vision sensor network tutorial
TRANSCRIPT
-
8/12/2019 Vision Sensor Network Tutorial
1/66
1
Distributed Vision NetworksDistributed Vision Networks
ACIVS ACIVS- -07 07
Hamid Aghajan, Stanford University, USARichard Kleihorst, NXP Research, NetherlandsChen Wu, Stanford University, USA
August 27, 2007
Delft University, Netherlands
Course Website http://wsnl.stanford.edu/acivs07/index.php
OutlineOutline
Introduction Application potentials Data fusion mechanisms Human pose analysis Multi-view gesture
Distributed Vision Networks ACIVS 2007 Tutorial 2
Smart cameras Outlook
-
8/12/2019 Vision Sensor Network Tutorial
2/66
2
Technology CrossTechnology Cross- -RoadsRoads
Sensor NetworksWireless communicationNetworking
Image Sensors Rich information Low power, low cost
Smart
Camera
Networks
Distributed Vision Networks ACIVS 2007 Tutorial 3
Embedded processing Collaboration methods
Architecture?Algorithms?
Applications?
Scene understanding Context awareness
Potential impact on designmethodologies in eachdiscipline
Sensor Networks PerspectiveSensor Networks Perspective
Opportunities for novel applications:
Make com lex inter retation of environment and events
Learn phenomena and behavior, not just measure effect
Incorporate context awareness into the application
Allow network to interact with the environment
Distributed Vision Networks ACIVS 2007 Tutorial 4
Change of paradigm:High-bandwidth sensors (vision)
-
8/12/2019 Vision Sensor Network Tutorial
3/66
3
Vision Processing PerspectiveVision Processing PerspectiveNovel approach to vision processing:
Use the additional available dimension: spaceData fusion across views, time, and feature levels
Design based on effective use of all available information(opportunistic fusion)
Utilize multiple views to:Overcome ambiguities
Achieve robustness Allow for low complexity algorithms
Distributed Vision Networks ACIVS 2007 Tutorial 5
Use communication to exchange descriptions - not raw dataIn-node processing
Change of paradigm:Networked vision sensors
Distributed Vision NetworksDistributed Vision Networks
High-bandwidth data
In-node processing
Low-bandwidth communication
Distributed Vision Networks ACIVS 2007 Tutorial 6
Collaborative interpretation
-
8/12/2019 Vision Sensor Network Tutorial
4/66
4
Distributed Vision NetworksDistributed Vision Networks
Rich design space utilizing concepts of: Vision processing Signal processing and optimization Wireless communications Networking Sensor networks
Novel smart environment applications:
Distributed Vision Networks ACIVS 2007 Tutorial 7
Context aware User centric
Distributed Vision NetworksDistributed Vision NetworksProcessing at source allows: Image transfer avoidance Descriptive reports ca a e ne wor s
Design opportunities: Processing architectures for real-time in-node processing Algorithms based on opportunistic data fusion Novel smart environment a lications
Distributed Vision Networks ACIVS 2007 Tutorial 8
Balance of in-node and collaborative processing:
Communication cost Latency Processing complexities Levels of data fusion
-
8/12/2019 Vision Sensor Network Tutorial
5/66
5
Distributed Vision NetworksDistributed Vision Networks
Vision sensing requires awareness of: Privacy issues
Em lo in-node rocessin Avoid image transfer Applications that provide services not based on monitoring / reporting
Bandwidth issues Transmit processed information not raw data Transmit based on information value for fusion / query-based
Distributed Vision Networks ACIVS 2007 Tutorial 9
Employ separate early vision and interpretive processing
mechanisms Layered processing architecture: Features, objects, relationships,
models, decisions Employ data exchange and collaboration across different layers
Distributed Vision NetworksDistributed Vision Networks
Robotics AgentsResponse systemsSmart environments
Feedback( features, parameters,
Distributed Vision Networks( DVN )
Enabling technologies:o
Vision processingo Wireless sensor networko Embedded computingo Signal processing
ArtificialIntelligence
ContextEvent interpretation
Behavior modeling
SmartEnvironments
Assisted livingOccupancy sensing
Augmented reality
, .
Distributed Vision Networks 10
Multimedia Human ComputerInteraction
Scene constructionVirtual realityGaming
Immersive virtual realityNon-restrictive interfaceRobotics
10 ACIVS 2007 Tutorial
-
8/12/2019 Vision Sensor Network Tutorial
6/66
6
OutlineOutline
Introduction Application potentials Data fusion mechanisms Human pose analysis Multi-view gesture
Distributed Vision Networks ACIVS 2007 Tutorial 11
Smart cameras Outlook
Examples by: Chen Wu, Chung-Ching Chang, Huang Lee, Joshua Goshporn, Itai Katz,Kevin Gabayan, Arezou Keshavarz, Ali Maleki-Tabar
Wireless Sensor Networks Lab, Stanford University
Application Potentials: View Selection Application Potentials: View Selection
Select best view of person of interest inreal-time tracking
Data exchange between camerasdetermines which one to stream visual CAM 1
DOOR
data
CAM 2
CAM 5
Distributed Vision Networks ACIVS 2007 Tutorial 12
CAM 3CAM 4
-
8/12/2019 Vision Sensor Network Tutorial
7/66
7
Application Potentials: Assisted Living Application Potentials: Assisted Living
Detect accidents at home
CAM 1
DOOR
CAM 2
CAM 5
Distributed Vision Networks ACIVS 2007 Tutorial 13
CAM 3CAM 4
Application Potentials: Multi Application Potentials: Multi- -Finger GestureFinger Gesture
Manipulate virtual world with free hand gesture
Pan Rotate
Zoom out Zoom in
Distributed Vision Networks ACIVS 2007 Tutorial 14
-
8/12/2019 Vision Sensor Network Tutorial
8/66
8
Application Potentials: Face Profiling Application Potentials: Face Profiling
Interpolate and reconstruct face model from a fewsnapshots
X
-100-50
0
X
Y
Z
Y
ZZ
Y
X
Distributed Vision Networks ACIVS 2007 Tutorial 15
Camera 1(Training set)
Camera 3(Test set)
t1
Application Potentials: 3D Model Reconstruction Application Potentials: 3D Model Reconstruction
