video analysis
Skip this Video
Download Presentation
Video Analysis

Loading in 2 Seconds...

play fullscreen
1 / 61

Video Analysis - PowerPoint PPT Presentation

  • Uploaded on

Video Analysis. Mei-Chen Yeh May 29, 2012. Outline. Video representation Motion Actions in Video. Videos. A natural video stream is continuous in both spatial and temporal domains. A digital video stream sample pixels in both domains. Video processing. YC b C r. YC b C r.

I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
Download Presentation

PowerPoint Slideshow about ' Video Analysis' - dyre

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
video analysis

Video Analysis

Mei-Chen Yeh

May 29, 2012

  • Video representation
  • Motion
  • Actions in Video
  • A natural video stream is continuous in both spatialand temporaldomains.
  • A digital video stream sample pixels in both domains.
video signal representation 1
Video signal representation (1)
  • Composite color signal
    • R, G, B
    • Y, Cb, Cr
  • Why Y, Cb, Cr?
    • Backward compatibility (back-and-white to color TV)
    • The eye is less sensitive to changes of Cb and Cr components




(Cb + Cr)

video signal representation 2
Video signal representation (2)
  • Y is the luma component and Cband Cr are the blue and red chromacomponents.




sampling formats 1
Sampling formats (1)


4:2:2 (DVB)

4:1:1 (DV)

Slide from Dr. Ding

sampling formats 2
Sampling formats (2)

4:2:0 (VCD, DVD)

tv encoding system 1
TV encoding system (1)
  • PAL
    • Phase Alternating Line, is a color encoding system used in broadcast television systems in large parts of the world.
    • (French: SéquentialCouleur Avec Mémoire), is an analog color television system first used in France.
  • NTSC
    • National Television System Committee, is the analog television system used in most of North America, South America, Burma, South Korea, Taiwan, Japan, Philippines, and some Pacific island nations and territories.
uncompressed bitrate of videos
Uncompressed bitrate of videos

Slide from Dr. Chang

  • Video representation
  • Motion
  • Actions in Video
motion and perceptual organization
Motion and perceptual organization
  • Sometimes, motion is foremost cue
motion and perceptual organization1
Motion and perceptual organization
  • Even poor motion data can evoke a strong percept
motion and perceptual organization2
Motion and perceptual organization
  • Even poor motion data can evoke a strong percept
uses of motion
Uses of motion
  • Estimating 3D structure
  • Segmenting objects based on motion cues
  • Learning dynamical models
  • Recognizing events and activities
  • Improving video quality (motion stabilization)
  • Compressing videos
  • ……
motion field
Motion field
  • The motion field is the projection of the 3D scene motion into the image
motion field1
Motion field




  • P(t) is a moving 3D point
  • Velocity of scene point:
    • V = dP/dt
  • p(t) = (x(t),y(t)) is the projection of P in the image
  • Apparent velocity v in the image:
    • vx = dx/dt
    • vy = dy/dt
  • These components are known as the motion field of the image




motion estimation techniques
Motion estimation techniques
  • Based on temporal changes in image intensities
  • Direct methods
    • Directly recover image motion at each pixel from spatio-temporal image brightness variations
    • Dense motion fields, but sensitive to appearance variations
    • Suitable when image motion is small
  • Feature-based methods
    • Extract visual features (corners, textured areas) and track them over multiple frames
    • Sparse motion fields, but more robust tracking
    • Suitable when image motion is large
optical flow
Optical flow
  • The velocity of observed 2-D motion vectors
  • Can be caused by
    • object motions
    • camera movements
    • illumination condition changes
optical flow the true motion field
Optical flow the true motion field

No motion field but shading changes

Motion field exists but no optical flow

problem definition optical flow

Key assumptions

    • color constancy: a point in Itlooks the same in It+dt
      • For grayscale images, this is brightness constancy
    • small motion: points do not move very far
  • This is called the optical flowproblem.
Problem definition: optical flow

How to estimate pixel motion from image I(x,y,t) to image I(x,y,t+dt)?

  • Solve pixel correspondence problem
    • given a pixel in It, look for nearby pixels of the same color in It+dt
optical flow constraints grayscale images
Optical flow constraints (grayscale images)

Let’s look at these constraints more closely:

  • brightness constancy:
  • small motion: (u and v are small)
    • using Taylor’s expansion

= 0

optical flow equation
Optical flow equation
  • Combining these two equations
  • Dividing both sides by dt

u, v: displacement vectors

velocity vector

spatial gradient vector

Known as the optical flow equation


Q: how many unknowns and equations per pixel?

