SlideShare a Scribd company logo
1 of 46
Download to read offline
Pattern Recognition
and Applications Lab
University
of Cagliari, Italy
Department of
Electrical and
Electronic Engineering
Fast Person Re-Identification for
Intelligent Video Surveillance Systems
PhD final dissertation
PhD Program in Electronic and Computer Engineering
March 2018
Bahram Lavi
lavi.bahram@diee.unica.it
http://pralab.diee.unica.it
Intelligent Video Surveillance
2
Application tools:
●
Person re-identification
●
On-line tracking of people and objects
●
Off-line image retrieval for an object of
interest within different camera views
●
Recognizing of suspicious
actions/behaviors
…
Intelligent
video surveillance
systems
Machine
learning
Pattern
recognition
Computer
vision
http://pralab.diee.unica.it
What is person re-identification?
• Recognizing a person in non-overlapping camera views
• Application tools:
– on-line (e.g. tracking people among camera network)
– off-line (e.g. support to human operators, video-surveillance
operators, and forensic investigators)
3
http://pralab.diee.unica.it
Challenges and difficulties
4
Low
quality
ofthe
im
agesPose
variation
O
cclusions
Illum
ination
change
face-recognition
cannotbe
applied
http://pralab.diee.unica.it
Person re-identification systems
5
Focus of this work: off-line support to human operators
probe
template gallery: n images
http://pralab.diee.unica.it
Image descriptors
6
One possible cue to generate an image signature:
clothing appearance based on

Color histograms

Textures

Convolutional neural networks
...
Descriptor
generation
Descriptor
generation
Descriptor
generation
Descriptor
generation
template gallery
probe
http://pralab.diee.unica.it
Image descriptors
7
a) pedestrian image
b) symmetry-based silhouette partition
c) weighted color histograms (WCH)
d) maximally stable color regions (MSCR)
e) recurrent highly structured patches
(RHSP)
Example: SDALF (Symmetry-Driven Accumulation of Local Features)
Farenzena et al., CVPR 2010
http://pralab.diee.unica.it
Matching score computation
8
Can be computed by:
●
manually defined a distance/similarity metric (e.g Euclidean dist.)
●
learnt from data
Descriptor
generation
Descriptor
generation
Descriptor
generation
Descriptor
generation
template gallery
probe
Matching scores
computation
http://pralab.diee.unica.it
Matching score computation
9
Example of matching score computation
(probe image vs. each image in gallery set)
probe
IA
template
IB
dWCH
dMSCR
dRHSP
 
Final matching score:
Descriptor: SDALF
http://pralab.diee.unica.it
Matching score computation
10
Descriptor
generation
Descriptor
generation
Descriptor
generation
Descriptor
generation
template gallery
probe
Matching scores
computation
Matching scores
http://pralab.diee.unica.it
Ranked list generation
11
A ranked list can be created by sorting the computed matching scores
Descriptor
generation
Descriptor
generation
Descriptor
generation
Descriptor
generation
template gallery
Matching scores
computation
Ranked list
Ranked list
probe
http://pralab.diee.unica.it
Performance of re-identification
systems
Recognition accuracy:
Cumulative Matching Characteristic (CMC) curve
12
Example: CMC curve
for a template gallery of size 55
http://pralab.diee.unica.it
Processing time
Two kind of processing times should be taken into account:
● To generate descriptor (tD
)
● To compute matching scores (tM
)
Descriptor
generation
Descriptor
generation
Descriptor
generation
Descriptor
generation
template gallery
probe
Matching scores
computation
Ranked list
creation
Off-line step
On-line step
In real-world applications:
processing time of matching phase
can be very high due to:
● Large size of template gallery
● Or using a high cost
similarity measurement
13
http://pralab.diee.unica.it
Has ever processing time addressed
on person Re-Id task?
NOT explicitly...
ONLY:

Durta et al. 2013: a two-stage system proposed
➔
Possibly losing the correct identity within the 2nd
stage

Satta et al. 2012: dissimilarity-based approach
14
http://pralab.diee.unica.it
First solution
A multi-stage ranking approach
FOR
 Proc. time tM using a given descriptor D and number of stage N
By

