Viewing page 3 of 5 pages.
Previous 1 2 3 4 5 Next
THE RESEARCH BEHIND THE DH-CAT
As with the G-CAT, the DH-CAT uses the opinions of real viewers to determine
what level of performance is acceptable. A number of factors are considered relevant to the viewing
experience: Dropped frames for playback, frame delay for streaming video, and
image quality for recording. Each of these factors was researched separately. The results are
summarized below:
Dropped Frames
Each test subject was asked to rate their viewing experience
on a five-point scale. All factors except the number of dropped frames were
held constant so that changes in the ratings could be attributed to the number
of dropped frames. All test subjects were shown the same 24 second video clip
under the same viewing conditions. At the end of it all, the results were
compiled and, on average, the acceptable threshold (rated "Fair" or above)
was found to be 88 dropped frames in a 720 frame video, or about 12%.
A maximum acceptable threshold for the number of dropped frames determines
what "acceptable" video quality is.
Frame Delay
A similar approach was used to determine acceptable
frame delay for streaming video. Viewers were shown a 24 second clip and
asked to rate the quality on a five point scale. This time, the independent
variable was the difference between actual playback time and theoretical playback
time. The threshold is around
a 12% deviation: Video quality was deemed unacceptable when the 24 second
video was delayed by more than 2.92 seconds.
Video streaming quality is determined by comparing theoretical vs. actual
playing time.
Image Quality
For recording or capturing video, image quality was identified as the most
important factor in user experience. But, how do you measure image quality?
Unlike dropped frames or frame delay, image quality cannot be easily quantified,
which makes it very difficult to measure.
Fortunately, the broadcast industry has studied this subject for years. Instead of duplicating this research, Intel adopted an existing standard: ITU
Standard J144. The research and perceptual models that it is based
on were carried out by a British company called Psytechnics,
and Intel has licensed their software for use in the DH-CAT. The software
works in much the same way as the G-CAT: It is a mathematical model
based on a database of viewers' responses.
Psytechnics' software rates image quality on a five point "Mean Opinion Score". The Mean Opinion Score is supposed to reflect the amount of degradation from
an original reference source, not an "absolute" measurement of the
video quality. This removes the possibility that the image content might affect
the final score. A perfect quality score would be given to a video that is
identical to the original source. Any deviation from this source is assumed
to be unwanted and thus reduces the final score.
Four basic factors are taken into account:
- Spatial Frequency Analysis: A mathematical comparison of the degraded
video with the original source.
- Color Analysis: Measures how well the degraded video maintains
the color information in the original source.
- Texture Analysis: Measures how much detail is maintained.
- Contour Analysis: Measures how well sharp edges are displayed.
Also takes into account video "blocking", where rapid movement appears as
a mosaic of squares.
A complex mathematical model maps measurable changes in image quality
to the opinions of actual viewers.
Because image quality is evaluated based on Psytechnics' methods, it is the
only part of the tool that does not belong to Intel. Intel will be making pieces of DH-CAT’s code available to developers, but their tools won’t be “open-source” in the GPL sense of that term. Developers will have access to the code, and can modify it in order to make improvements. They will able to make more of the code available to developers, but the term for obtaining the source code won’t be GPL.
| Help support this site, buy from one of our affiliate retailers! |
|
