video synopsis yael pritch alex rav-acha shmuel peleg the hebrew university of jerusalem

86
Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Upload: emma-scott

Post on 15-Jan-2016

215 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Video Synopsis

Yael Pritch Alex Rav-Acha Shmuel Peleg

The Hebrew University of Jerusalem

Page 2: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Detective Series: “Elementary”

Page 3: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Video Surveillance Problem

• It took weeks to find these events in video archives.

• Cost of a lost information or a delay may be very high.

Terrorists, London tube, 7-7-05Cologne Train Bombs, 31-7-06

Page 4: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Challenges in Video Surveillance

• Millions of surveillance cameras are installed, capturing data 24/365

• Number of cameras and their resolution increases rapidly

• Not enough people to watch captured data

• Human Attention is Lost after ~20 Minutes

• Result: Recorded Video is Lost Video– Less than 1% of surveillance video is

examined

Page 5: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Handling Surveillance Video

• Object Detection and Tracking– Background Subtraction

• Object Recognition– Individual people

• Activity Recognition– Left luggage; Fight

• A lot of progress done. More work remains.

Page 6: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

• Object Detection and Tracking– Background Subtraction (Assume Done)

• Object Recognition (Do not use)– Individual people

• Activity Recognition (Do not use)– Left luggage; Fight

• A lot of progress done. More work remains.

• Let People do the Recognition

Handling Surveillance VideoVideo Synopsis

Page 7: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem
Page 8: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Video Synopsis

Video SynopsisOriginal video

• A fast way to browse & index video archives.• Summarize a full day of video in a few minutes.• Events from different times appear simultaneously.• Human inspection of synopsis!!!

Page 9: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Synopsis of Surveillance VideosHuman Inspection of Search Results

• Serve queries regarding each camera:– Generate a 3 minutes video showing

most activities in the last 24 hours– Generate the shortest video showing all

activities in the last 24 hours

• Each presented activity points back to original time in the original video

• Orthogonal to Video Analytics

Page 10: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Non-Chronological Time

Dynamic Mosaicing Video Synopsis

SalvadorDali

The Hebrew University of Jerusalem

Page 11: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Dynamic Mosaics

Non Chronological Time

Page 12: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

HandheldStereo Mosaic

Page 13: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

u

t

Mosaic Image

Original framesstrips

Page 14: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Frame tl

u

t

Frame tk

uaub

Mosaic Image

Space-TimeSlice

Visibility region

Page 15: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

u

t

First Slice

Last Slice

play

Creating Dynamic Panoramic Movies

First Mosaic - Appearance

Last Mosaic - Disappearance

Page 16: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Dynamic Panorama: Iguazu Falls

u

t

Page 17: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

From Video In to Video OutConstructing an aligned

Space-Time Volume

u

dtv

aαt

bAlignment: Parallax, Dynamic Scenes, etc.

Page 18: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

t

u

kk+1

u

t

Stationary Camera Panning Camera

kk+1

Aligned ST Volume: View from Top

Page 19: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Generate Output VideoSweeping a “Time Front” surface

Time is not chronological any more

Interpolation

Page 20: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Generate Output VideoSweeping a “Time Front” surface

Time is not chronological any more

Interpolation

Page 21: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

u

t

Evolving Time Frontu

t

x

Mapping each TF to a new frame using spatio-temporal interpolation

Page 22: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Example: Demolition

Page 23: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

t

u

Page 24: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Example: Racing

Page 25: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

t

v

Page 26: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Dynamic Panorama: Thessaloniki

Page 27: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Creating Panorama: 4D min-cutAligned space-time

volume

t

x

Page 28: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Mosaic Stitching Examples

Page 29: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Mosaic Stitching Examples

Page 30: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Video Synopsis and IndexingMaking a Long Video Short

• 11 million cameras in 2008• Expected 30 million in 2013• Recording 24 hours a day, every day

Page 31: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

2009

Explosive growth in cameras…

201431

11m

24m

Page 32: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Handling the Video Overflow

• Not enough people to watch captured data

• Guards are watching 1% of video

• Automatic Video Analytics covers less than 5%

– Only when events can be accurately defined & detected

• Most video is never watched or examined!!!

Page 33: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

A Recent Example

Page 34: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

• Key framesC. Kim and J. Hwang. An integrated scheme for object-based video abstraction. In ACM Multimedia, pages 303–311, New York, 2000.

• Collection of short video sequencesA. M. Smith and T. Kanade. Video skimming and characterization through the combination of image and

language understanding. In CAIVD, pages 61–70, 1998.

• Adaptive Fast Forward N. Petrovic, N. Jojic, and T. Huang. Adaptive video fast forward. Multimedia Tools and Applications,

26(3):327–344, August 2005.

