SlideShare a Scribd company logo
1 of 19
Distributed video analysis
Big Data Expo 2015
Data is important innovation driverLooking forward is key
Access all information in order to make
decisions and achieve their objectives
Grow Live!
Low risk, High Impact
Sprin
t
PoC
Sprin
t
Sprin
t
Sprin
t
Tim
e
Value
WS
Proof of Concept:
• Small 50 -
200hrs
• Fast 4/6 weeks
Sprint:
• Short period (2 weeks)
• Business value after sprint
• Reality check and go/no-go
after each sprint.
Workshop:
• Identification
and Big Data
use case
• 0,5 day
Low risk High impact
Fast earnback Up-and-running
GROW
LIVE
Consumer 360° : the right presence
24/7 business : prevent risks & reduce data-to-action cycle
5-10-2015 6
More and more video!
5-10-2015 7
Online
SecurityTelevision
Inspection
Retail
Sport analysis
Most is done manually
5-10-2015 8
Automating (parts of) the
process:
• Man-machine cooperation
• Fast(er) insights
• Reduce costs
• Easier to scale up
Possibilities
5-10-2015 9
Support for video?
5-10-2015 10
Solutions still largely in the lab
5-10-2015 11
Lots of case studies:
OCR (Pythian)
X-ray analysis (ETH Zurich)
Surveillance (Pivotal)
Image tagging (Flickr)
…
Some software:
Hadoop Image Processing Interface (HIPI)
4Quant: Spark Imaging Layer
StormCV: Apache Storm + OpenCV
…
Challenges
• Computationally expensive (state-full) algorithms
• Large volumes, even when encoded
• Requires video/image connectors and serializers
• Bindings needed for CV libraries (often C/C++)
5-10-2015 12
StormCV = Apache Storm + OpenCV
• Open source https://github.com/sensorstorm/StormCV
• Designed for video streams but can also process files
• Specific model (frames, features etc.) and serialization for these
objects
• Supports the use of the OpenCV library (through JNI interface)
• Scales by defining the number of operations
• Runs on standard Apache Storm cluster
5-10-2015 13
Operation
1
Operation
2
Operation 3Operation
2
Operation
2
Operation 3
An example
5-10-2015 14
Moving object & keypoint detection
An example: the processing pipeline
5-10-2015 15
Decode
video
SIFT
extraction
Backgroun
d
subtraction
Drawer Streamer
Chaining (minimizes I/O)
5-10-2015 16
Decode
video
SIFT
extraction
Backgroun
d
subtraction
Drawer Streamer
Demo/video
• 18 streams
• 9 readers
• 18 detectors
• 1 streamer
• 28 cores total
• Storm 0.9.3 on
AWS cluster
To conclude
• We love pixels… but they are a challenge to crunch
• Automating video processing can improve speed, reduce
costs and easer to scale up and down when needed
• Some specific video solutions exist, no doubt there are
more to come!
5-10-2015 18
Big Data Expo 2015 - Anchormen Distributed video analysis

More Related Content

What's hot

ACE/TAO/CIAO/DAnCE Maintenance overview
ACE/TAO/CIAO/DAnCE Maintenance overviewACE/TAO/CIAO/DAnCE Maintenance overview
ACE/TAO/CIAO/DAnCE Maintenance overviewRemedy IT
 
How To Introduce Cloud Based Load Testing to Your Jenkins Continuous Delivery...
How To Introduce Cloud Based Load Testing to Your Jenkins Continuous Delivery...How To Introduce Cloud Based Load Testing to Your Jenkins Continuous Delivery...
How To Introduce Cloud Based Load Testing to Your Jenkins Continuous Delivery...Jennifer Finney
 
WebRTC Live Q&A and Screen Capture session 3
WebRTC Live Q&A and Screen Capture session 3WebRTC Live Q&A and Screen Capture session 3
WebRTC Live Q&A and Screen Capture session 3Amir Zmora
 
