computer science engineering lee sang seon. introduction basic notions for temporal video...

32
Temporal Video Boundaries Computer Science Engineering Lee Sang Seon

Upload: brice-glenn

Post on 17-Dec-2015

227 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Temporal Video Bound-aries

Computer Science EngineeringLee Sang Seon

Page 2: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

WhyTemporal Video Boundaries

Techniqueis useful in the

Video content analysis?

Page 3: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Index

Introduction Basic notions for temporal video boundaries Micro-Boundaries Macro-Boundaries Mega-Boundaries Conclusion Q & A

Page 4: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Introduction

Brief definition of Temporal Video Boundary technique

→ Examine the temporal boundary problem at different levels of video content structure analysis

Why we need Temporal Video Boundary technique?

Show example

Page 5: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Example : Oscar awards

Insufficient metadata

opening

ending

Page 6: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Example : Oscar awards

Detailed metadata

opening

ending

actor

winners

awards

ending

Page 7: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Basic notions - modali-ties Video contains three types of modalities (i) Visual (ii) Audio (iii) Textual

Each modality has three levels(i) low-level (ii) mid -level (iii) high-level→ levels describe the amount of details described in each modality in terms of granularity and ab-straction

Page 8: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Basic notions - modali-ties For each modality and for each level there if

a set of attributes. These can be formalized as vectors:

Page 9: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Basic notions - modali-ties Adding to this, given a set of vectors

→ their average value denote the vector

Page 10: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Basic notions - method Local method→ the difference is computed between con-

secutive frames

Global method→ the difference if computed over a series of

frames

Page 11: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Micro-Boundaries

Definition Boundaries associated to the smallest video

units for which a given attribute is constant or slowly varying

The attribute can be any feature in the visual, audio, or text domain

Page 12: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Example

Page 13: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Make family histogram

Data structure that represents the color in-formation of a family of frames.

Set of frames that exhibits uniform features

= Frame histogram

Page 14: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Histogram difference measures Histogram difference using L1 metrics

Bin-wise histogram intersection

Total number of color bins used

Histogram of previous frame

Histogram of current frame

Page 15: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Merging of family his-tograms

Page 16: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Multiple ways to compare and merge families - contiguity & memory

1. Contiguous with zero memory → A new frame histogram is compared with

previous frame histogram

2. Contiguous with limited memory→ A new frame histogram is compared with

previous family histogram

Page 17: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Multiple ways to compare and merge families - contiguity & memory

3. Non contiguous with unlimited memory → A new frame histogram is compared with all

previous family histograms within the same video.

4. Hybrid→ First a new frame histogram is compared using

the contiguous frames and then generated family histograms are merged using non con-tiguous case.

Page 18: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Compare different Histogram difference measures

Page 19: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Macro-Boundaries

Definition Boundaries between collections of video micro-

segments that are clearly identifiable organic parts of an event defining a structural (action) or thematic (story) unit

Video : collection of stories that may or may not be interconnected

→ Macro-Boundaries detection= Segmenting stories

textual cues

audio cuesvisual cues

Page 20: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Two types of uniform segment detection

Unimodal segment detection A video segment exhibits same characteristic

over a period of time

Multimodal segment detection A video segment exhibits a certain characteris-

tic taking into account attributes from different modalities

Page 21: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Single Modality Segmen-taion

Partition a continuous bit-stream of audio data into non-

overlapping segments

Classification

Seven mid-level audio cate-gories

Using low-level audio features

Audio segmen-tation & classifi-

cationText transcript

Extracted from either the closed captions or speech-to-

text conversion

Segmented and categorized with respect to a predefined

topic list

Frequency-of-word-occurrence metric is used

Page 22: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Multimodal Segmentaion

Pre-merging Steps

Uniform seg-ment detection

Intra-modal segment clus-

tering

Attribute tem-plate determi-

nation

Dominant at-tribute deter-

mination

Template ap-plication

Descent Meth-ods

Goal :Create macro-bound-

aries that are more ac-curate than the bound-aries produced by indi-

vidual modalities.

Page 23: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Descent MethodsText seg-

ment

Audio segment

Video segment

Page 24: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Single descent Method

Single descent with intersecting

union

Single descent with intersec-

tion

Single descent with secondary

voting attributes

Single descent with conditional

union

Page 25: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Mega-Boundaries

Definition Boundaries between collections of macro-seg-

ments that exhibit different structural and fea-ture consistency (e.g. different genres)

Example Commercial detection method

Page 26: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Trigger & Verifiers Model

Features that can aid in determining the location of the commercial break

Triggers

Features that can determine the boundaries of the commercial break

Verifiers

Page 27: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Black frames

Time interval be-tween detected

black frames as trig-gers

Used as verifiers

Letterbox change

High cut rate(= low cut distance)

Page 28: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Bayesian Belief Network Modelstart

Page 29: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Genetic Algorithms

Page 30: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Conclusion

Type of bound-aries Methods Example

Micro-boundaries Frame & Family histogram comparing and merging

Visual scene segmenta-tion

Macro-boundaries Single modality segmenta-tion

&Multimodal segmentation

Multimodal story segmen-tation

Mega-boundaries Trigger & Verifier Commercial detection

Page 31: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

Whenever metadata is availableor unavailable,

we can segment video by using this technique that

categorized three types

Page 32: Computer Science Engineering Lee Sang Seon.  Introduction  Basic notions for temporal video boundaries  Micro-Boundaries  Macro-Boundaries  Mega-Boundaries

&Thank you!

Q & A