Cascading simplified versions of descriptor D
D1
,D2
,…,DN
,where DN
=D
With

an application constraint on processing time:
t ≤ tmax, with tM > tmax
15
http://pralab.diee.unica.it
Goal of this work
16
D1
D1 D2
D2 DN = DDN = D
probe
template gallery
final ranking
...
...
...
Trade-off between processing time and recognition accuracy for
a given descriptor D
http://pralab.diee.unica.it
Example: two-stage system
17
probe
template gallery: n images
http://pralab.diee.unica.it
Example: two-stage system
18
D1
D1
probe
1st
stage: t1
template gallery: n1 images
A fast first-stage descriptor is used to rank all the n1 images in the
template gallery, where n1
=n
n1=10
http://pralab.diee.unica.it
Example: two-stage system
19
D1
D1
probe
rank 1 2 3 4 5 6 7 8 9 10
1st
stage: t1
A fast first-stage descriptor is used to rank all the n1 images in the
template gallery
http://pralab.diee.unica.it
Example: two-stage system
20
D1
D1
probe
rank 1 2 3 4 5 6 7 8 9 10
1st
stage: t1
D2
D2
2nd
stage: t2 > t1
A slower but more accurate second-stage descriptor is used to
re-rank the top-ranked templates
n2=5
http://pralab.diee.unica.it
Example: two-stage system
21
D1
D1
probe
rank 1 2 3 4 5 6 7 8 9 10
1st
stage: t1
A slower but more accurate second-stage descriptor is used to
re-rank the top-ranked templates
D2
D2
2nd
stage: t2 > t1
n2=5
http://pralab.diee.unica.it
Example: two-stage system
22
D1
D1
probe
1 2 3 4 5 6 7 8 9 10
1st
stage: t1
Whole procedure of a two-stage system
final ranked listfinal ranked list
D2
D2
2nd
stage: t2 > t1
n2=5
template gallery
http://pralab.diee.unica.it
Example: two-stage system
23
D1
D1
probe
1 2 3 4 5 6 7 8 9 10
1st
stage: t1
Whole procedure of a two-stage system
final ranked listfinal ranked list
D2
D2
2nd
stage: t2 > t1
 
processing time:
 
n2=5
template gallery
http://pralab.diee.unica.it
Example: two-stage system
24
D1
D2
D1
D1 D2
D2
http://pralab.diee.unica.it
Example: two-stage system
25
D1
D2
D1
D1 D2
D2
n2=?
Rank
http://pralab.diee.unica.it
Simplified versions of a descriptor
26
●
Generating the simplified versions by
(1) Ad hoc (e.g. histogram-based descriptor; by reducing number of bins)
(2) OR dimensionality feature reduction methods (e.g. PCA)
●
Descriptors that
– generates fixed-size feature vector
●
LOMO (Liao et al., CVPR-2015), ~26000 elements
●
gBiCov (Ma et. al. IVC-2014), ~6000 elements
http://pralab.diee.unica.it
Simplified versions of a descriptor
27
●
Generating the simplified versions by
(1) Ad hoc
Example:
MCM → reducing the number of patches
●
Descriptors that
– does NOT generate fixed-size feature vector
●
SDALF (Farenzena et al., CVPR-2010),
●
MCM (Satta et. al. ICIAP-2011),
http://pralab.diee.unica.it
Multi-stage system design
28
DD
tM > tmax
D1
t1
D1
t1
D2
t2
D2
t2
DN = D
tN
=tM
DN = D
tN
=tM
...
n2 n3 nNn1=n
● Given a descriptor D with matching processing time tM
● Deploying into a multi-stage system
● Where
t1
<t2
<...<tN-1
<tN
AND n=n1
>n2
>...>nN
>1
http://pralab.diee.unica.it
✔ trial-and-error procedure to choose
●
Number of stages N
● N-1 Simplified versions of D = {D1, ..., DN-1}
✔ Number of templates n2
, n3
,…, nN
to be ranked by
D = {D1,..., DN-1, DN
} are chosen by

Two-stage system (N=2):