Reduce Test Automation Execution Time by 80%
Reduce Test Automation Execution Time by 80%Reduce Test Automation Execution Time by 80%
Reduce Test Automation Execution Time by 80%TechWell
 
ECTR IoT MisterX & IPS Live Demo
ECTR IoT MisterX & IPS Live DemoECTR IoT MisterX & IPS Live Demo
ECTR IoT MisterX & IPS Live DemoSergey Seleznev
 
Performance and penetration_testing_with_a_partner_how_to_start!
Performance and penetration_testing_with_a_partner_how_to_start!Performance and penetration_testing_with_a_partner_how_to_start!
Performance and penetration_testing_with_a_partner_how_to_start!Sasha Kolomiichuk
 
Testing in a continuous delivery world - Lean Agile Scotland
Testing in a continuous delivery world - Lean Agile ScotlandTesting in a continuous delivery world - Lean Agile Scotland
Testing in a continuous delivery world - Lean Agile ScotlandWouter Lagerweij
 
Your Framework for Success: introduction to JavaScript Testing at Scale
Your Framework for Success: introduction to JavaScript Testing at ScaleYour Framework for Success: introduction to JavaScript Testing at Scale
Your Framework for Success: introduction to JavaScript Testing at ScaleSauce Labs
 
DevDay 2018: Martin Schurz - Aufbau einer Monitoringlösung für moderne Applik...
DevDay 2018: Martin Schurz - Aufbau einer Monitoringlösung für moderne Applik...DevDay 2018: Martin Schurz - Aufbau einer Monitoringlösung für moderne Applik...
DevDay 2018: Martin Schurz - Aufbau einer Monitoringlösung für moderne Applik...DevDay Dresden
 
Dev secops security and compliance at the speed of continuous delivery - owasp
Dev secops  security and compliance at the speed of continuous delivery - owaspDev secops  security and compliance at the speed of continuous delivery - owasp
Dev secops security and compliance at the speed of continuous delivery - owaspDag Rowe
 
Perforce on Tour 2015 - Grab Testing By the Horns and Move
Perforce on Tour 2015 - Grab Testing By the Horns and MovePerforce on Tour 2015 - Grab Testing By the Horns and Move
Perforce on Tour 2015 - Grab Testing By the Horns and MovePerforce
 
HIS 2015: Neil White - Advances in Practical Techniques for Critical Developm...
HIS 2015: Neil White - Advances in Practical Techniques for Critical Developm...HIS 2015: Neil White - Advances in Practical Techniques for Critical Developm...
HIS 2015: Neil White - Advances in Practical Techniques for Critical Developm...AdaCore
 
Automation at Philips Healthcare
Automation at Philips HealthcareAutomation at Philips Healthcare
Automation at Philips HealthcareArnon Axelrod
 

What's hot (14)

ACE/TAO/CIAO/DAnCE Maintenance overview
ACE/TAO/CIAO/DAnCE Maintenance overviewACE/TAO/CIAO/DAnCE Maintenance overview
ACE/TAO/CIAO/DAnCE Maintenance overview
 
How To Introduce Cloud Based Load Testing to Your Jenkins Continuous Delivery...
How To Introduce Cloud Based Load Testing to Your Jenkins Continuous Delivery...How To Introduce Cloud Based Load Testing to Your Jenkins Continuous Delivery...
How To Introduce Cloud Based Load Testing to Your Jenkins Continuous Delivery...
 
WebRTC Live Q&A and Screen Capture session 3
WebRTC Live Q&A and Screen Capture session 3WebRTC Live Q&A and Screen Capture session 3
WebRTC Live Q&A and Screen Capture session 3
 
Reduce Test Automation Execution Time by 80%
Reduce Test Automation Execution Time by 80%Reduce Test Automation Execution Time by 80%
Reduce Test Automation Execution Time by 80%
 
ECTR IoT MisterX & IPS Live Demo
ECTR IoT MisterX & IPS Live DemoECTR IoT MisterX & IPS Live Demo
ECTR IoT MisterX & IPS Live Demo
 
Performance and penetration_testing_with_a_partner_how_to_start!
Performance and penetration_testing_with_a_partner_how_to_start!Performance and penetration_testing_with_a_partner_how_to_start!
Performance and penetration_testing_with_a_partner_how_to_start!
 