Entire frames are used as the fundamental building blocks

• Mosaic images together with some meta-data for video indexingM. Irani, P. Anandan, J. Bergen, R. Kumar, and S. Hsu. Efficient representations of video sequences

and their applications. Signal Processing: Image Communication, 8(4):327–351, 1996.

• Space Time Video montageH. Kang, Y. Matsushita, X. Tang, and X. Chen. Space-time video montage. In CVPR’06, pages 1331–

1338, New-York, June 2006.

Related Work (Video Summary)

Page 35: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

• We proposed Objects / Events based summary as opposed to Frames based summary– Enables to shorten a very long video

into a short time

– No fast forward of objects (preserve dynamics)

– Causality is not necessarily kept

Object Based Video Summary

Page 36: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Original video: 24 hours Video Synopsis: 1 minute

Video Synopsis• Browse Hours in Minutes• Index back to Original Video

Page 37: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

t

Video SynopsisShift Objects in Time

Input Video I(x,y,t)

Synopsis Video S(x,y,t)

Page 38: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Objects Extracted to Database

10:00

09:0311:08

14:38

18:45

21:50

38

How does Video Synopsis work?

Original: 9 hours

Video Synopsis:30 seconds

38

Page 39: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

How Does Video Synopsis works

Original: 9 hours

Video Synopsis:30 seconds

Page 40: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

• Detect and track objects, store in database.• Select relevant objects from database• Display selected objects in a very short

“Video Synopsis”• In “Video Synopsis”, objects from different

times can appear simultaneously• Index from selected objects into original video• Cluster similar objects

Steps in Video Synopsis

Page 41: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

42

Input Video

t

Synopsis Video

x

Object “Packing”

• Compute object

trajectories

• Pack objects in shorter

time (minimize overlap)

• Overlay objects on top

of time-laps background

Page 42: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Example: Monitoring a Coffee Station

t

x

Page 43: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

x

t

Page 44: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Original Movie Stroboscopic Movie

Page 45: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Panoramic Synopsis

Panoramic synopsis is possible when the camera is rotating.

Original

Panoramic Video Synopsis

Page 46: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Endless video – Challenges

• Endless video – finite storage (“forget” events)

• Background changes during long time periods

• Stitching object on a background from a different time

• Fast response to user queries

Page 47: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Online Monitoring• Online Monitoring (real time)

– Compute background (background model)– Find Activity Tubes and insert to database– Handle a queue of objects

• Query Service– Collect tubes with desired properties (time…)– Generate Time Lapse Background– Pack tubes into desired length of synopsis– Stitching of objects to background

2 Phase approach

Page 48: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Online Monitoring• Online Monitoring (real time)

– Compute background (background model)– Find Activity Tubes and insert to database– Handle a queue of objects

• Query Service– Collect tubes with desired properties (time…)– Generate Time Lapse Background– Pack tubes into desired length of synopsis– Stitching of objects to background

2 Phase approach

Page 49: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Extract TubesObject Detection and

Tracking• We used a simplification of

Background-Cut*– combining background subtraction

with min-cut

• Connect space time tubes component

• Morphological operations

* J. Sun, W. Zhang, X. Tang, and H. Shum. Background cut. In ECCV, pages 628–641, 2006

Page 50: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Extract Tubes

Page 51: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

The Object Queue

• Limited Storage Space with Endless Video– May need to discard objects

• Estimate object usefulness for future queries– “Importance” (application dependent)– Collision Potential – Age: discard older objects first

• Take mistakes into account….

Page 52: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Query Service• Online Monitoring (real time)

– Pre-Processing : remove stationary frames– Compute background (temporal median)– Find Activity Tubes and insert to database– Handle a queue of objects

• Query Service– Collect tubes with desired properties (time…)– Generate Time Lapse Background– Pack tubes into desired length of synopsis– Stitching of objects to background

2 Phase approach

Page 53: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Time-Lapse Background

Page 54: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Time-Lapse Background

• Time Lapse background goals– Represent background changes over time– Represent the background of activity tubes

Activity distribution over time(parking lot 24 hours)

20% night frames

Page 55: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Tubes Selection

Guidelines for the tubes arrangement :• Maximum “activity” in synopsis• Minimum collision between objects• Preserve causality (temporal consistency)

This defines energy minimization process :

A time mapping between the input tubes and the appearance time in the output synopsis

Page 56: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Energy Minimization Problem

Bb Bbb

tca bbEbbEbEME',

)'ˆ,ˆ()'ˆ,ˆ()ˆ()(

Activity Cost(favors synopsis

video with maximal activity)

Temporal consistency Cost(favors synopsis video that preserves original

order of events )

Collision Cost(favors synopsis

video withminimal collision between tubes )

synopsis theinto b tubeof shift) (time mapping the- b̂

ubesactivity t -

synopsis theinput to thefrom mapping temporal-

B

M

Page 57: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Tubes Selection as Energy Minimization

• Each state – temporal mapping of tubes into the synopsis

• Neighboring states - states in which a single activity tube changes its mapping into the synopsis.

