Upload
marcia-webb
View
221
Download
0
Embed Size (px)
DESCRIPTION
Problem Formulation The digital video capture devices such as DVs are made more affordable for end users. It’s interesting to shoot videos but frustrating for editing them. There’s still a tremendous barrier between amateurs (home users) and the powerful video editing software. Finally people leave their precious shots in piles of DV tapes without editing and management. Type I home video: memorial Type II home video: recreational
Citation preview
Automatic Video Authoring with Media Analysis
2003/11/25
Chen-hsiu HuangAdvisor: Dr. Ja-Ling Wu
Outline Problem formulation Solutions and framework Expectations Status report Demonstration Questions and discuss
Problem Formulation The digital video capture devices such as DVs are made m
ore affordable for end users. It’s interesting to shoot videos but frustrating for editing the
m. There’s still a tremendous barrier between amateurs (home
users) and the powerful video editing software. Finally people leave their precious shots in piles of DV tape
s without editing and management. Type I home video: memorial Type II home video: recreational
According to a survey on DVworld*, the relations between the video length and how many times will user review them after days:
People are inpatient for videos without scenario or voice-over, especially for those with no music.
Video clips with no more then 5 minutes are best for human’s concentration.
Video length Review times
>= 1 hr 1 or 0
30 min ~ 1 hr 2 ~ 3
15 ~ 30 min 5 ~ 10
5 ~ 15 min >= 10
<= 5 min You take it out and watch it when you think about!
*http://www.DVworld.com.tw/
Solutions and Framework A consumer product called “muvee autoProducer” has bee
n announced to ease the burden of professional video editing.
The application scenario is quite simple: Pickup a video Choose your music Produce musical video!
Although there are commercial products in the market, only few academic publications related.
Goal: To achieve the near or beyond quality in the similar application scenario with the content-analysis technologies developed in multimedia domain.
Jump!
Input video
Input music
Shot changeScene change
Audio segment
cutting
Alignment
Output Video
VolumeZCR
BrightnessBandwidth
…
Human faceFlash light
Motion strengthColor variance
Edgeness...
Scene selectionKey shot selection
Audio rhythm &Video motion/color
synchronization
Framework of AVAMA system
Currently finished
Expectations Quality results Time & space complexity consideration
Must not take too longer to make a video Must not consume too much memory
Complete consumer software implementation Deal with MPEG-1/2 videos and MPEG-1 Layer 1/2/3 audios
directly without pre-processing Simple application scenario to produce videos
The need of different profile? Is semi-automatic necessary?
Status Report Audio Cutting:
Cutting with zero-crossing rate (not so good) Cutting with dramatic volume change (great results) Brightness, bandwidth, ...
Video Segmentation: Shot change detection by pixel MAD Detect scenes with flash light event Detect fast motion scenes
Longer fast motion scenes means author’s tracing some objects Short fast motion scenes may due to
Detect human face information (time complexity?)
Demonstration
Questions and Discuss Any comments are welcomed. Special thanks for Mr. 劉嘉倫 , for his videos and suggesti
ons. Thanks friends in DVworld who provide lots of ideas and co
mments.
Create Music Videos using Automatic Media Analysis, ACM Multimedia, 2002
Let’s see its demo!
Back