N-stage system (N>2):
✔ Accordingly, processing time for a multi-stage system:
Multi-stage system design
29
 
n2=⌊
n1(tmax−t1)
t2
⌋
ni=⌊ ´αni−1⌋, ´α=max α:t≤tmax
http://pralab.diee.unica.it
Experimental set-up
• Benchmark datasets:
– VIPeR (1264 images, 632 pedestrians)
– i-LIDS (476 images, 119 pedestrians)
– ETHZ sequence 1 (4,857 images, 83 pedestrians)
30
• State-of-the-art descriptors:
– SDALF (Farenzena et al., 2010)
– gBiCov (Ma et al., 2014)
– LOMO (Liao et al., 2015)
– MCM (Satta et al., 2011)
http://pralab.diee.unica.it
Experimental set-up
31
● As in Farenzena et al. (2010):
● for each dataset and each individual: one image as probe, one image as
template (is selected randomly)
● 10 runs of experiments
● average CMC curves over 10 runs
● Two- and three-stage system
● Application constraint, for a given descriptor D
➔ t ≤ 0.3tM
➔ t ≤ 0.4tM
➔ t ≤ 0.5tM
http://pralab.diee.unica.it
Results: two-stage systems
32
D1
D2
t1 = 2.08 sec
t2 = 9.44 sec
D1
D1 D2
D2
http://pralab.diee.unica.it
Results: two-stage systems
33
D1
D2
t1 = 2.08 sec
t2 = 9.44 sec
t <= 0.3t2
D1
D1 D2
D2
7
n2
n2=7
http://pralab.diee.unica.it
Results: two-stage systems
34
D1
D2
t1 = 2.08 sec
t2 = 9.44 sec
t <= 0.4t2
D1
D1 D2
D2
7 15
n2
n2=15
http://pralab.diee.unica.it
Results: two-stage systems
35
D1
D2
t1 = 2.08 sec
t2 = 9.44 sec
t <= 0.5t2
D1
D1 D2
D2
7 15 23
n2
n2=23
http://pralab.diee.unica.it
Results: three-stage systems
36
D1
D3
D2
D1
D1 D3
D3D2
D2
t1 = 0.0015 sec
t2 = 0.0057 sec
t3 = 0.0400 sec
http://pralab.diee.unica.it
Results: three-stage systems
37
D1
D3
D2
D1
D1 D3
D3D2
D2
16 37
n2n3
n2=37 n3=16
t1 = 0.0015 sec
t2 = 0.0057 sec
t3 = 0.0400 sec
t <= 0.3t3
http://pralab.diee.unica.it
Results: three-stage systems
38
D1
D3
D2
D1
D1 D3
D3D2
D2
16 23 37 44
n2n3
n2=44 n3=23
t1 = 0.0015 sec
t2 = 0.0057 sec
t3 = 0.0400 sec
t <= 0.4t3
http://pralab.diee.unica.it
Results: three-stage systems
39
D1
D3
D2
D1
D1 D3
D3D2
D2
16 23 30 37 44 50
n2n3
n2=50 n3=30
t1 = 0.0015 sec
t2 = 0.0057 sec
t3 = 0.0400 sec
t <= 0.5t3
http://pralab.diee.unica.it
Second solution
A feature reduction method
FOR
●
Descriptor with fixed-size feature vector (e.g. gBiCov)
40
Descriptor
generation
Descriptor
generation
Descriptor
generation
Descriptor
generation
template gallery
probe
Matching scores
computation
Ranked list
Off-line step
On-line step
Feature reduction
method
http://pralab.diee.unica.it
Experimental set-up
• Benchmark datasets:
– VIPeR (1264 images, 632 pedestrians)
– i-LIDS (476 images, 119 pedestrians)
• State-of-the-art descriptors:
– gBiCov (Ma et al., 2014): ~6000 elements
– LOMO (Liao et al., 2015): ~26000 elements
41
• Feature reduction methods:
– Principal Component Analysis (PCA)
– K-PCA
– ISOMAP
• Reduction in features size for:
r=[2,5 ,20 ,50,80,100,150,200,500,1000,1200,2000,2500,3500]
http://pralab.diee.unica.it
Results: gBiCov on VIPeR using PCA
42
Feature size reduced for:
and average processing
time in second
r=
[
2
5
20
100
200
500
1000
]
http://pralab.diee.unica.it
Results: Reconstruction error
43
Frobenius norm:
E=
‖X−X‖F
2
‖X‖
r=2
r=5
r=20
r=100
r=200
r=500
http://pralab.diee.unica.it
Publications
1) Bahram Lavi, G. Fumera, and F. Roli:
'Multi-stage ranking approach for fast person re-identification’,
Journal of IET Computer Vision, 2018
2) Bahram Lavi, M. Fatan, and D. Valls:
'Comparative Study of the Behavior of Feature Reduction Methods in
Person Re-identification Task',
7th International Conference on Pattern Recognition Applications and Methods,
ICPRAM, 2018
3) Bahram Lavi, G. Fumera, and F. Roli:
'A Multi-Stage Approach for Fast Person Re- identification',
Joint IAPR International Workshops on Statistical Techniques in Pattern
Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR),
Springer, 2016.
44
http://pralab.diee.unica.it
Conclusions
• Goal: to tune the trade-off between processing time and
accuracy in person re-identification systems
– for any given descriptor
– under constraint on processing time
• Proposed solutions:
– multi-stage ranking approach
– feature reduction methods for fixed-sized descriptors
45
http://pralab.diee.unica.it
Open issues
• Multi-stage ranking approach: design a criteria to optimize
the multi-stage system by suitably choosing:
– number of stages
– simplified versions of the chosen descriptor
➢ For instance, using the Pareto optimization technique to jointly
optimized all the design parameters
• Feature reduction method: design a criteria to choose a
suitable reduced feature size for a fixed-size descriptor
46

