Copyright © 2003 Texas Instruments. All rights reserved. DSP C5000 Chapter 18 Image Compression and Hardware Extensions.

Slides:



Advertisements
Similar presentations
TWO STEP EQUATIONS 1. SOLVE FOR X 2. DO THE ADDITION STEP FIRST
Advertisements

Polyphase FIR Filter Implementation for Communication Systems
Chapter 19 Fast Fourier Transform
Chapter 5 Assembly Language
DSP C5000 Chapter 16 Adaptive Filter Implementation Copyright © 2003 Texas Instruments. All rights reserved.
Using Matrices in Real Life
Low-Complexity Transform and Quantization in H.264/AVC
Copyright © 2003 Pearson Education, Inc. Slide 1 Computer Systems Organization & Architecture Chapters 8-12 John D. Carpinelli.
Copyright © 2006 by The McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill Technology Education Copyright © 2006 by The McGraw-Hill Companies,
Chapter 1 The Study of Body Function Image PowerPoint
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 4 Computing Platforms.
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 1 Embedded Computing.
Copyright © 2011, Elsevier Inc. All rights reserved. Chapter 5 Author: Julia Richards and R. Scott Hawley.
Copyright © 2011, Elsevier Inc. All rights reserved. Chapter 4 Author: Julia Richards and R. Scott Hawley.
FIGURE 10.1 Graphics Overview.. FIGURE 10.2 Display Pipes.
1 Copyright © 2010, Elsevier Inc. All rights Reserved Fig 2.1 Chapter 2.
1 Copyright © 2013 Elsevier Inc. All rights reserved. Chapter 38.
1 Chapter 40 - Physiology and Pathophysiology of Diuretic Action Copyright © 2013 Elsevier Inc. All rights reserved.
By D. Fisher Geometric Transformations. Reflection, Rotation, or Translation 1.
Chapter 1 Image Slides Copyright © The McGraw-Hill Companies, Inc. Permission required for reproduction or display.
Business Transaction Management Software for Application Coordination 1 Business Processes and Coordination.
Jeopardy Q 1 Q 6 Q 11 Q 16 Q 21 Q 2 Q 7 Q 12 Q 17 Q 22 Q 3 Q 8 Q 13
Jeopardy Q 1 Q 6 Q 11 Q 16 Q 21 Q 2 Q 7 Q 12 Q 17 Q 22 Q 3 Q 8 Q 13
Title Subtitle.
0 - 0.
DIVIDING INTEGERS 1. IF THE SIGNS ARE THE SAME THE ANSWER IS POSITIVE 2. IF THE SIGNS ARE DIFFERENT THE ANSWER IS NEGATIVE.
SUBTRACTING INTEGERS 1. CHANGE THE SUBTRACTION SIGN TO ADDITION
MULT. INTEGERS 1. IF THE SIGNS ARE THE SAME THE ANSWER IS POSITIVE 2. IF THE SIGNS ARE DIFFERENT THE ANSWER IS NEGATIVE.
Addition Facts
How Much Do I Remember? Are you ready to play.....
ZMQS ZMQS
Chapter 9 Bootloader.
ABC Technology Project
Chapter 21b Reference Frameworks. Dr. Naim Dahnoun, Bristol University, (c) Texas Instruments 2004 Chapter 21b, Slide 2 Learning Objectives Introduce.
Multimedia System Video
© Charles van Marrewijk, An Introduction to Geographical Economics Brakman, Garretsen, and Van Marrewijk.
© Charles van Marrewijk, An Introduction to Geographical Economics Brakman, Garretsen, and Van Marrewijk.
Squares and Square Root WALK. Solve each problem REVIEW:
Introduction to H.264 / AVC Video Coding Standard Multimedia Systems Sharif University of Technology November 2008.
JPEG Compresses real images Standard set by the Joint Photographic Experts Group in 1991.
Chapter 5 Test Review Sections 5-1 through 5-4.
Addition 1’s to 20.
25 seconds left…...
Test B, 100 Subtraction Facts
Chapter 18 Discrete Cosine Transform. Dr. Naim Dahnoun, Bristol University, (c) Texas Instruments 2004 Chapter 18, Slide 2 Learning Objectives  Introduction.
Week 1.
Chapter 20 This chapter provides a series of applications. There is no daughter cards with the DSK6713 and DSK6416 Part 1: Applications using the PCM3003.
We will resume in: 25 Minutes.
1 Unit 1 Kinematics Chapter 1 Day
How Cells Obtain Energy from Food
INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS, ICT '09. TAREK OUNI WALID AYEDI MOHAMED ABID NATIONAL ENGINEERING SCHOOL OF SFAX New Low Complexity.
JPEG.
T.Sharon-A.Frank 1 Multimedia Image Compression 2 T.Sharon-A.Frank Coding Techniques – Hybrid.
Still Image Conpression JPEG & JPEG2000 Yu-Wei Chang /18.
JPEG C OMPRESSION A LGORITHM I N CUDA Group Members: Pranit Patel Manisha Tatikonda Jeff Wong Jarek Marczewski Date: April 14, 2009.
Introduction to JPEG Alireza Shafaei ( ) Fall 2005.
Performance Enhancement of Video Compression Algorithms using SIMD Valia, Shamik Jamkar, Saket.
DSP C5000 Chapter 16 Adaptive Filter Implementation Copyright © 2003 Texas Instruments. All rights reserved.
Copyright © 2003 Texas Instruments. All rights reserved. DSP C5000 Chapter 18 Image Compression and Hardware Extensions.
CS654: Digital Image Analysis
Implementing JPEG Encoder for FPGA ECE 734 PROJECT Deepak Agarwal.
Media Compression.
JPEG Compression What is JPEG? Motivation
JPEG Image Coding Standard
CIS679: MPEG MPEG.
ENEE 631 Project Video Codec and Shot Segmentation
VLIW DSP vs. SuperScalar Implementation of a Baseline H.263 Encoder
Standards Presentation ECE 8873 – Data Compression and Modeling
The JPEG Standard.
Presentation transcript:

Copyright © 2003 Texas Instruments. All rights reserved. DSP C5000 Chapter 18 Image Compression and Hardware Extensions

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 2 Image Compression Discrete Cosine Transform (DCT) based compression Discrete Cosine Transform (DCT) based compression Still image: JPEG. Still image: JPEG. Remove spatial redundancy Remove spatial redundancy Video: H263, MPEG4. Video: H263, MPEG4. Remove spatial redundancy Remove spatial redundancy Remove temporal redundancy Remove temporal redundancy

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 3 JPEG Encoder Image is split into 8x8 pixel block that are processed. Image is split into 8x8 pixel block that are processed. DCT is applied on input block to obtain the frequency data. DCT is applied on input block to obtain the frequency data. Values are read from low to high frequency thanks to zig-zag addressing. Values are read from low to high frequency thanks to zig-zag addressing. Data are then quantized according to a quality factor. Data are then quantized according to a quality factor. This output is then run length and entropy coded. This output is then run length and entropy coded.

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 4 JPEG Decoder Data are entropy decoded. Data are entropy decoded. They are dequantized according to a quality factor. They are dequantized according to a quality factor. Zig-zag addressing to re-order the data pixel by pixel. Zig-zag addressing to re-order the data pixel by pixel. Inverse DCT to recover spatial data. Inverse DCT to recover spatial data.

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 5 H263 and MPEG4 encoder Same basic building blocks Same basic building blocks Hardware accelerator provided by C5509/10

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 6 H263 and MPEG4 Decoder Same basic building blocks Same basic building blocks Hardware accelerator provided by C5509/10

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 7 Hardware Extensions C5509 and C5510 provide H/W extensions for video compression: C5509 and C5510 provide H/W extensions for video compression: DCT, IDCT DCT, IDCT Pixel interpolation Pixel interpolation Motion estimation Motion estimation Hardware extensions are embedded co- processors: Hardware extensions are embedded co- processors: Access to ACx, DARAM and SARAM. Access to ACx, DARAM and SARAM. Provide video codec with less than half of the processing bandwidth. Provide video codec with less than half of the processing bandwidth.