• Initial state - all tubes are shifted to the beginning of the synopsis video.

Page 58: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Stitching the Synopsis

• Challenge : Different lighting for objects and background

• Assumption : Extracted tubes are surrounded with background pixels

• Our Stitching method :Modification of Poisson Editing – add weight for object to

keep original color

Page 59: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Stitching the Synopsis

• Challenge : objects stitched on time lapse background with possibly different lighting condition (for example : day / night)

• Assumption : no accurate segmentation. Tubes are extracted surrounded with background pixels

• Our Stitching method : modification of Poisson editing

add weight

for object to

keep original color

Page 60: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Stitching the Synopsis

Page 61: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Stitching the Synopsis

Page 62: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Webcam in Parking LotTypical Webcam Stream

(24 hours)

Webcam Synopsis :20 Seconds

Page 63: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Video Indexing

Webcam Synopsis :20 Seconds

Link from the synopsis back to the original video context

synopsis can be used for video indexing

Page 64: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Webcam Synopsis :20 Seconds

Link from the synopsis back to the original video context

synopsis can be used for video indexing

Video Indexing

Page 65: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Link from the synopsis back to the original video context

Video Indexing

Hotspot on Tracked Objects

Page 66: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Link from the synopsis back to the original video context

Video Indexing

Hotspot on Tracked Objects

Page 67: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Who soiled my lawn?

Unexpected Applications

2 hours 20 seconds

Page 68: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Examples

Page 69: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem
Page 70: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Video Synopsis Should be More Organized

Page 71: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Clustered SynopsisFaster and more accurate browsing

cars people

Example: Cluster into 2 clusters based on shape

Continue Examining the ‘Car’ cluster

Page 72: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Clustering by Motion of ‘Cars’ ClassSynopsis now useful in crowded scenes

ExitEnter

Up HillRight

Page 73: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

)ˆˆ(2

1 k k

ik

jk

jk

ikij ssss

Nsd

Appearance (Shape) Distance Between Objects

Symmetric Average Nearest Neighbor distance between SIFT descriptors

 O. Boiman,  E. Shechtman   and   M. Irani,  In Defense of Nearest-Neighbor Based Image Classification .  

IEEE Conference on Computer Vision and  Pattern Recognition (CVPR), June 2008    .

K’s Sift Descriptor in tube iSift Descriptor closest to K of tube j

Page 74: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Spectral Clustering by Appearance

Cluster 1 Cluster 2

Cluster 3 Cluster 4

Page 75: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

• More Classes : Easy to Remove False Alarm Classes

Gate Trees

Spectral Clustering by Appearance

Page 76: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

)()(

)()( kSep

kT

kwkMd ij

ijij

Object Distance: MotionTrajectory Similarity

– Computing minimum area between trajectories over all temporal shifts

– Efficient computation using NN and KD trees

Weight encouraging long temporal overlap

Common Time of tubes

Space Time trajectory distance

))()(()()(

22

kTt

j

kt

i

t

j

kt

i

tij

ij

yyxxkSep

x

t

k

Page 77: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Spectral Clustering by Motion‘Cars’ Class

ExitEnter

Up HillRight

Page 78: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Creating Video Synopsis

• Goals – Video Synopsis Having Shortest Duration– Minimal Collision Between Objects

• Approach– Displaying clustered objects together– Objects packed in space-time like sardines

Page 79: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Packing Cost Example• Packing cars on the top road

Affinity Matrix after Clustering

Arranged Cluster 1 Arranged Cluster 2

Page 80: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Combining Two Clusters

Low Collision Cost Between

Classes

High Collision Cost Between

Classes

Page 81: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

An Important Application:Display Results of Video Analytics

• Display the hundreds of “Blue Cars”

• Display thousands of people going left

• Good for verification of algorithm as well as for

deployment

Page 82: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Two Clusters

Cars

People

Camera in St. Petersburg

• Detect specific events• Discover activity patterns

Page 83: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Cars

People

Two Clusters

Camera in China

Page 84: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem

Automatically Generated ClustersUsing Only Shape & Motion

People LeftPeople Right

Cars LeftCars Right Cars Parking

People Misc.

Page 85: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem
Page 86: Video Synopsis Yael Pritch Alex Rav-Acha Shmuel Peleg The Hebrew University of Jerusalem