More Related Content

What's hot

Dissimilarity-based people re-identification and search for intelligent video...
Dissimilarity-based people re-identification and search for intelligent video...Dissimilarity-based people re-identification and search for intelligent video...
Dissimilarity-based people re-identification and search for intelligent video...Riccardo Satta
 
Visual Object Tracking: review
Visual Object Tracking: reviewVisual Object Tracking: review
Visual Object Tracking: reviewDmytro Mishkin
 
Person re-identification, PhD Day 2011
Person re-identification, PhD Day 2011Person re-identification, PhD Day 2011
Person re-identification, PhD Day 2011Riccardo Satta
 
A Genetic Algorithm-Based Moving Object Detection For Real-Time Traffic Surv...
 A Genetic Algorithm-Based Moving Object Detection For Real-Time Traffic Surv... A Genetic Algorithm-Based Moving Object Detection For Real-Time Traffic Surv...
A Genetic Algorithm-Based Moving Object Detection For Real-Time Traffic Surv...Chennai Networks
 
International Journal of Engineering Research and Development
International Journal of Engineering Research and DevelopmentInternational Journal of Engineering Research and Development
International Journal of Engineering Research and DevelopmentIJERD Editor
 
Real-time Object Tracking
Real-time Object TrackingReal-time Object Tracking
Real-time Object TrackingWonsang You
 
multiple object tracking using particle filter
multiple object tracking using particle filtermultiple object tracking using particle filter
multiple object tracking using particle filterSRIKANTH DANDE
 
Presentation Object Recognition And Tracking Project
Presentation Object Recognition And Tracking ProjectPresentation Object Recognition And Tracking Project
Presentation Object Recognition And Tracking ProjectPrathamesh Joshi
 
Object Detection & Tracking
Object Detection & TrackingObject Detection & Tracking
Object Detection & TrackingAkshay Gujarathi
 
Object detection technique using bounding box algorithm for
Object detection technique using bounding box algorithm forObject detection technique using bounding box algorithm for
Object detection technique using bounding box algorithm forVESIT,Chembur,Mumbai
 
motion and feature based person tracking in survillance videos
motion and feature based person tracking in survillance videosmotion and feature based person tracking in survillance videos
motion and feature based person tracking in survillance videosshiva kumar cheruku
 
Object tracking survey
Object tracking surveyObject tracking survey
Object tracking surveyRich Nguyen
 
GTSRB Traffic Sign recognition using machine learning
GTSRB Traffic Sign recognition using machine learningGTSRB Traffic Sign recognition using machine learning
GTSRB Traffic Sign recognition using machine learningRupali Aher
 
Video surveillance Moving object detection& tracking Chapter 1
Video surveillance Moving object detection& tracking Chapter 1 Video surveillance Moving object detection& tracking Chapter 1
Video surveillance Moving object detection& tracking Chapter 1 ahmed mokhtar
 
Review: Incremental Few-shot Instance Segmentation [CDM]
Review: Incremental Few-shot Instance Segmentation [CDM]Review: Incremental Few-shot Instance Segmentation [CDM]
Review: Incremental Few-shot Instance Segmentation [CDM]Dongmin Choi
 

What's hot (20)

Dissimilarity-based people re-identification and search for intelligent video...
Dissimilarity-based people re-identification and search for intelligent video...Dissimilarity-based people re-identification and search for intelligent video...
Dissimilarity-based people re-identification and search for intelligent video...
 