t1t2
t2
Onlyobservations at t2
Distributed Vision Networks ACIVS 2007 Tutorial 16
Observations at t1 Observations at t2
-
8/12/2019 Vision Sensor Network Tutorial
9/66
9
Application Potentials: Virtual Reality Application Potentials: Virtual Reality
Place people in virtual world CAM 1
CAM 2
DOOR
CAM 3CAM 4
CAM 5
Distributed Vision Networks ACIVS 2007 Tutorial 17
OutlineOutline
Introduction Application potentials Data fusion mechanisms Human pose analysis Multi-view gesture
Distributed Vision Networks 18
Smart cameras Outlook
18 ACIVS 2007 Tutorial
-
8/12/2019 Vision Sensor Network Tutorial
10/66
10
Smart Camera NetworksSmart Camera NetworksTimeTime
(Views)
FeatureLevels
(Views)
FeatureLevels
Space (views) Overcome ambiguities, occlusions Enhance estimate robustness
Fusion Dimensions
Distributed Vision Networks ACIVS 2007 Tutorial 19
Time Increase confidence level of estimates Detection of key frames
Feature levels Exchange of features with other nodes across algorithmic layers
Fusion MechanismsFusion MechanismsFeature fusion:
Use of multiple, complementaryfeatures within a camera node
Spatial fusion:Localization, epipolar geometry, ROIand feature matchingValidation of estimates by checkingconsistency, outlier removal3D reconstructionTemporal fusion:
Local interpolation / smoothing
of estimatesExchange of updates viaspatial fusionSpatiotemporal estimatesmoothing and prediction
Model-based fusion:3D human body reconstruction,human gesture analysisFeedback to in-node featureextraction
Distributed Vision Networks ACIVS 2007 Tutorial 20
Decision fusion:Estimates based on soft decisions
Adequate features in ownobservationsCost, latency of communication
Key features and keyframes:
Information assisting othernodes
-
8/12/2019 Vision Sensor Network Tutorial
11/66
11
Layered Spatial CollaborationLayered Spatial Collaboration
Description Layer 4 :Gestures G
Description Layers Decision LayersFinal decision
Case Study: Human Gesture Analysis
Security
Description Layer 2 :Features
Description Layer 3 :Gesture Elements
Decision Layer 2 :collaboration between
cameras
Decision Layer 3 :collaboration between
cameras
F1 F2 F3f12f11 f21
f22f31
f32
E1 E2 E3
Feature-based fusion
Soft decision fusion
In-node feature
Gaming
Mutual reasoning:- Joint estimation
Assisted reasoning:- Estimate validation- Key feature exchange
Distributed Vision Networks ACIVS 2007 Tutorial 21
Description Layer 1 :Images
ec s on ayer :within a single camera
R1 R2 R3
Opportunisticdata fusion
Fusion of features within a single camera
Fusion based on collaboration among multiple cameras
extraction SmartPresentation
AccidentDetection
- In-node feature extraction
Fusion MechanismsFusion Mechanisms
Distributed Vision Networks ACIVS 2007 Tutorial 22
Mutual Reasoning
Spatial fusion Spatiotemporal fusion
Model-based Active vision Feedback
Feature fusion Temporal fusion
Self Reasoning
Assisted ReasoningExchange of key features
-
8/12/2019 Vision Sensor Network Tutorial
12/66
12
The Big PictureThe Big Picture
Distributed Vision Networks ACIVS 2007 Tutorial 23
ModelModel--based Fusionbased Fusion Motivation to build a human model:
A concise reference for merging information from camerasOffers flexibility for interpretation in different applications:
Various esture inter retation a lications
Allows recreation of body gesture in virtual domain Viewing angles to body not available from any of the cameras
Allows employment of active vision methods: Focus on what is important Develop more detail in time
Helps address privacy concerns in various applications
Distributed Vision Networks ACIVS 2007 Tutorial 24
-
8/12/2019 Vision Sensor Network Tutorial
13/66
-
8/12/2019 Vision Sensor Network Tutorial
14/66
14
Use of FeedbackUse of Feedback
CAM 1
CAM 2
CAM N
Merge informationProject / decompose toeach image plane again
CAM 1
CAM 2
CAM N
3Ddescription
Gestureextraction
1e
2e
3e
CAM 1
CAM 2
CAM N
Distributed Vision Networks ACIVS 2007 Tutorial 27
Gestures
Feedback Initialize in-node feature extraction Active vision (focus on what is important)
OutlineOutline
Introduction Application potentials Data fusion mechanisms Human pose analysis Multi-view gesture
Distributed Vision Networks ACIVS 2007 Tutorial 28
Smart cameras Outlook
-
8/12/2019 Vision Sensor Network Tutorial
15/66
15
RegionRegion- -based Feature Fusionbased Feature Fusion Problems with pixel-based features:
Localized attributes need local thresholds hard to set Comparing color of foreground / background pixels
No information from extended neighborhood considered Knowledge about extent of neighborhood not available
That is the objective in many cases segmentation
Objects often contain correlated attributes in aregion
Distributed Vision Networks ACIVS 2007 Tutorial 29
The idea is to grow regions based on correlatedattributes Achieve segmentation an intermediate step in many
applications
Feature Fusion: Optical Flow and Color Feature Fusion: Optical Flow and Color Use of complementary features
Edge and color Color and motion
Combine pixel-based andregion-based methods
Distributed Vision Networks ACIVS 2007 Tutorial 30
-
8/12/2019 Vision Sensor Network Tutorial
16/66
16
RegionRegion- -based Fusion: Optical Flow and Color based Fusion: Optical Flow and Color
Distributed Vision Networks ACIVS 2007 Tutorial 31
Joint Refinement of Color and MotionJoint Refinement of Color and Motion
Description Layer 3 :Gesture Elements
Description Layer 4 :Gestures
Decision Layer 3 :collaboration between
cameras
E1 E2 E3
G
Description Layers Decision Layersimages
coarse estimation ofcolor segmentation
coarse estimationof motion flows
Description Layer 1 :Images
Description Layer 2 :Features
Decision Layer 1 :within a single camera
Decision Layer 2 :collaboration between
cameras
R1 R2 R3
F1 F2 F3f12f11 f21
f22f31
f32
better color segmentation better motion flows
refine refine
. . . . . . . . . . . .
