Download A Fast MB Mode Decision Algorithm for MPEG-2 to H.264 P

A FAST MB MODE DECISION
ALGORITHM FOR MPEG-2 TO
H.264 P-FRAME TRANSCODING
PEDRO CUENCA, MEMBER, IEEE,
LUIS OROZCO-BARBOSA, MEMBER, IEEE,
GERARDO FERNÁNDEZ-ESCRIBANO,
ANTONIO GARRIDO,
HARI KALVA
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS
FOR VIDEO TECHNOLOGY, 2008
Outline
2




Introduction
Fast MB Mode Decision Using Machine Learning
Performance Evaluation
Conclusion
Introduction
1/3
3

Motivation:
make transcoding from MPEG-2 to H.264 seamless.

Hypothesis:
the MB mode decision in H.264 have a correlation with the
distribution of the motion compensated residual in MPEG-2
video.
Introduction
2/3
4
the H.264 MB mode computation
problem is posed as a data
classification problem.

the MPEG-2 MB coding mode
and residual have to be classified
into one of the several H.264
coding modes.

Fig. 1. Relationship between MPEG-2 MB
residual and H.264 MB coding mode.
Introduction
3/3
5

Method:
use machine learning tools to exploit the correlation and
construct decision trees to classify the MPEG-2 MBs into one of
the coding modes in H.264.
6
Fast MB Mode Decision
Using Machine Learning
1/14
Fig. 2. Process for building decision trees for
MPEG-2 to H.264 transcoding.
7
Fast MB Mode Decision
Using Machine Learning
2/14

WEKA data mining tool :
machine learning software written
in Java and supports several
standard data mining tasks.

the J48 algorithm:
implemented in the WEKA data mining tool was used to
create the WEKA decision trees.
 the J48 algorithm is an implementation of the C4.5
algorithm which widely used as a reference for building
decision trees.

8
Fast MB Mode Decision
Using Machine Learning
3/14

Attribute-Relation File Format (ARFF):
The file used by the WEKA data mining program, contain the
existing relationship between a set of attributes.
An ARFF file has two sections:
(1) header: contains the name of the relation, the attributes
and their types.
(2) section: containing the data.
9
Fast MB Mode Decision
Using Machine Learning
4/14

Training sets:

the MPEG-2 sequences encoded at high quality since no
B-frames have been used.
 use
H.264 encoder with a QP of 25 and the R-D
optimization enable.

Goal:
develop a single, generalized, decision tree to be used for the
MPEG-2 to H.264 transcoding process. It’s found that Flower
sequence was good for a large number of videos.
10
Fast MB Mode Decision
Using Machine Learning
5/14

The Decision Tree for the proposed transcoder is a hierarchical
decision tree consisting of three different WEKA trees.
Fig. 3. Decision tree.
11
Fast MB Mode Decision
Using Machine Learning
6/14
A. Creating the Training Files



mean and variance of each one
of the 4x4 residual subblocks.
MB mode in MPEG-2.
coded block pattern (CBPC) used
in MPEG-2.
12
Fast MB Mode Decision
Using Machine Learning
7/14
B. Decision Tree
decision tree
Works as follow
Node 1
Input: MPEG-2 MB information.
Output: First level decision that classifies the MB as Skip, Intra, Inter8x8 or Inter-16x16.
Rule:
MPEG-2 MB mode
H.264 MB mode
MC not coded
Inter-16x16
intra
Intra or Inter-8X8
skip
skip
13
Fast MB Mode Decision
Using Machine Learning
8/14
B. Decision Tree
decision tree
Node 2
Works as follow
Input: 16x16 MBs classified by the Node 1.
Output: 16x16 submode decision used for coding the MB into
16x16, 16x8 or 8x16.
Rule: This tree examines if there are continuous 16x8 or 8x16
subblocks that might result in a better prediction.
14
Fast MB Mode Decision
Using Machine Learning
9/14
B. Decision Tree
decision tree
Node 3
Works as follow
Input: The MBs classified by Node 1 as 8x8.
Output: 8x8 submode decision used for coding the MB into
8x8, 8x4, 4x8 or 4x4.
Rule:
(1)Evaluates only the H.264 8x8 modes using the third WEKA tree
and selects the best option.
(2)This node is different from the others since this one only uses four
means and four variances to make the decision.
15
Fast MB Mode Decision
Using Machine Learning
10/14
B. Decision Tree
decision tree
Node 4
Works as follow
Input:
(1) skip-mode MBs in the MPEG-2 bit stream classified by Node 1
(2) the 16x16 MBs classified by Node 2
Output: Select skip or inter-16x16.
Rule: Evaluates only the H.264 16x16 mode (without the submodes
16x8 or 8x16). Then, the node selects the best option.
16
Fast MB Mode Decision
Using Machine Learning
11/14


MB mode decision and threshold used in the
decision tree depend on the QP used in the
H.264 encoding stage.
The mean and variance threshold will have to
be different at each QP.
17
Fast MB Mode Decision
Using Machine Learning
12/14
Solution(1):
method: Develop the decision trees for each QP and use the
appropriate decision tree depending on the QP
selected.
drawback: It's complex since implies to switch between 52
different decision trees resulting in 156 WEKA
trees for a transcoder.
18
Fast MB Mode Decision
Using Machine Learning
13/14
Solution(2):
method:
 Develop a single decision tree and adjust the mean and
variance threshold used by the trees based on the QP of
25.

For QP values higher than 25, the thresholds are
decreased and for QP values lower than 25 thresholds
are oportionally increased. The threshold are adjusted by
2.5% for a change in QP of 1.
19
Fast MB Mode Decision
Using Machine Learning
14/14
Fig. 2. Process for building decision trees
for MPEG-2 to H.264 transcoding
.
.
Fig. 4. Proposed transcoder
Performance Evaluation
1/8
20
Input:
(1) A high quality MPEG-2 video.
(2) QP ranging from 5 up to 45 in steps of 5.
(3) The size of the GOP is 12 frames;where the first
frame was I-frame, and the rest of the frames were
P-frames.
(4) The rate control and CABAC algorithms were disabled for
all the simulations.
(5) The number of reference in P-frames was set to 1.
(6) The motion search range was set to 16 pels with a MV
resolution of 1/4 pel.
Performance Evaluation
2/8
21
Fig. 6. MB mode decisions generated by the proposed algorithm for the first
P-frame in the Ayersroc, Paris, and Foreman sequence.
Full estimation
of H.264
Proposed
algorithm
Performance Evaluation
3/8
22
RD-results:
R-D-cost without FME option
or R-D-cost with FME option
Test sequence:
Martin, Ayersroc, Paries,
Tempete, News, Foreman
Fromat:
CCIR, CIF, QCIF
Performance Evaluation
4/8
23
Performance Evaluation
5/8
24
RD-results:
SAE-cost without FME option
or SAE-cost with FME option
Performance Evaluation
6/8
25
Performance Evaluation
7/8
26
Reference
transcoder
Proposed
transcoder
WIN
Performance Evaluation
8/8
27
Conclusion
28


The proposed algorithm uses machine learning
techniques to develop decision tree decide MPEG-2
to H.264 coding mode, considerably reducing the
computational complexity .
It can be applied to develop other transcoders as
well.