Visual Object Tracking: review
Visual Object Tracking: reviewVisual Object Tracking: review
Visual Object Tracking: review
 
Person re-identification, PhD Day 2011
Person re-identification, PhD Day 2011Person re-identification, PhD Day 2011
Person re-identification, PhD Day 2011
 
A Genetic Algorithm-Based Moving Object Detection For Real-Time Traffic Surv...
 A Genetic Algorithm-Based Moving Object Detection For Real-Time Traffic Surv... A Genetic Algorithm-Based Moving Object Detection For Real-Time Traffic Surv...
A Genetic Algorithm-Based Moving Object Detection For Real-Time Traffic Surv...
 
Object tracking
Object trackingObject tracking
Object tracking
 
Object tracking
Object trackingObject tracking
Object tracking
 
International Journal of Engineering Research and Development
International Journal of Engineering Research and DevelopmentInternational Journal of Engineering Research and Development
International Journal of Engineering Research and Development
 
Real-time Object Tracking
Real-time Object TrackingReal-time Object Tracking
Real-time Object Tracking
 
Presentation of Visual Tracking
Presentation of Visual TrackingPresentation of Visual Tracking
Presentation of Visual Tracking
 
Object tracking final
Object tracking finalObject tracking final
Object tracking final
 
multiple object tracking using particle filter
multiple object tracking using particle filtermultiple object tracking using particle filter
multiple object tracking using particle filter
 
Presentation Object Recognition And Tracking Project
Presentation Object Recognition And Tracking ProjectPresentation Object Recognition And Tracking Project
Presentation Object Recognition And Tracking Project
 
Object Detection & Tracking
Object Detection & TrackingObject Detection & Tracking
Object Detection & Tracking
 
Object detection technique using bounding box algorithm for
Object detection technique using bounding box algorithm forObject detection technique using bounding box algorithm for
Object detection technique using bounding box algorithm for
 
motion and feature based person tracking in survillance videos
motion and feature based person tracking in survillance videosmotion and feature based person tracking in survillance videos
motion and feature based person tracking in survillance videos
 
Multiple Object Tracking - Laura Leal-Taixe - UPC Barcelona 2018
Multiple Object Tracking - Laura Leal-Taixe - UPC Barcelona 2018Multiple Object Tracking - Laura Leal-Taixe - UPC Barcelona 2018
Multiple Object Tracking - Laura Leal-Taixe - UPC Barcelona 2018
 
Object tracking survey
Object tracking surveyObject tracking survey
Object tracking survey
 
GTSRB Traffic Sign recognition using machine learning
GTSRB Traffic Sign recognition using machine learningGTSRB Traffic Sign recognition using machine learning
GTSRB Traffic Sign recognition using machine learning
 
Video surveillance Moving object detection& tracking Chapter 1
Video surveillance Moving object detection& tracking Chapter 1 Video surveillance Moving object detection& tracking Chapter 1
Video surveillance Moving object detection& tracking Chapter 1
 
Review: Incremental Few-shot Instance Segmentation [CDM]
Review: Incremental Few-shot Instance Segmentation [CDM]Review: Incremental Few-shot Instance Segmentation [CDM]
Review: Incremental Few-shot Instance Segmentation [CDM]
 

Similar to Fast Person Re-Identification for Intelligent Video Surveillance Systems

Discrete-event simulation: best practices and implementation details in Pytho...
Discrete-event simulation: best practices and implementation details in Pytho...Discrete-event simulation: best practices and implementation details in Pytho...
Discrete-event simulation: best practices and implementation details in Pytho...Carlos Natalino da Silva
 