Bringing VR to your BIM Process
Bringing VR to your BIM ProcessBringing VR to your BIM Process
Bringing VR to your BIM Process
 
Testing in a continuous delivery world - Lean Agile Scotland
Testing in a continuous delivery world - Lean Agile ScotlandTesting in a continuous delivery world - Lean Agile Scotland
Testing in a continuous delivery world - Lean Agile Scotland
 
Your Framework for Success: introduction to JavaScript Testing at Scale
Your Framework for Success: introduction to JavaScript Testing at ScaleYour Framework for Success: introduction to JavaScript Testing at Scale
Your Framework for Success: introduction to JavaScript Testing at Scale
 
DevDay 2018: Martin Schurz - Aufbau einer Monitoringlösung für moderne Applik...
DevDay 2018: Martin Schurz - Aufbau einer Monitoringlösung für moderne Applik...DevDay 2018: Martin Schurz - Aufbau einer Monitoringlösung für moderne Applik...
DevDay 2018: Martin Schurz - Aufbau einer Monitoringlösung für moderne Applik...
 
Dev secops security and compliance at the speed of continuous delivery - owasp
Dev secops  security and compliance at the speed of continuous delivery - owaspDev secops  security and compliance at the speed of continuous delivery - owasp
Dev secops security and compliance at the speed of continuous delivery - owasp
 
Perforce on Tour 2015 - Grab Testing By the Horns and Move
Perforce on Tour 2015 - Grab Testing By the Horns and MovePerforce on Tour 2015 - Grab Testing By the Horns and Move
Perforce on Tour 2015 - Grab Testing By the Horns and Move
 
HIS 2015: Neil White - Advances in Practical Techniques for Critical Developm...
HIS 2015: Neil White - Advances in Practical Techniques for Critical Developm...HIS 2015: Neil White - Advances in Practical Techniques for Critical Developm...
HIS 2015: Neil White - Advances in Practical Techniques for Critical Developm...
 
Automation at Philips Healthcare
Automation at Philips HealthcareAutomation at Philips Healthcare
Automation at Philips Healthcare
 

Similar to Big Data Expo 2015 - Anchormen Distributed video analysis

Securing Your App Deployments with Tunnels, OIDC, RBAC, and Progressive Deliv...
Securing Your App Deployments with Tunnels, OIDC, RBAC, and Progressive Deliv...Securing Your App Deployments with Tunnels, OIDC, RBAC, and Progressive Deliv...
Securing Your App Deployments with Tunnels, OIDC, RBAC, and Progressive Deliv...Weaveworks
 
Enterprise-Grade DevOps Solutions for a Start Up Budget
Enterprise-Grade DevOps Solutions for a Start Up BudgetEnterprise-Grade DevOps Solutions for a Start Up Budget
Enterprise-Grade DevOps Solutions for a Start Up BudgetDevOps.com
 
[2015-11월 정기 세미나] Cloud Native Platform - Pivotal
[2015-11월 정기 세미나] Cloud Native Platform - Pivotal[2015-11월 정기 세미나] Cloud Native Platform - Pivotal
[2015-11월 정기 세미나] Cloud Native Platform - PivotalOpenStack Korea Community
 
Continuos Integration and Delivery: from Zero to Hero with TeamCity, Docker a...
Continuos Integration and Delivery: from Zero to Hero with TeamCity, Docker a...Continuos Integration and Delivery: from Zero to Hero with TeamCity, Docker a...
Continuos Integration and Delivery: from Zero to Hero with TeamCity, Docker a...Lean IT Consulting
 