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 8 DCT H/W Extension 1 of 5 Allows 4x4 and 8x8 pixels DCT/IDCT computation: Allows 4x4 and 8x8 pixels DCT/IDCT computation: 2D DCT 2D DCT 2D IDCT 2D IDCT

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 9 DCT H/W Extension 2 of 5 Basic steps to complete a 2D DCT/IDCT: Basic steps to complete a 2D DCT/IDCT: Input Data: macro block (4x4 or 8x8) is read in (DCT). DCT coefficient matrix is read in (IDCT). Input Data: macro block (4x4 or 8x8) is read in (DCT). DCT coefficient matrix is read in (IDCT). Column DCT/IDCT process: output to temporary registers that will be transposed for Row processing. Column DCT/IDCT process: output to temporary registers that will be transposed for Row processing. Row DCT/IDCT process: data read from temporary register which are processed column by column. Row DCT/IDCT process: data read from temporary register which are processed column by column.

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 10 DCT H/W Extension 3 of 5

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 11 DCT H/W Extension 4 of 5 Instruction set: Instruction set: Load+computation+transfer to accumulator: Load+computation+transfer to accumulator:ACy=copr(k8,ACx,Xmem,Ymem) Computation+transfer to accumulator+memory write: Computation+transfer to accumulator+memory write:ACy=copr(k8,ACx,ACy),Lmem=Acz Special instructions: Special instructions:ACy=copr(k8,ACx,ACy) Refer to application note for details and listings of macros realizing complete 8x8 DCT/IDCT. Refer to application note for details and listings of macros realizing complete 8x8 DCT/IDCT.application noteapplication note

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 12 DCT H/W Extension 5 of 5 H/W extensions can be used through C- callable functions provided by IMLIB H/W extensions can be used through C- callable functions provided by IMLIBIMLIB

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 13 Debug To look at the internal register of the hardware extension …To look at the internal register of the hardware extension … DCT and IDCT Hardware accelerator registers

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 14 Tutorial DCT/IDCT with IMLIB Describe step by step how to use H/W extensions with IMLIB. Describe step by step how to use H/W extensions with IMLIB. Requires installation of IMLIB before continuing. Requires installation of IMLIB before continuing.IMLIB Requires special memory configuration to obtain optimum performance. Requires special memory configuration to obtain optimum performance. CCS allows display of image contained in DSP memory. CCS allows display of image contained in DSP memory.

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 15 Memory Configuration dct.cmd hwdct.cdb

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 16 Display Input Image 1 of 2 Load hwdct.pjt Load hwdct.pjt Build and load application Build and load application Input image is « goldhill » 128x128 which is included by the header file ( #include «imagesample.h» ) at the address goldhill Input image is « goldhill » 128x128 which is included by the header file ( #include «imagesample.h» ) at the address goldhill To have the internal memory initialized use Debug>go to main command. To have the internal memory initialized use Debug>go to main command. You are now ready to display the input image using view>Graph>image You are now ready to display the input image using view>Graph>image

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 17 Display Input Image 2 of 2

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 18 In place DCT Computation

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 19 Actual dct.c Program

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 20 Output Display and Initialization

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 21 Output Buffer Update

Copyright © 2003 Texas Instruments. All rights reserved. ESIEE, Slide 22 References JPEG for digital panel (SPRA664) JPEG for digital panel (SPRA664)SPRA664 TMS320C55x Hardware extensions for image/video applications - Programmers reference (SPRU098) TMS320C55x Hardware extensions for image/video applications - Programmers reference (SPRU098)SPRU098 TMS320C55x image/video processing library programmers reference (SPRU037) TMS320C55x image/video processing library programmers reference (SPRU037)SPRU037