A study of Machine Learning approach for Predictive Maintenance in Industry 4.0
A study of Machine Learning approach for Predictive Maintenance in Industry 4.0A study of Machine Learning approach for Predictive Maintenance in Industry 4.0
A study of Machine Learning approach for Predictive Maintenance in Industry 4.0Mohsen Sadok
 
Electrónica digital: practicas de electrónica digital
Electrónica digital: practicas de electrónica digitalElectrónica digital: practicas de electrónica digital
Electrónica digital: practicas de electrónica digitalSANTIAGO PABLO ALBERTO
 
SAND: A Fault-Tolerant Streaming Architecture for Network Traffic Analytics
SAND: A Fault-Tolerant Streaming Architecture for Network Traffic AnalyticsSAND: A Fault-Tolerant Streaming Architecture for Network Traffic Analytics
SAND: A Fault-Tolerant Streaming Architecture for Network Traffic AnalyticsQin Liu
 
VL/HCC 2014 - A Longitudinal Study of Programmers' Backtracking
VL/HCC 2014 - A Longitudinal Study of Programmers' BacktrackingVL/HCC 2014 - A Longitudinal Study of Programmers' Backtracking
VL/HCC 2014 - A Longitudinal Study of Programmers' BacktrackingYoungSeok Yoon
 
IRJET- Criminal Recognization in CCTV Surveillance Video
IRJET-  	  Criminal Recognization in CCTV Surveillance VideoIRJET-  	  Criminal Recognization in CCTV Surveillance Video
IRJET- Criminal Recognization in CCTV Surveillance VideoIRJET Journal
 
Automating Speed: A Proven Approach to Preventing Performance Regressions in ...
Automating Speed: A Proven Approach to Preventing Performance Regressions in ...Automating Speed: A Proven Approach to Preventing Performance Regressions in ...
Automating Speed: A Proven Approach to Preventing Performance Regressions in ...HostedbyConfluent
 
Simple Drools Examples
Simple Drools ExamplesSimple Drools Examples
Simple Drools ExamplesMatteo Mortari
 
IRJET- Automated Student’s Attendance Management using Convolutional Neural N...
IRJET- Automated Student’s Attendance Management using Convolutional Neural N...IRJET- Automated Student’s Attendance Management using Convolutional Neural N...
IRJET- Automated Student’s Attendance Management using Convolutional Neural N...IRJET Journal
 
Prometheus: From technical metrics to business observability
Prometheus: From technical metrics to business observabilityPrometheus: From technical metrics to business observability
Prometheus: From technical metrics to business observabilityJulien Pivotto
 
C programming project by navin thapa
C programming project by navin thapaC programming project by navin thapa
C programming project by navin thapaNavinthp
 
On-line, non-clairvoyant optimization of workflow activity granularity task o...
On-line, non-clairvoyant optimization of workflow activity granularity task o...On-line, non-clairvoyant optimization of workflow activity granularity task o...
On-line, non-clairvoyant optimization of workflow activity granularity task o...Rafael Ferreira da Silva
 
Next generation alerting and fault detection, SRECon Europe 2016
Next generation alerting and fault detection, SRECon Europe 2016Next generation alerting and fault detection, SRECon Europe 2016
Next generation alerting and fault detection, SRECon Europe 2016Dieter Plaetinck
 
Digital Signal Processinf (DSP) Course Outline
Digital Signal Processinf (DSP) Course OutlineDigital Signal Processinf (DSP) Course Outline
Digital Signal Processinf (DSP) Course OutlineMohammad Sohai Khan Niazi
 
3D Functional Tolerancing And Annotation CATIA
3D Functional Tolerancing And Annotation CATIA3D Functional Tolerancing And Annotation CATIA
3D Functional Tolerancing And Annotation CATIALeslie Schulte
 

Similar to Fast Person Re-Identification for Intelligent Video Surveillance Systems (20)

Discrete-event simulation: best practices and implementation details in Pytho...
Discrete-event simulation: best practices and implementation details in Pytho...Discrete-event simulation: best practices and implementation details in Pytho...
Discrete-event simulation: best practices and implementation details in Pytho...
 