Cloud native development without the toil
Cloud native development without the toilCloud native development without the toil
Cloud native development without the toilAmbassador Labs
 
GOTOpia 2/2021 "Cloud Native Development Without the Toil: An Overview of Pra...
GOTOpia 2/2021 "Cloud Native Development Without the Toil: An Overview of Pra...GOTOpia 2/2021 "Cloud Native Development Without the Toil: An Overview of Pra...
GOTOpia 2/2021 "Cloud Native Development Without the Toil: An Overview of Pra...Daniel Bryant
 
Arm html5 presentation
Arm html5 presentationArm html5 presentation
Arm html5 presentationIan Renyard
 
Pivotal + Apigee Workshop (June 4th, 2019)
Pivotal + Apigee Workshop (June 4th, 2019)Pivotal + Apigee Workshop (June 4th, 2019)
Pivotal + Apigee Workshop (June 4th, 2019)Alexandre Roman
 
AWS live hack: Atlassian + Snyk OSS on AWS
AWS live hack: Atlassian + Snyk OSS on AWSAWS live hack: Atlassian + Snyk OSS on AWS
AWS live hack: Atlassian + Snyk OSS on AWSEric Smalling
 
Continuous Performance Testing: The New Standard
Continuous Performance Testing: The New StandardContinuous Performance Testing: The New Standard
Continuous Performance Testing: The New StandardTechWell
 
Volta: Logging, Metrics, and Monitoring as a Service
Volta: Logging, Metrics, and Monitoring as a ServiceVolta: Logging, Metrics, and Monitoring as a Service
Volta: Logging, Metrics, and Monitoring as a ServiceLN Renganarayana
 
Removing Barriers Between Dev and Ops
Removing Barriers Between Dev and OpsRemoving Barriers Between Dev and Ops
Removing Barriers Between Dev and OpsVMware Tanzu
 
Achieving end to-end bidirectional traceability in complex software projects
Achieving end to-end bidirectional traceability in complex software projectsAchieving end to-end bidirectional traceability in complex software projects
Achieving end to-end bidirectional traceability in complex software projectsIntland Software GmbH
 
Taking AppSec to 11 - BSides Austin 2016
Taking AppSec to 11 - BSides Austin 2016Taking AppSec to 11 - BSides Austin 2016
Taking AppSec to 11 - BSides Austin 2016Matt Tesauro
 
Dances with bits - industrial data analytics made easy!
Dances with bits - industrial data analytics made easy!Dances with bits - industrial data analytics made easy!
Dances with bits - industrial data analytics made easy!Julian Feinauer
 
Sps toronto introduction to azure functions microsoft flow
Sps toronto introduction to azure functions microsoft flowSps toronto introduction to azure functions microsoft flow
Sps toronto introduction to azure functions microsoft flowVincent Biret
 
Cerberus : Framework for Manual and Automated Testing (Web Application)
Cerberus : Framework for Manual and Automated Testing (Web Application)Cerberus : Framework for Manual and Automated Testing (Web Application)
Cerberus : Framework for Manual and Automated Testing (Web Application)CIVEL Benoit
 
Cerberus_Presentation1
Cerberus_Presentation1Cerberus_Presentation1
Cerberus_Presentation1CIVEL Benoit
 
Taking AppSec to 11: AppSec Pipeline, DevOps and Making Things Better
Taking AppSec to 11: AppSec Pipeline, DevOps and Making Things BetterTaking AppSec to 11: AppSec Pipeline, DevOps and Making Things Better
Taking AppSec to 11: AppSec Pipeline, DevOps and Making Things BetterMatt Tesauro
 
JAX London 2021: Jumpstart Your Cloud Native Development: An Overview of Prac...
JAX London 2021: Jumpstart Your Cloud Native Development: An Overview of Prac...JAX London 2021: Jumpstart Your Cloud Native Development: An Overview of Prac...
JAX London 2021: Jumpstart Your Cloud Native Development: An Overview of Prac...Daniel Bryant
 

Similar to Big Data Expo 2015 - Anchormen Distributed video analysis (20)

Securing Your App Deployments with Tunnels, OIDC, RBAC, and Progressive Deliv...
Securing Your App Deployments with Tunnels, OIDC, RBAC, and Progressive Deliv...Securing Your App Deployments with Tunnels, OIDC, RBAC, and Progressive Deliv...
Securing Your App Deployments with Tunnels, OIDC, RBAC, and Progressive Deliv...
 