Optical flow assisting color segmentation Color segmentation assisting optical flow
Distributed Vision Networks ACIVS 2007 Tutorial 32
without using angles of ellipses after using angles of ellipses
Search for fitted ellipse in motion flow allows for effectivedetection of arms motion vector
Clustering close-by points with similar motionvector allows for better segmentation of the leg
-
8/12/2019 Vision Sensor Network Tutorial
17/66
17
Spatial FusionSpatial Fusion Geometric fusion
Mutual reasoning
Making correspondences Tracking Reconstruction of 3D models Camera network calibration o n es ma on
Joint refinement Decision fusion
Assisted reasoning Estimate validation
Use of epipolar geometry to:
Feature matchingOutlier removalROI mapping between camera views
X
Distributed Vision Networks 33
-100-50
0
X
Y
Z
YZZ
Y
X
Mapped to an ellipsoidCamera 1
(Training set)Camera 3(Test set)
Face Orientation Estimation Color and geometry-based method Spatial / temporal validation method
33 ACIVS 2007 Tutorial
* *
Color and Geometry FusionColor and Geometry FusionFace orientation analysis
In-node feature extraction by fusion of Color and Geometry Apply position constraints for the eyes when thresholding Cb/Cr
CompensatedImage Eye-map
Mean andCovariance
Skin colorellipse model
EyeCandidate
Cb/Cr
Eye-GaussianDistribution x
Gaussian-ChrominanceDistribution
x
Distributed Vision Networks 34
Skin mask
34 ACIVS 2007 Tutorial
-
8/12/2019 Vision Sensor Network Tutorial
18/66
18
Color and Geometry FusionColor and Geometry Fusion
Use geometry of cameras to:
Face orientation analysisFeature matching with epipolar geometry
x1 x2
X
l x1 x2
X
l
100 200 300 100 200 300 100 200 300
F a
l s e
f a c e
c a n
d i d a
t e
Remove false feature candidates
ase ne
Epipolar line for x 1
ase ne
Epipolar line for x 1
Distributed Vision Networks 35
0
0
0
0
50
100
150
200
50
100
150
200
0
0
0
0
50
100
150
200
50
100
150
200
F a
l s e e y e
c a n
d i d a
t e s
Epipolar lines forfalse candidates
An Example ofMutual Reasoning
35 ACIVS 2007 Tutorial
Feature FusionFeature Fusion Level of features for fusion between cameras?
Features are typically dense fields Edge points, motion vectors
Descriptions are exchanged
Valuable features may be exchanged as dense descriptors
Communication cost issues need to be considered
High-level descriptionsCollaborationbetween cameras
Sparse
Distributed Vision Networks 36
Key features and key frames allow selective sharing of dense features
Low-level features
High-level features
ow- eve escr p ons
Processing withina single camera
Features (single camera)or descriptions (shared)
Dense
36 ACIVS 2007 Tutorial
-
8/12/2019 Vision Sensor Network Tutorial
19/66
19
Key FramesKey Frames Frames with high confidence estimates
Node with key frame observation broadcasts derivedinformation
Other nodes use them to refine their local estimates
Distributed Vision Networks 3737 ACIVS 2007 Tutorial
Temporal FusionTemporal Fusion Use key frames to re-initialize local face angle estimate
Use angle estimates close to zero (frontal view)
Aims to limit error propagation in time Use optical flow to locally track angle changes between frames Interpolate between two key frames to limit optical flow error propagation
Cameras initializeface angles
Cameras initializeface angles
Local optical flow is usedto track face anglebetween key frames
Distributed Vision Networks 38
Cameras interpolateface angles betweenkey frames usinglocal optical flow
Key frames
38 ACIVS 2007 Tutorial
-
8/12/2019 Vision Sensor Network Tutorial
20/66
20
Spatial / Temporal ValidationSpatial / Temporal Validation Estimates between key frames are
corrected by: Temporal smoothing (one camera) Temporal
smoothing
Spatialsmoothing
u er remova mu p e cameras
Can this be done more effectively?Spatiotemporal filtering
Key frames
Distributed Vision Networks 3939 ACIVS 2007 Tutorial
Spatiotemporal FusionSpatiotemporal Fusion
0 5 10 15 20 25 30 35 40-200
0
200
d e g r e e
Backward Pass
Forward Pass
0
50
100
150 True orientation
d e g r e e
RightProfile
ppor un s c crea on o ace pro e
Distributed Vision Networks 40
0 10 20 5045 62 70 80 8 5 1 10 120 130-10-20-27-40-50-65-70-80-95-100-105-125-140 30
B C D E F G H I J KA M N O P Q R S T U VL X Y ZW
0 5 10 15 20 25 30 35 40-150
-100
-50
frame
LeftProfile
Query result examples:side profiles
Mapped toellipsoid
40 ACIVS 2007 Tutorial
-
8/12/2019 Vision Sensor Network Tutorial
21/66
21
Spatiotemporal FusionSpatiotemporal Fusion
Distributed Vision Networks 4141 ACIVS 2007 Tutorial
ModelModel--based Human Posture Reconstructionbased Human Posture Reconstruction
From model,or via k -means
Refine color models(PerceptuallyOrganized)
Or other morphologicalmethod with constraints
Concise description ofsegments
Segmentation function: Single cameraFeedback
Distributed Vision Networks ACIVS 2007 Tutorial 42
Model fitting function: CollaborativeGoodness of ellipsefits to segments
Projection on imageplanes
E.g. parameters for theupper body (arms)
-
8/12/2019 Vision Sensor Network Tutorial
22/66
22
InIn--Node Feature Fusion for SegmentationNode Feature Fusion for Segmentation
Distributed Vision Networks ACIVS 2007 Tutorial 43
Collaborative Model FittingCollaborative Model FittingFrame 105
Distributed Vision Networks ACIVS 2007 Tutorial 44
-