Dsp lab manual 15 11-2016
Dsp lab manual 15 11-2016Dsp lab manual 15 11-2016
Dsp lab manual 15 11-2016
 
Sqa Automation
Sqa AutomationSqa Automation
Sqa Automation
 
A study of Machine Learning approach for Predictive Maintenance in Industry 4.0
A study of Machine Learning approach for Predictive Maintenance in Industry 4.0A study of Machine Learning approach for Predictive Maintenance in Industry 4.0
A study of Machine Learning approach for Predictive Maintenance in Industry 4.0
 
Electrónica digital: practicas de electrónica digital
Electrónica digital: practicas de electrónica digitalElectrónica digital: practicas de electrónica digital
Electrónica digital: practicas de electrónica digital
 
LVTS Projects
LVTS ProjectsLVTS Projects
LVTS Projects
 
master_seminar
master_seminarmaster_seminar
master_seminar
 
SAND: A Fault-Tolerant Streaming Architecture for Network Traffic Analytics
SAND: A Fault-Tolerant Streaming Architecture for Network Traffic AnalyticsSAND: A Fault-Tolerant Streaming Architecture for Network Traffic Analytics
SAND: A Fault-Tolerant Streaming Architecture for Network Traffic Analytics
 
VL/HCC 2014 - A Longitudinal Study of Programmers' Backtracking
VL/HCC 2014 - A Longitudinal Study of Programmers' BacktrackingVL/HCC 2014 - A Longitudinal Study of Programmers' Backtracking
VL/HCC 2014 - A Longitudinal Study of Programmers' Backtracking
 
IRJET- Criminal Recognization in CCTV Surveillance Video
IRJET-  	  Criminal Recognization in CCTV Surveillance VideoIRJET-  	  Criminal Recognization in CCTV Surveillance Video
IRJET- Criminal Recognization in CCTV Surveillance Video
 
Automating Speed: A Proven Approach to Preventing Performance Regressions in ...
Automating Speed: A Proven Approach to Preventing Performance Regressions in ...Automating Speed: A Proven Approach to Preventing Performance Regressions in ...
Automating Speed: A Proven Approach to Preventing Performance Regressions in ...
 
Simple Drools Examples
Simple Drools ExamplesSimple Drools Examples
Simple Drools Examples
 
Face Detection And Tracking
Face Detection And TrackingFace Detection And Tracking
Face Detection And Tracking
 
IRJET- Automated Student’s Attendance Management using Convolutional Neural N...
IRJET- Automated Student’s Attendance Management using Convolutional Neural N...IRJET- Automated Student’s Attendance Management using Convolutional Neural N...
IRJET- Automated Student’s Attendance Management using Convolutional Neural N...
 
Prometheus: From technical metrics to business observability
Prometheus: From technical metrics to business observabilityPrometheus: From technical metrics to business observability
Prometheus: From technical metrics to business observability
 
C programming project by navin thapa
C programming project by navin thapaC programming project by navin thapa
C programming project by navin thapa
 
On-line, non-clairvoyant optimization of workflow activity granularity task o...
On-line, non-clairvoyant optimization of workflow activity granularity task o...On-line, non-clairvoyant optimization of workflow activity granularity task o...
On-line, non-clairvoyant optimization of workflow activity granularity task o...
 
Next generation alerting and fault detection, SRECon Europe 2016
Next generation alerting and fault detection, SRECon Europe 2016Next generation alerting and fault detection, SRECon Europe 2016
Next generation alerting and fault detection, SRECon Europe 2016
 
Digital Signal Processinf (DSP) Course Outline
Digital Signal Processinf (DSP) Course OutlineDigital Signal Processinf (DSP) Course Outline
Digital Signal Processinf (DSP) Course Outline
 
3D Functional Tolerancing And Annotation CATIA
3D Functional Tolerancing And Annotation CATIA3D Functional Tolerancing And Annotation CATIA
3D Functional Tolerancing And Annotation CATIA
 

Recently uploaded

An experimental study in using natural admixture as an alternative for chemic...
An experimental study in using natural admixture as an alternative for chemic...An experimental study in using natural admixture as an alternative for chemic...
An experimental study in using natural admixture as an alternative for chemic...Chandu841456
 
Call Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile serviceCall Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile servicerehmti665
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfAsst.prof M.Gokilavani
 
Artificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptxArtificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptxbritheesh05
 
An introduction to Semiconductor and its types.pptx
An introduction to Semiconductor and its types.pptxAn introduction to Semiconductor and its types.pptx
An introduction to Semiconductor and its types.pptxPurva Nikam
 
