Transcript 投影片 1 - NCCU

Video Special Effects
Wen-Hung Liao
10/3/2006
Outline



Hardware-based video special effects
Software-based video special effects
Video content analysis
Hardware-based VFX


Matrox RT.X2
http://www.matrox.com/video/ct/home.cfm
Real-time multi-layer workflows in HD and
SD: Designed primarily for real-time native
HDV and DV editing, Matrox RT.X2 also
provides a high-quality MPEG-2 4:2:2 I-frame
codec so you can capture other HD and SD
formats using RT.X2's analog inputs, and mix
all types of footage on the timeline in real
time.
Where to purchase?


http://www.voxelvision.com.tw/
http://www.avideo.com.tw/
Real-time CPU Effects










Realtime primary color correction
Realtime secondary color correction
Realtime chroma and luma keying
Realtime speed changes
Realtime transitions
Realtime track matte
Realtime move & scale
Realtime SD clip upscaling in an HD timeline
Realtime HD clip downscaling in an SD timeline
Native Adobe Premiere Pro effects
Real-time GPU Effects
















Realtime Adobe Motion effect
Realtime advanced 2D/3D DVE
Realtime shadow
Realtime blur/glow/soft focus
Realtime page curl
Realtime surface finish
Realtime pan & scan
Realtime mask
Realtime mask blur
Realtime mask mosaic
Realtime four-corner pin
Accelerated shine
Native Adobe Premiere Pro transitions
Realtime crystallize
Realtime lens flare
Realtime old movie effect
Graphics Processing Unit (GPU)


A Graphics Processing Unit or GPU (also
occasionally called Visual Processing Unit
or VPU) is a dedicated graphics rendering
device for a personal computer, workstation,
or game console.
Modern GPUs are very efficient at
manipulating and displaying computer
graphics, and their highly parallel structure
makes them more effective than typical CPUs
for a range of complex algorithms.
GPU Operations



A GPU implements a number of graphics primitive
operations in a way that makes running them much
faster than drawing directly to the screen with the
host CPU.
The most common operations for early 2D computer
graphics include the BitBLT operation (combine two
bitmap patterns using a RasterOp), usually in
special hardware called a "blitter", and operations
for drawing rectangles, triangles, circles, and arcs.
Modern GPUs also have support for 3D computer
graphics, and typically include digital video-related
functions as well.
Applications: Example 1

OpenVIDIA : GPU accelerated Computer
Vision Library,
http://openvidia.sourceforge.net/


The OpenVIDIA project implements computer
vision algorithms on computer graphics
hardware, using OpenGL and Cg.
The project provides useful example
programs which run real time computer vision
algorithms on single or parallel graphics
processing units.
Applications: Example 2

Real-time stereo using GPU

“... Since the GPU is built to process images it is
particularly well suited to perform some computer vision
and image processing algorithms very efficiently. We
developed a real-time stereo algorithm that runs on the
GPU and is several times faster than most CPU-based
implementations.”
Software-based Video Special
Effects

Examples:


EffectTV: http://effectv.sourceforge.net/
FreeFrame:
http://freeframe.sourceforge.net/gallery.html
RGB/YUV Conversion


http://www.fourcc.org/index.php?http%3A//www.four
cc.org/intro.php
RGB to YUV Conversion




Y = (0.257 * R) + (0.504 * G) + (0.098 * B) + 16
Cr = V = (0.439 * R) - (0.368 * G) - (0.071 * B) + 128
Cb = U = -(0.148 * R) - (0.291 * G) + (0.439 * B) + 128
YUV to RGB Conversion



B = 1.164(Y - 16) + 2.018(U - 128)
G = 1.164(Y - 16) - 0.813(V - 128) - 0.391(U - 128)
R = 1.164(Y - 16) + 1.596(V - 128)
Types of Special Effects





Applying to the whole image frame
Applying to part of the image (edges, moving
pixels,…)
Applying to a collection of frames (framebuffer)
Applying to detected areas
Overlaying virtual objects:


at pre-determined locations
in response to user’s position
Compressed-Domain
Processing


Video special effects editing in MPEG-2
compressed video
Fernando, W.A.C.; Canagarajah, C.N.; Bull,
D.R
Fade, dissolve and wipe production in
MPEG-2 compressed video
Fernando, W.A.C.; Canagarajah, C.N.; Bull,
D.R.;
Video Content Analysis



Event detection
For indexing/searching
To obtain high-level semantic description of
the content.
Image Databases



Problem: accessing and searching large databases
of images, videos and music
Traditional solutions: file IDs, keywords, associated
text.
Problems:





can’t query based on visual or musical properties
depends on the particular vocabulary used
doesn’t provide queries by example
time consuming
Solution: content-based retrieval using automatic
analysis tools (see http://wwwqbic.almaden.ibm.com)
Retrieval of images by similarity

Components:




Extraction of features or image signatures and efficient
representation and storage
A set of similarity measures
A user interface for efficient and ordered representation of
retrieved images and to support relevance feedback
Considerations



Many definitions of similarity are possible
User interface plays a crucial role
Visual content-based retrieval is best utilized when
combined with traditional search
Image features for similarity
definition

Color similarity





Similarity: e.g., “distance” between color histograms
Should use perceptually meaningful color spaces (HSV,
Lab...)
Should be relatively independent of illumination (color
constancy)
Locality:“find a red object such as this one
Texture similarity


Texture feature extraction (statistical models)
Texture qualities: directionality, roughness, granularity...
Shape Similarity
Must distinguish between similarity between actual geometrical
2-D shapes in the image and underlying 3-D shape
 Shape features: circularity, eccentricity, principal axis orientation...
Spatial similarity
 Assumes images have been (automatically or manually)
segmented into meaningful objects (symbolic image)
 Considers the spatial layout of the objects in the scene

Object presence analysis
 Is this particular object in the image?
Main components of retrieval
system

Database population: images and videos are
processed to extract features (color, texture, shape,
camera and object motion)

Database query: user composes query via graphic
user interface. Features are generated from
graphical query and input to matching engine

Relevance feedback: automatically adjusts existing
query using information fed back by user about
relevance of previously retrieved objects
Video parsing and
representation

Interaction with video using conventional
VCR-like manipulation is difficult - need to
introduce structural video analysis

Video parsing


Temporal segmentation into elemental units
Compact representation of elemental unit
Temporal segmentation


Fundamental unit of video manipulation: video shots
Types of transition between shots:





Abrupt shot change
Fades: slow change in brightness
Dissolve
Wipe: pixels from second shots replace those of previous
shot in regular patterns
Other factors of image change:


Motion, including camera motion and object motion
Luminosity changes and noise
Representation of Video

Video database population has three major components:
 Shot detection
 Representative frame creation for each shot
 Derivation of layered representation of coherently moving
structures/objects

A representative frame (R-frame) is used for:
 population: R-frame is treated as a still image for representation
 query: R-frames are basic units initially returned in video query


Choice of R-frame:
first - middle - last frame in video shot
sprite built by seamless mosaicing all frames in a shot
Video soundtrack analysis

Image/sound relationships are critical to the perception and
understanding of video content. Possibilities:
 Speech, music and Foley sound, detection and representation
 Locutor identification and retrieval
 Word spotting and labeling (speech recognition)
 A possible query could be: “find the next time this locutor is
again present in this soundtrack”

Video scene analysis

500-1000 shots per hours in typical movies
One level above shot: sequence or scene (a series of
consecutive shots constituting a unit from the narrative point of
view)