    • 2 unknowns, one equation
  • What does this constraint mean?
    • The component of the flow perpendicular to the gradient (i.e., parallel to the edge) is unknown



  • If (vx,vy) satisfies the equation, so does (vx+u’, vy+v’) if





Q: how many unknowns and equations per pixel?

    • 2 unknowns, one equation
  • What does this constraint mean?
    • The component of the flow perpendicular to the gradient (i.e., parallel to the edge) is unknown

This explains the Barber Pole illusion



the aperture problem
The aperture problem

Perceived motion

the barber pole illusion
The barber pole illusion

the barber pole illusion1
The barber pole illusion

to solve the aperture problem
To solve the aperture problem…
  • We need more equations for a pixel.
  • Example
    • Spatial coherence constraint: pretends the pixel’s neighbors have the same (vx,vy)
    • Lucas & Kanade (1981)
  • Video representation
  • Motion
  • Actions in Video
    • Background subtraction
    • Recognition of actions based on motion patterns

Using optical flow:recognizing facial expressions

Recognizing Human Facial Expression (1994)

by YaserYacoob, Larry S. Davis

example use of optical flow visual effects in films
Example use of optical flow: visual effects in films

background subtraction
Background subtraction
  • Simple techniques can do ok with static camera
  • …But hard to do perfectly
  • Widely used:
    • Traffic monitoring (counting vehicles, detecting & tracking vehicles, pedestrians),
    • Human action recognition (run, walk, jump, squat),
    • Human-computer interaction
    • Object tracking
pros and cons
Pros and cons


  • Extremely easy to implement and use
  • Fast
  • Background models need not be constant, they change over time


  • Accuracy of frame differencing depends on object speed and frame rate
  • Median background model: relatively high memory requirements
  • Setting global threshold Th…

Slide credit: BirgiTamersoy

background subtraction with depth
Background subtraction with depth

How can we select foreground pixels based on depth information?


  • Video representation
  • Motion
  • Actions in video
    • Background subtraction
    • Recognition of action based on motion patterns
motion analysis in video
Motion analysis in video
  • “Actions”: atomic motion patterns -- often gesture-like, single clear-cut trajectory, single nameable behavior (e.g., sit, wave arms)
  • “Activity”: series or composition of actions (e.g., interactions between people)
  • “Event”: combination of activities or actions (e.g., a football game, a traffic accident)

Modifiedfrom VenuGovindaraju


human activity in video basic approaches
Human activity in video:basic approaches
  • Model-based action/activity recognition:
    • Use human body tracking and pose estimation techniques, relate to action descriptions
    • Major challenge: accurate tracks in spite of occlusion, ambiguity, low resolution
  • Activity as motion, space-time appearance patterns
    • Describe overall patterns, but no explicit body tracking
    • Typically learn a classifier
    • We’ll look at a specific instance…

The 30-Pixel Man

  • Recognize actions at a distance [ICCV 2003]
    • Low resolution, noisy data, not going to be able to track each limb.
    • Moving camera, occlusions
    • Wide range of actions (including non-periodic)

[Efros, Berg, Mori, & Malik 2003]

  • Motion-based approach
    • Non-parametric; use large amount of data
    • Classify a novel motion by finding the most similar motion from the training set
  • More specifically,
    • A motion description based on optical flow
    • an associated similarity measure used in a nearest neighbor framework

[Efros, Berg, Mori, & Malik 2003]

motion description matching results
Motion description matching results

More matching results: video 1, video 2

gathering action data
Gathering action data
  • Tracking
    • Simple correlation-based tracker
    • User-initialized
figure centric representation
Figure-centric representation
  • Stabilized spatio-temporal volume
    • No translation information
    • All motion caused by person’s limbs, indifferent to camera motion!
using optical flow action recognition at a distance
Using optical flow:action recognition at a distance

Extract optical flow to describe the region’s motion.

[Efros, Berg, Mori, & Malik 2003]

using optical flow action recognition at a distance1
Using optical flow:action recognition at a distance





Use nearest neighbor classifier to name the actions occurring in new video frames.

[Efros, Berg, Mori, & Malik 2003]

football actions classification
Football Actions: classification

[.67 .58 .68 .79 .59 .68 .58 .66]

(8 actions, 4500 frames, taken from 72 tracked sequences)

application motion retargeting
Application: motion retargeting


[Efros, Berg, Mori, & Malik 2003]

  • Background subtraction:
    • Essential low-level processing tool to segment moving objects from static camera’s video
  • Action recognition:
    • Increasing attention to actions as motion and appearance patterns
    • For constrained environments, relatively simple techniques allow effective gesture or action recognition
closing remarks
Closing remarks
  • Thank you all for your attention and participation to the class!
  • Please be well prepared for the final project (06/12 and 06/19). Come to class on time. Start early!