8/12/2019 Vision Sensor Network Tutorial
23/66
23
Collaborative Model FittingCollaborative Model Fitting
Distributed Vision Networks ACIVS 2007 Tutorial 45
Virtual PlacementVirtual Placement
Distributed Vision Networks 46 ACIVS 2007 Tutorial
-
8/12/2019 Vision Sensor Network Tutorial
24/66
24
Virtual PlacementVirtual PlacementCollaborativeFace Analysis
Feature Fusion Ellipse Fitting
Distributed Vision Networks ACIVS 2007 Tutorial 47
In-node processing-
SpatiotemporalFusion
Decision FusionDecision Fusion Smart home care network for fall detection
States are combined as soft decisions to create a report
AccelerometerSignal Classifier
State1 State2 State3
Decision Making Process
State0Trigger Image Analysis
Camera 1 Camera 2 Camera 3
Analysis Analysis Analysis
50 100 150 200 250 3000
50
100
150
200
250 Accelerometer Signal for Falling and Sitting Down
Time (s)
S i g n a
l L e v e l
xaxis
yaxiszaxis
FallSitting Down
50 100 150 200 250 3000
50
100
150
200
250 Accelerometer Signal for Falling and Sitting Down
Time (s)
S i g n a
l L e v e l
xaxis
yaxiszaxis
FallSitting Down
Distributed Vision Networks ACIVS 2007 Tutorial 48
0 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 1.80
20
40
60
80
100
120
140
160
180
A c c e
l e r o m e
t e r
A m p
l i t u
d e
C h a n g e
Duration (s)
Falling versus Sitting Down
Sitting DownFalling
State0=1State0=3
0 0.2 0.4 0.6 0.8 1 1.2 1.4 1.6 1.80
20
40
60
80
100
120
140
160
180
A c c e
l e r o m e
t e r
A m p
l i t u
d e
C h a n g e
Duration (s)
Falling versus Sitting Down
Sitting DownFalling
State0=1State0=3
NoReport(Safe)
Report AllUsefulData
(PossibleHazard)
Report(Hazard)
Joint work with: Arezou Keshavarz, Ali Maleki-Tabar
-
8/12/2019 Vision Sensor Network Tutorial
25/66
25
Decision FusionDecision Fusion
W ai t f or
-I ni t i al i z e S e ar
-V al i d a t eM
o d
Distributed Vision Networks ACIVS 2007 Tutorial 49
or e O b s er v a t i on s
c h S p a c ef or 3 DM
o d el
el
Decision FusionDecision Fusion
Distributed Vision Networks ACIVS 2007 Tutorial 50
-
8/12/2019 Vision Sensor Network Tutorial
26/66
26
Decision FusionDecision Fusion
Distributed Vision Networks ACIVS 2007 Tutorial 51
Decision FusionDecision Fusion
Alert level= 0.6598
Confidence= 0
Alert level= 0.8370
Confidence= 0.7389
Alert level= 0.8080
Confidence= 0.7695
combine
Distributed Vision Networks ACIVS 2007 Tutorial 52
Lying down, danger ( 0.6201 )
-
8/12/2019 Vision Sensor Network Tutorial
27/66
27
Event InterpretationEvent Interpretation
Vision Reasoning /Interpretations
Human Model
Kinematics AttributesStates
Interpretationlevels
Behavioranalysis
Instantaneousaction
Low-level
AI reasoning
Posture / attributes
AI
VisionProcessing
Distributed Vision Networks ACIVS 2007 Tutorial 53
features o e parame ers
QueriesContextPersistenceBehavior attributes
Feedback
Event InterpretationEvent Interpretation
Distributed Vision Networks ACIVS 2007 Tutorial 54
-
8/12/2019 Vision Sensor Network Tutorial
28/66
28
OutlineOutline
Introduction Application potentials Data fusion mechanisms Human pose analysis Multi-view gesture
Distributed Vision Networks ACIVS 2007 Tutorial 55
Smart cameras Outlook
Why is it difficult to estimate posture?Why is it difficult to estimate posture?
Image cues arenot obvious
Human modelvaries(body part sizes)
Distributed Vision Networks ACIVS 2007 Tutorial 56
High-dimensionaloptimization
-
8/12/2019 Vision Sensor Network Tutorial
29/66
29
Image CuesImage Cues Edge
Templates Chamfer distance
Motion Structure Object boundaries / edges
,
Color skin color adaptively learned color
No single one is robust ! Point/line features v.s. region
features
Distributed Vision Networks ACIVS 2007 Tutorial 57
Human ModelHuman Model
Measured Motion capture devices
Acquisition Init at the beginning, with not too difficult postures
If differs from the subject too much, fitting might be
Distributed Vision Networks ACIVS 2007 Tutorial 58
trapped into ar-away local minima easily
-
8/12/2019 Vision Sensor Network Tutorial
30/66
30
OptimizationOptimization
Top-down approach 3D model > 2D projections of
Validate 2D projections with image observations
Deutscher(particle filtering), Sminchisescu(scaled covariance sampling) etc.
Distributed Vision Networks ACIVS 2007 Tutorial 59
OptimizationOptimization Bottom-up approach
Looking for body part candidates in images Assemble 2D/3D models from body part
can ates Sigal(loose limbed people), Ramanan(profile
pose)
Distributed Vision Networks ACIVS 2007 Tutorial 60
-
8/12/2019 Vision Sensor Network Tutorial
31/66
31
OptimizationOptimization - - Pros and ConsPros and Cons
Top-down approach+ Easy to handle occlusions Time consuming in calculating projections and evaluate
them
Bottom-up approach+ Distribute more computation in images (i.e. body part
candidates, local assemblage)
Distributed Vision Networks ACIVS 2007 Tutorial 61
Difficult to handle occlusions without knowing relative configurations of body parts
Not direct to map from 2D assemblage to the 3D model
Multiple Views?Multiple Views?
Gains More image cues Resolve ambiguity (sometimes helps a lot!)
Challenges Huge redundancy, how to reduce?
Misleading Correspondence? Communication?
Distributed Vision Networks ACIVS 2007 Tutorial 62
Review Score addition (Gavrila etc.) 3D voxels / stereo (Malik etc.) 3D templates from training (Sigal etc.)