Enterprise-Grade DevOps Solutions for a Start Up Budget
Enterprise-Grade DevOps Solutions for a Start Up BudgetEnterprise-Grade DevOps Solutions for a Start Up Budget
Enterprise-Grade DevOps Solutions for a Start Up Budget
 
[2015-11월 정기 세미나] Cloud Native Platform - Pivotal
[2015-11월 정기 세미나] Cloud Native Platform - Pivotal[2015-11월 정기 세미나] Cloud Native Platform - Pivotal
[2015-11월 정기 세미나] Cloud Native Platform - Pivotal
 
Continuos Integration and Delivery: from Zero to Hero with TeamCity, Docker a...
Continuos Integration and Delivery: from Zero to Hero with TeamCity, Docker a...Continuos Integration and Delivery: from Zero to Hero with TeamCity, Docker a...
Continuos Integration and Delivery: from Zero to Hero with TeamCity, Docker a...
 
Cloud native development without the toil
Cloud native development without the toilCloud native development without the toil
Cloud native development without the toil
 
GOTOpia 2/2021 "Cloud Native Development Without the Toil: An Overview of Pra...
GOTOpia 2/2021 "Cloud Native Development Without the Toil: An Overview of Pra...GOTOpia 2/2021 "Cloud Native Development Without the Toil: An Overview of Pra...
GOTOpia 2/2021 "Cloud Native Development Without the Toil: An Overview of Pra...
 
Arm html5 presentation
Arm html5 presentationArm html5 presentation
Arm html5 presentation
 
Pivotal + Apigee Workshop (June 4th, 2019)
Pivotal + Apigee Workshop (June 4th, 2019)Pivotal + Apigee Workshop (June 4th, 2019)
Pivotal + Apigee Workshop (June 4th, 2019)
 
AWS live hack: Atlassian + Snyk OSS on AWS
AWS live hack: Atlassian + Snyk OSS on AWSAWS live hack: Atlassian + Snyk OSS on AWS
AWS live hack: Atlassian + Snyk OSS on AWS
 
Continuous Performance Testing: The New Standard
Continuous Performance Testing: The New StandardContinuous Performance Testing: The New Standard
Continuous Performance Testing: The New Standard
 
Volta: Logging, Metrics, and Monitoring as a Service
Volta: Logging, Metrics, and Monitoring as a ServiceVolta: Logging, Metrics, and Monitoring as a Service
Volta: Logging, Metrics, and Monitoring as a Service
 
Removing Barriers Between Dev and Ops
Removing Barriers Between Dev and OpsRemoving Barriers Between Dev and Ops
Removing Barriers Between Dev and Ops
 
Achieving end to-end bidirectional traceability in complex software projects
Achieving end to-end bidirectional traceability in complex software projectsAchieving end to-end bidirectional traceability in complex software projects
Achieving end to-end bidirectional traceability in complex software projects
 
Taking AppSec to 11 - BSides Austin 2016
Taking AppSec to 11 - BSides Austin 2016Taking AppSec to 11 - BSides Austin 2016
Taking AppSec to 11 - BSides Austin 2016
 
Dances with bits - industrial data analytics made easy!
Dances with bits - industrial data analytics made easy!Dances with bits - industrial data analytics made easy!
Dances with bits - industrial data analytics made easy!
 
