation
- Modules
3) IO-CUDA Module
GPU
Image already get
Global
Memory
Send Return
image image
Shared
Memory
Process
Image
11
3. Implementation
- Automatic Image Conversion
• Visitor Design pattern
– Image type: CPUBuffer image and CUDABuffer image
Output: CUDABuffer
Concrete Element
Element
Concrete Element
Concrete Visitor
Visitor
Concrete Visitor
Output: CPUBuffer
12
3. Implementation
- Image Source Integration
• General Hierarchy Pattern
13
3. Implementation
- Extensible Architecture
• Construction of Gaussian & Laplacian Pyramid
14
3. Implementation
- Extensible Architecture
• Building the Gaussian pyramid
– Non modifiable code along with placeholders for extending it
• Using Factory Method pattern placeholders
– Creating the image buffer
– Gaussian blur
– REDUCE operation
• Realized by the respective subclasses
– Ex. CPUBlendingFactory
– Ex. IOCUDABlendingFactory
15
3. Implementation
- Extensible Architecture
• Combine Pyramid Operation
16
3. Implementation
- Extensible Architecture
• Combine Pyramid Operation
– Validating an input pyramids
– Allocating memory for an output pyramid
– Combining high pass and low pass images
• The Template Method pattern is used to define the
skeleton
• Combining high pass images and low pass image are
placeholder or extension points
• Subclasses redefine combining high pass and low pass
images without changing basic algorithm structure
– Ex. CPUCombinePyramidOperation
– Ex. IOCUDACombinePyramidOperation
17
4. Result
• Specification
– Intel Core 2 Duo with E8400 3.00 GHz processor
– 2GB RAM
– NVIDIA’s Quadro FX 4600
– Input images covers low resolution (128x128) as well as a
high resolution (2048x2048)
18
4. Result
• Panoramic image stitching
19
4. Result
• CUDA based modules perform much better than the CPU
module
• Simple-CUDA
– Device global memory
• IO-CUDA module
– Fast on-chip shared memory
20
5. Conclusion
• Implemented an object oriented framework for a
GPU based image processing
• Using software engineering principles and design
patterns
• Extending the framework for computation using the
GPU memory
21
THANK YOU
22

similar documents