-
8/12/2019 Vision Sensor Network Tutorial
32/66
32
MultiMulti--View Camera NetworkView Camera Network
Basic Assumption and Constraint-- Powerful local image processor, limited communication e uce oca n orma on Maximally utilize multi-views:
to compensate for partial observations and reduced descriptions
Ideas Combine bottom-up and top-down approaches
Concise and informative local deduction
Choose best view for different purposes
Distributed Vision Networks ACIVS 2007 Tutorial 63
Optimally combine Reduce redundancy
Challenge: Can we learn adaptively? Model (size, appearance) Behaviors -> prediction & validation
TemporalTemporal- -Spatial FusionSpatial Fusion
Distributed Vision Networks ACIVS 2007 Tutorial 64
-
8/12/2019 Vision Sensor Network Tutorial
33/66
-
8/12/2019 Vision Sensor Network Tutorial
34/66
34
Spatial FusionSpatial FusionCombining top-down and bottom-up approaches
Distributed Vision Networks ACIVS 2007 Tutorial 67
Distributed Communication FlowDistributed Communication Flow
Camera 5 wants to update itsCAM 5
Fusion to update localknowledge of the subject
knowledge of the subject
1Broadcast the request for
collaborationCAM 1
2 The other cameras sendrequested descriptions
3
4Updated knowledgeof the subject is fedback
Vector of model parameters
5
Distributed Vision Networks ACIVS 2007 Tutorial 68
CAM 2
CAM 3
CAM 4
Vector of descriptions from local processing
5
5
5
Up-to-date knowledge of the subjectis used in local processing 1 2 3 4 5
-
8/12/2019 Vision Sensor Network Tutorial
35/66
35
Algorithm AlgorithmFrom model,or via k -means
Refine color models(PerceptuallyOrganized)
Or other morphologicalmethod with constraints
Concise description ofsegments
Segmentation function: Single cameraFeedback
Distributed Vision Networks ACIVS 2007 Tutorial 69
Model fitting function: CollaborativeGoodness of ellipsefits to segments
Projection on imageplanes
E.g. parameters for theupper body (arms)
SegmentationSegmentation In-node function based on:
Feature fusion Feedback from model
Feedback allows for incorporation of spatiotemporal fusion outcome intolocal analysis
Rough estimate of segments provided by: Local initialization
Segmentation function: Single camera
Distributed Vision Networks ACIVS 2007 Tutorial 70
Expectation Maximization (EM) methods use new observation to refinelocal color distributions EM produces markers (collection of high-confidence segment islands) for
watershed Also helps with varying color distributions between cameras
Watershed enforces spatial proximity information to link the segment
-
8/12/2019 Vision Sensor Network Tutorial
36/66
36
EM SegmentationEM Segmentation Initialization:
Not a good idea to arbitrarily specify an initial estimate EM may be trapped to local optima
ays o o a n n a es ma es: K-means
Centers of clusters are taken as the initial estimations for EM Segment parameters from the 3D body model
Assumes appearance doesnt change very quickly
Distributed Vision Networks ACIVS 2007 Tutorial 71
Segmentation function: Single camera
Perceptually Organized EM (POEM)Perceptually Organized EM (POEM) Regular EM method:
A pixel-based method Doesnt use spatial relationship between pixels / segment islands
POEM: Segments are continuous, so consider a pixels neighborhood
Use a measure of expected grouping: 2 21 2
( ) ( )
( , )i j i j x x coord x coord x
iw x x e
=
Distributed Vision Networks ACIVS 2007 Tutorial 72
The neighborhood votes for ( xi in segment l ):
( ) ( ) ( , ), where ( ) ( | ) j
l i l j i j l j j j x
V x x w x x x p y l x = = =
-
8/12/2019 Vision Sensor Network Tutorial
37/66
37
Watershed SegmentationWatershed Segmentation Removing vague pixels is important for watershed,
since wrong seeds/markers would compete withcorrect ones and cause false segments
Segmentation function: Single camera Red : undecided pixels
Distributed Vision Networks ACIVS 2007 Tutorial 73
Assigns labels to undecided ( dark blue ) pixels
Ellipse FittingEllipse Fitting
Motivation: Concise descriptions of segments Each ellipse should represent a
segment with similar shape Not necessarily correspond to
body parts
Goodness of fit measures
Distributed Vision Networks ACIVS 2007 Tutorial 74
Occupancy of the ellipse Coverage of the segment
-
8/12/2019 Vision Sensor Network Tutorial
38/66
38
ModelModel--based Human Posturebased Human Posture ReconstructionReconstruction
1 3
1 3
Ellipse parameters are exchanged betweencameras
Reduced data communication load forcollaboration
2 4
2 4
data and create a virtual skeleton
Distributed Vision Networks ACIVS 2007 Tutorial 75
Goodness of ellipsefits to segments
Projection on imageplanes
E.g. parameters for theupper body (arms)
Skeleton FittingSkeleton Fitting
Frame 1
Frame 28
Frame 70
Frame 81
Distributed Vision Networks ACIVS 2007 Tutorial 76
Frame 105
Frame 148
-
8/12/2019 Vision Sensor Network Tutorial
39/66
-
8/12/2019 Vision Sensor Network Tutorial
40/66
40
OutlineOutline
Introduction Application potentials Data fusion mechanisms Human pose analysis Multi-view gesture
Distributed Vision Networks 79
Smart cameras Outlook
79 ACIVS 2007 Tutorial
Aims of This Section Aims of This Section
o n ro uce smar camera arc ec ures To motivate smart wireless cameras from
a power consumption point of view To discuss the research and industrial
Distributed Vision Networks ACIVS 2007 Tutorial 80
-
8/12/2019 Vision Sensor Network Tutorial
41/66
41
Vision SystemsVision Systems
Are systems that analyse images and video They report in events/objects/properties DVD recorders, set-top boxes, smart
cameras
Distributed Vision Networks ACIVS 2007 Tutorial 81
VISIONSYSTEMimage
data
Smart Camera VisionSmart Camera Vision S Systemystem
Source: Wikipdia
A definition
smar camera s an ntegrate mac ne v s on system w c , in addition to image capture circuitry, includes a processor, which can extract information from
images without need for an external processing unit, and interface devices used to make results available to otherdevices.
Distributed Vision Networks ACIVS 2007 Tutorial 82
= + +
Franois Berry, Univ. Blaise Pascal, France
-
8/12/2019 Vision Sensor Network Tutorial
42/66
42
Granularity of IntegrationGranularity of IntegrationSmart camera is vision system
with an intermediate hardware granularity
Vision chipsSmart CameraMachine
Vision System
Distributed Vision Networks ACIVS 2007 Tutorial 83
PROCESSING IN INTEGRATED LEVEL
Franois Berry, Univ. Blaise Pascal, France
Smart CamerasSmart Cameras
= Camera + intelligence = The basis for new applications Such as: detection, tracking, scene
analysis
Distributed Vision Networks ACIVS 2007 Tutorial 84
Automotive Surveillance ConsumerMobile Comm .
-
8/12/2019 Vision Sensor Network Tutorial
43/66
43
Challenges in Wireless Smart CamerasChallenges in Wireless Smart Cameras
Performance Power consumption Programmability
Distributed Vision Networks ACIVS 2007 Tutorial 85
Actually, Why a Smart Wireless Camera? Actually, Why a Smart Wireless Camera?
Distributed Vision Networks ACIVS 2007 Tutorial 86
Why not a radio connection to PC that does processing?
-
8/12/2019 Vision Sensor Network Tutorial
44/66
44
Power Consumption of a Wireless VGA CameraPower Consumption of a Wireless VGA Camera
200 mWatt to transmit life video over a short distance.