Introduction to Machine Learning Unit-3 for II MECH
Introduction to Machine Learning Unit-3 for II MECHIntroduction to Machine Learning Unit-3 for II MECH
Introduction to Machine Learning Unit-3 for II MECHC Sai Kiran
 
Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...VICTOR MAESTRE RAMIREZ
 
Biology for Computer Engineers Course Handout.pptx
Biology for Computer Engineers Course Handout.pptxBiology for Computer Engineers Course Handout.pptx
Biology for Computer Engineers Course Handout.pptxDeepakSakkari2
 
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsyncWhy does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsyncssuser2ae721
 
Oxy acetylene welding presentation note.
Oxy acetylene welding presentation note.Oxy acetylene welding presentation note.
Oxy acetylene welding presentation note.eptoze12
 
Risk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdfRisk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdfROCENODodongVILLACER
 
Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)
Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)
Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)dollysharma2066
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxJoão Esperancinha
 
Correctly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleCorrectly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleAlluxio, Inc.
 

Recently uploaded (20)

An experimental study in using natural admixture as an alternative for chemic...
An experimental study in using natural admixture as an alternative for chemic...An experimental study in using natural admixture as an alternative for chemic...
An experimental study in using natural admixture as an alternative for chemic...
 
Call Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile serviceCall Girls Delhi {Jodhpur} 9711199012 high profile service
Call Girls Delhi {Jodhpur} 9711199012 high profile service
 
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Serviceyoung call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
young call girls in Rajiv Chowk🔝 9953056974 🔝 Delhi escort Service
 
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdfCCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
CCS355 Neural Network & Deep Learning UNIT III notes and Question bank .pdf
 
Artificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptxArtificial-Intelligence-in-Electronics (K).pptx
Artificial-Intelligence-in-Electronics (K).pptx
 
An introduction to Semiconductor and its types.pptx
An introduction to Semiconductor and its types.pptxAn introduction to Semiconductor and its types.pptx
An introduction to Semiconductor and its types.pptx
 
9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf
9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf
9953056974 Call Girls In South Ex, Escorts (Delhi) NCR.pdf
 
Introduction to Machine Learning Unit-3 for II MECH
Introduction to Machine Learning Unit-3 for II MECHIntroduction to Machine Learning Unit-3 for II MECH
Introduction to Machine Learning Unit-3 for II MECH
 
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptxExploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
Exploring_Network_Security_with_JA3_by_Rakesh Seal.pptx
 
Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...Software and Systems Engineering Standards: Verification and Validation of Sy...
Software and Systems Engineering Standards: Verification and Validation of Sy...
 
Biology for Computer Engineers Course Handout.pptx
Biology for Computer Engineers Course Handout.pptxBiology for Computer Engineers Course Handout.pptx
Biology for Computer Engineers Course Handout.pptx
 
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsyncWhy does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
Why does (not) Kafka need fsync: Eliminating tail latency spikes caused by fsync
 
Design and analysis of solar grass cutter.pdf
Design and analysis of solar grass cutter.pdfDesign and analysis of solar grass cutter.pdf
Design and analysis of solar grass cutter.pdf
 
Oxy acetylene welding presentation note.
Oxy acetylene welding presentation note.Oxy acetylene welding presentation note.
Oxy acetylene welding presentation note.
 
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
🔝9953056974🔝!!-YOUNG call girls in Rajendra Nagar Escort rvice Shot 2000 nigh...
 
Risk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdfRisk Assessment For Installation of Drainage Pipes.pdf
Risk Assessment For Installation of Drainage Pipes.pdf
 
Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)
Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)
Call Us ≽ 8377877756 ≼ Call Girls In Shastri Nagar (Delhi)
 
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptxDecoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
Decoding Kotlin - Your guide to solving the mysterious in Kotlin.pptx
 
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCRCall Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
Call Us -/9953056974- Call Girls In Vikaspuri-/- Delhi NCR
 
Correctly Loading Incremental Data at Scale
Correctly Loading Incremental Data at ScaleCorrectly Loading Incremental Data at Scale
Correctly Loading Incremental Data at Scale
 

Fast Person Re-Identification for Intelligent Video Surveillance Systems