1 year of daily use means 1750 Wh
Distributed Vision Networks ACIVS 2007 Tutorial 87
2.2 liters of methanol fuel per year.
This takes about 400X the total camera volume
Consumption is in the RadioConsumption is in the Radio P Pathath
RFDADS01101 PA
TRANSMITTER
transmit signal processingenergy per bit
Link energy per bitELET
Distributed Vision Networks ACIVS 2007 Tutorial 88
E T [nJ/bit] E L [nJ/bit]
Bluetooth 150 1GSM (0.2 Watt) 500-1000 2500
-
8/12/2019 Vision Sensor Network Tutorial
45/66
45
PowerPower ConsumptionConsumption forfor RadioRadioPower
1W
802.11a
mains UTP
1m
10mBluetooth
Zigbeebattery
Data RatePicoRadiopower/bit does not scalewith Moores Law100 Auto-
Distributed Vision Networks ACIVS 2007 Tutorial 89
s10k 100k 1M 10M 100M
~ moving pictures~ speech, audio, hifi~sensor
nomous1k100
Raf Roovers
Computational Efficiency is GComputational Efficiency is G rowing (Moore)rowing (Moore)
[GOPSer 10
1010 11
20 Age in Years80
Watt]
ASICs
CPUs
10 510 410 310 210 1
10 810 7
10 6
HumanBrain
SIMD Processor
Distributed Vision Networks ACIVS 2007 Tutorial 90
Feature size [um]
2 1 0.5 0.25 0.13 0.07
Pentium 410 0
SIMD Single Instruction Multiple Data
-
8/12/2019 Vision Sensor Network Tutorial
46/66
-
8/12/2019 Vision Sensor Network Tutorial
47/66
47
Smart Wireless Camera PlatformSmart Wireless Camera Platform
Distributed Vision Networks ACIVS 2007 Tutorial 93
WiCa (Xetal SIMD)50 GOPS @ 600mWatt
Cyclops (AVR RISC)8 MIPS @ 50mWatt?
Architecture Architecture
Smart Camera
Embedded system
Differentiating features:power cost Not end-user
Operates in fixedrun-timeconstraints Real
Distributed Vision Networks ACIVS 2007 Tutorial 94
performanceRuns a few
applications oftenknown at design
time
programmable time)
Franois Berry, Univ. Blaise Pascal, France
-
8/12/2019 Vision Sensor Network Tutorial
48/66
48
Smart Camera Designs for ResearchSmart Camera Designs for Research
Technology
Processor approach:DSP,Media Processor,GPU
Programmable Logic approach:CPLD, FPGA
Distributed Vision Networks ACIVS 2007 Tutorial 95
Franois Berry, Univ. Blaise Pascal, France
Processor ApproachProcessor Approach GPU and DSP
DSP (Digital Signal Processor) : ,
generally in real-time computing
Features:
Highly parallel accumulator and multiplier : MAC OperationFixed-point arithmetic is often used to speed up arithmeticprocessing.
The specification of DSPs is 4 algorithms:
Distributed Vision Networks ACIVS 2007 Tutorial 96
Franois Berry, Univ. Blaise Pascal, France
Infinite Impulse Response (IIR) filtersFinite Impulse Response (FIR) filtersFFTConvolvers
-
8/12/2019 Vision Sensor Network Tutorial
49/66
49
Smart Camera Designs for ResearchSmart Camera Designs for Research
Technology
Programmable Logic approach:CPLD, FPGA
Processor approach:DSP,Media Processor,GPU
Distributed Vision Networks ACIVS 2007 Tutorial 97
Franois Berry, Univ. Blaise Pascal, France
Programmable Logic ApproachProgrammable Logic Approach
FPGA (Field Programmable Gate Array):Its an electronic component used to build dedicated digital circuits
+Hardware
DescriptionFPGA
VHDLVerilo
=Customized ICProcessor Specific Glue logicS ecific a lications
u v y ufundamental computing components via configuration information stored inonboard static RAM
Distributed Vision Networks ACIVS 2007 Tutorial 98
Franois Berry, Univ. Blaise Pascal, France
-
8/12/2019 Vision Sensor Network Tutorial
50/66
50
Programmable Logic ApproachProgrammable Logic Approach
Increasing speed & density
Increased I/O pin count and bandwidth
FPGA (Field Programmable Gate Array):
Integration of hard IP (e.g. multipliers, processor soft cores,)
150
200
250
300
r a t i o n s
Maximum Floating-PointMultiply-Accumulates
Floating Point Operations (GFLOPS)
Maximum Sustained Single PrecisionFPGA Costs
$150
$200
$250
$300
$350
i l l i o n
G a
t e s
Distributed Vision Networks ACIVS 2007 Tutorial 99
Franois Berry, Univ. Blaise Pascal, France
0
50
100
1998 1999 2000 2002 2005
O p e
$0
$50
$100
1998 1999 2000 2001 2002 2003
C o s
t p e r
1 M
Smart Camera for ResearchSmart Camera for Research
A very efficient smart cam could be based onan efficient mix of FPGA, DSP, GPU,!!!
Distributed Vision Networks ACIVS 2007 Tutorial 100
Franois Berry, Univ. Blaise Pascal, France
-
8/12/2019 Vision Sensor Network Tutorial
51/66
51
Smart Camera Design forSmart Camera Design for C Consumer onsumer UseUse
Challenges:
Performance Energy consumption Cost
Distributed Vision Networks ACIVS 2007 Tutorial 101
Let us look at an example
Example Event Casting: Face DetectionExample Event Casting: Face Detection
Distributed Vision Networks 102 ACIVS 2007 Tutorial
-
8/12/2019 Vision Sensor Network Tutorial
52/66
52
Face Detection Application MappingFace Detection Application Mapping
lowlow intermediateintermediate highhighVideo Data
Image processing :Image pyramid
Application:Draw box, event
Pixel processing:Haar filters
for ever ixel for ever ima e For every event
Distributed Vision Networks ACIVS 2007 Tutorial 103
similar similar different
SIMD10++GOPS
FPGA/DSP100MOPS
CPU1MOPS
SIMD Single Instruction Multiple Data
Why SIMD for LowWhy SIMD for Low- -Level?Level?
High-performance (need > 10GOPS) g n erna - an w nee > s
A
instruction
B
10GOPS * 3 * 16bits
Bandwidth =
Distributed Vision Networks ACIVS 2007 Tutorial 104
C
SIMD Single Instruction Multiple Data
-
8/12/2019 Vision Sensor Network Tutorial
53/66
53
Uniprocessor Uniprocessor to SIMD: 1 PEto SIMD: 1 PE
4.6mm 20.6mm 2
Data Memor
1mm 2
0.02mm 2
DSP ControlProgramMemory
Performance 100MOPS
100MHz
Distributed Vision Networks ACIVS 2007 Tutorial 105
Size 5.22mm 2
Performance/area 19MOPS/mm 2
Overhead 26%
Bandwidth 4.8Gb/s
Uniprocessor Uniprocessor to SIMD: 2PEsto SIMD: 2PEs
4.6mm 20.6mm 2
1mm 2
0.02mm2
DSP ControlProgramMemory
Performance 200MOPS
0.02mm2
1 2
100MHz
Distributed Vision Networks ACIVS 2007 Tutorial 106
Size 5.24mm 2
Performance/area 38MOPS/mm 2
Overhead 25%
Bandwidth 9.6Gb/s
-
8/12/2019 Vision Sensor Network Tutorial
54/66
54
Uniprocessor Uniprocessor to SIMD: 100PEsto SIMD: 100PEs
4.6mm 20.6mm 2
1mm 2
0.02mm 2
DSP Control
Performance 10 GOPS
0.02mm 2
1 2 100ProgramMemory
100MHz
Distributed Vision Networks ACIVS 2007 Tutorial 107
Size 8.2 mm 2
Performance/area 1.2 GOPS/mm 2
Overhead 20%
Bandwidth 480 Gb/sec.
Uniprocessor Uniprocessor to SIMDto SIMD
RISC : 1PE50MHz
Xetal-II SIMD :320PE@150MHz
Pentium42.4GHz
Peak 0.05 100 6Performance GOPS GOPS GOPSSize 6.4
mm 244.4 (0.18u)
11.1 (0.09u) mm 2131mm 2
Performance /area 0.18u
0.008GOPS/mm 2
2.25GOPS/mm 2
0.045GOPS/mm 2
Overhead 26% 12% ??%
Distributed Vision Networks ACIVS 2007 Tutorial 108
Bandwidth 2 Gb/S 1.5Tb/S 58 Gb/S
Peak PowerConsumption
1.0Watt
59Watt
-
8/12/2019 Vision Sensor Network Tutorial
55/66
55
Why is SIMD LowWhy is SIMD Low- -Power?Power?
Typical DSP
accesses to memory
PE
A
instruction
B
Distributed Vision Networks ACIVS 2007 Tutorial 109
CC = A + B;C = A > B ? A : B;
Why is SIMD LowWhy is SIMD Low- -Power?Power?
SIMD have multiple PEs in parallel r me c a ways as o e one But: Instruction fetch is shared multiple times.
Data (A,B,C) access is shared inmultiple-word-wide memories
Accessin an 8 times wider memor takes
Distributed Vision Networks ACIVS 2007 Tutorial 110
half the amount of energy per data entity.
-
8/12/2019 Vision Sensor Network Tutorial
56/66
56
SIMD Energy ConsumptionSIMD Energy Consumption
25SIMD Energy Consumption
Basis: Convolution
10
15
20
E n e r y
C o n s u m p
t i o n
[ n J / p i x e
l ]
W=9
W=11
W=13
W Communication Memory access
Distributed Vision Networks 111
0 100 200 300 400 500 6000
5
Number of PEs
W=3
W=5
W=7
Parallelism Memory Localization
Without voltage scaling,energy saving levels off
ACIVS 2007 Tutorial
SIMD Power/Energy ScalingSIMD Power/Energy Scaling
0.9
1Scaling Energy Consumption in SIMD Architectures
30 GOPS
Parallelism enables
[Vddmax, f max][40,1]
0.3
0.4
0.5
0.6
0.7
0.8
E n e r g y S c a l i n g F a c t o r
10 GOPS
20 GOPS
scaling Vth limits degree of
scaling f max = 50 MHz
Sets P min N = 640 pixels[200,0.3]
Distributed Vision Networks ACIVS 2007 Tutorial 112
0 100 200 300 400 500 600 7000.1
0.2
Number of PEs
0.1 GOPS
max [Vddmin, f min]
-
8/12/2019 Vision Sensor Network Tutorial
57/66
-
8/12/2019 Vision Sensor Network Tutorial
58/66
58
Smart Wireless Camera PCBSmart Wireless Camera PCB
ZigBee module
Distributed Vision Networks 115
Ben Schueler, NXP
Battery module
ACIVS 2007 Tutorial
Picture of WiCa SetupPicture of WiCa Setup
Distributed Vision Networks ACIVS 2007 Tutorial 116
Alexander Danilin, NXP
-
8/12/2019 Vision Sensor Network Tutorial
59/66
59
Which Algorithms Run Easily on WiCa?Which Algorithms Run Easily on WiCa?
Where much of the application is running on the
Where the DSP/CPU is used for limited oroccasional tasks only
Choose appropriate algorithmic basis for sceneanalysis
Distributed Vision Networks 117
or examp e: ea ure ase
ACIVS 2007 Tutorial
What Have We Mapped to WiCa?What Have We Mapped to WiCa?
Face detection: soft edge features
Horizontal soft edges
Distributed Vision Networks 118
Vertical soft edges
ACIVS 2007 Tutorial
-
8/12/2019 Vision Sensor Network Tutorial
60/66
60
What Have We Mapped to WiCa?What Have We Mapped to WiCa?
Wireless intruder detection system
Distributed Vision Networks 119 ACIVS 2007 Tutorial
What Have We Mapped to WiCa?What Have We Mapped to WiCa?
Object recognition applications
Distributed Vision Networks 120 ACIVS 2007 Tutorial
-
8/12/2019 Vision Sensor Network Tutorial
61/66
-
8/12/2019 Vision Sensor Network Tutorial
62/66
62
ConclusionsConclusions
Low-power smart wireless cameras can bees gne w ron -en s
Real-time applications ZigBee node opens research challenges
for distributed camera networks
Distributed Vision Networks 123
ACIVS 2007 Tutorial
OutlineOutline
Introduction Application potentials Data fusion mechanisms Human pose analysis Multi-view gesture
Distributed Vision Networks 124
Smart cameras Outlook
124 ACIVS 2007 Tutorial
-
8/12/2019 Vision Sensor Network Tutorial
63/66
63
SummarySummarySmart camera networks:
Enable novel user-centric applications:InterpretiveContext awareUser centric
Processing at source allows:Image transfer avoidanceScalable networksDescri tive re orts
Distributed Vision Networks ACIVS 2007 Tutorial 125
Privacy issues: Awareness of user choicesIn-node processing and image transfer avoidanceModel-based or silhouetted images
SummarySummarySmart camera networks:
Algorithm design is key in efficient use of computingresources
In-node feature extraction and opportunistic fusionUse of key features in the data exchange mechanismModel-based approach provides feedback / initial points for in-nodeprocessing
Balance between in-node and collaborative processing
Distributed Vision Networks ACIVS 2007 Tutorial 126
Communication costLatencyProcessing complexitiesLevels of data fusion
-
8/12/2019 Vision Sensor Network Tutorial
64/66
64
Towards Active VisionTowards Active Vision
Active vision in feature extraction:Use of key features instead of generic features (edges, motion, etc.)Detection of prominent color / texture attributesUse of spatiotemporal fusion results to learn key features
Active vision in modules with processing load:Instead of avoiding methods with high processing cost / latency:
Define what they should look for Perform initialization to restrict searches
Distributed Vision Networks ACIVS 2007 Tutorial 127
Active vision in gesture analysis:Use history of subject and semantic meanings of gestures tofeedback what is important to detect
OutlookOutlook
Applications:Select best view of person of interest in real-time tracking
Manipulate virtual world with free hand / finger gesturesDetect accidental falls at home / elderly careReconstruct face model from a few snapshotsBuild 3D models of objects
Distributed Vision Networks ACIVS 2007 Tutorial 128
-
8/12/2019 Vision Sensor Network Tutorial
65/66
65
OutlookOutlook
Robotics AgentsResponse systemsSmart environments
Feedback( features, parameters,
Distributed Vision Networks
( DVN )
Enabling technologies:o Vision processingo Wireless sensor networko Embedded computingo Signal processing
ArtificialIntelligence
ContextEvent interpretationBehavior modeling
SmartEnvironments
Assisted livingOccupancy sensing
Augmented reality
, .
Distributed Vision Networks ACIVS 2007 Tutorial 129
Multimedia Human ComputerInteraction
Scene constructionVirtual realityGaming
Immersive virtual realityNon-restrictive interfaceRobotics
OutlookOutlook
Distributed Vision Networks
( DVN )
Enabling technologies:o Vision processingo Wireless sensor networkso Embedded computing
ContextEvent interpretationBehavior models
Artificial Intelligence(AI)
o Signal processing
Human Computer Immersive virtual realityNon-restrictive interface
Feedback( features, parameters,
decisions, etc. )
QualitativeKnowledge
QuantitativeKnowledge
Distributed Vision Networks ACIVS 2007 Tutorial 130
Robotics
Multimedia
nteract on
AgentsResponse systemsUser interactions
Scene constructionVirtual realityGaming
Interactive robotics
SmartEnvironments
-
8/12/2019 Vision Sensor Network Tutorial
66/66
ReferencesReferences H. Aghajan and C. Wu, From Distributed Vision Environment to Human Behavior Interpretations, Behaviour
Monitoring and Interpretation Workshop at the 30th German Conference on Artificial Intelligence, Sept. 2007.
C. Wu and H. Aghajan, Model-based Human Posture Estimation for Gesture Analysis in an OpportunisticFusion Smart Camera Network, Int. Conf. on Advanced Video and Signal based Surveillance (AVSS), Sept.2007.
C. Chang and H. Aghajan, A LQR Spatiotemporal Fusion Technique for Face Profile Collection in Smartamera urve ance, n . on . on vance eo an gna ase urve ance , ep . .
C. Chang and H. Aghajan, Spatiotemporal Fusion Framework for Multi-Camera Face Orientation Analysis, Advanced Concepts for Intelligent Vision Systems (ACIVS), August 2007.
C. Wu and H. Aghajan, Model-based Image Segmentation for Multi-View Human Gesture Analysis, AdvancedConcepts for Intelligent Vision Systems (ACIVS), August 2007.
Hamid Aghajan and Chen Wu, Layered and Collaborative Gesture Analysis in Multi-Camera Networks, Int.Conf. on Acoustics, Speech, and Signal Processing (ICASSP), April 2007.
Chen Wu and Hamid Aghajan, Opportunistic Feature Fusion-based Segmentation for Human Gesture Analysisin Vision Networks, IEEE SPS-DARTS, March 2007.
Chen Wu and Hamid Aghajan, Collaborative Gesture Analysis in Multi-Camera Networks, ACM SenSys
Distributed Vision Networks ACIVS 2007 Tutorial 131
, . .
Chung-Ching Chang and Hamid Aghajan, Collaborative Face Orientation Detection in Wireless Image SensorNetworks, ACM SenSys Workshop on Distributed Smart Cameras (DSC), Oct. 2006.
A. Maleki-Tabar, A. Keshavarz, H. Aghajan, Smart Home Care Network using Sensor Fusion and DistributedVision-Based Reasoning, ACM Multimedia Workshop On Video Surveillance and Sensor Networks (VSSN),Oct. 2006.
A. Keshavarz, A. Maleki-Tabar, H. Aghajan, Distributed Vision-Based Reasoning for Smart Home Care, ACM SenSys Workshop on Distributed Smart Cameras (DSC), Oct. 2006.
http://wsnl.stanford.edu/publications.php
www.ICDSC.org
First ACM / IEEE International Conference on Tutorials:
Smart camera architectures Image sensing techniques for smart cameras Embedded vision programming Fusion of vision and other sensors Distributed vision processing algorithms Distributed appearance modeling
Distributed Smart Cameras (ICDSC-07)September 25-28, 2007
Vienna, Austria
Andrea Cavallaro, Queen Mary Universityof London, UK: Smart Cameras:
Algorithms, Evaluation and Applications
Bjoern Gottfried, U. of Bremen, Germany:
Ambient Intelligence and the Role ofSpatial Reasoning: Smart Environmentswith Smart Cameras
Richard Radke, Rensselaer PolytechnicInstitute, USA: Multiview Geometry forCamera Networks o a ora ve ea ure ex rac on, a a an ec s o n us o n
Architectures and protocols for camera networks Wireless and mobile image senor networks
Position disco er and middle are applications
Wilfried Elmenreich, Vienna Univ., Real-time Sensor Networks for Smart Cameras:Communication, Data Processing and