Sps toronto introduction to azure functions microsoft flow
Sps toronto introduction to azure functions microsoft flowSps toronto introduction to azure functions microsoft flow
Sps toronto introduction to azure functions microsoft flow
 
Cerberus : Framework for Manual and Automated Testing (Web Application)
Cerberus : Framework for Manual and Automated Testing (Web Application)Cerberus : Framework for Manual and Automated Testing (Web Application)
Cerberus : Framework for Manual and Automated Testing (Web Application)
 
Cerberus_Presentation1
Cerberus_Presentation1Cerberus_Presentation1
Cerberus_Presentation1
 
Taking AppSec to 11: AppSec Pipeline, DevOps and Making Things Better
Taking AppSec to 11: AppSec Pipeline, DevOps and Making Things BetterTaking AppSec to 11: AppSec Pipeline, DevOps and Making Things Better
Taking AppSec to 11: AppSec Pipeline, DevOps and Making Things Better
 
JAX London 2021: Jumpstart Your Cloud Native Development: An Overview of Prac...
JAX London 2021: Jumpstart Your Cloud Native Development: An Overview of Prac...JAX London 2021: Jumpstart Your Cloud Native Development: An Overview of Prac...
JAX London 2021: Jumpstart Your Cloud Native Development: An Overview of Prac...
 

More from BigDataExpo

Centric - Jaap huisprijzen, GTST, The Bold, IKEA en IENS. Zomaar wat toepassi...
Centric - Jaap huisprijzen, GTST, The Bold, IKEA en IENS. Zomaar wat toepassi...Centric - Jaap huisprijzen, GTST, The Bold, IKEA en IENS. Zomaar wat toepassi...
Centric - Jaap huisprijzen, GTST, The Bold, IKEA en IENS. Zomaar wat toepassi...BigDataExpo
 
Google Cloud - Google's vision on AI
Google Cloud - Google's vision on AIGoogle Cloud - Google's vision on AI
Google Cloud - Google's vision on AIBigDataExpo
 
Pacmed - Machine Learning in health care: opportunities and challanges in pra...
Pacmed - Machine Learning in health care: opportunities and challanges in pra...Pacmed - Machine Learning in health care: opportunities and challanges in pra...
Pacmed - Machine Learning in health care: opportunities and challanges in pra...BigDataExpo
 
PGGM - The Future Explore
PGGM - The Future ExplorePGGM - The Future Explore
PGGM - The Future ExploreBigDataExpo
 
Universiteit Utrecht & gghdc - Wat zijn de gezondheidseffecten van omgeving e...
Universiteit Utrecht & gghdc - Wat zijn de gezondheidseffecten van omgeving e...Universiteit Utrecht & gghdc - Wat zijn de gezondheidseffecten van omgeving e...
Universiteit Utrecht & gghdc - Wat zijn de gezondheidseffecten van omgeving e...BigDataExpo
 
Rob van Kranenburg - Kunnen we ons een sociaal krediet systeem zoals in het o...
Rob van Kranenburg - Kunnen we ons een sociaal krediet systeem zoals in het o...Rob van Kranenburg - Kunnen we ons een sociaal krediet systeem zoals in het o...
Rob van Kranenburg - Kunnen we ons een sociaal krediet systeem zoals in het o...BigDataExpo
 
OrangeNXT - High accuracy mapping from videos for efficient fiber optic cable...
OrangeNXT - High accuracy mapping from videos for efficient fiber optic cable...OrangeNXT - High accuracy mapping from videos for efficient fiber optic cable...
OrangeNXT - High accuracy mapping from videos for efficient fiber optic cable...BigDataExpo
 
Dynniq & GoDataDriven - Shaping the future of traffic with IoT and AI
Dynniq & GoDataDriven - Shaping the future of traffic with IoT and AIDynniq & GoDataDriven - Shaping the future of traffic with IoT and AI
Dynniq & GoDataDriven - Shaping the future of traffic with IoT and AIBigDataExpo
 
Teleperformance - Smart personalized service door het gebruik van Data Science
Teleperformance - Smart personalized service door het gebruik van Data Science Teleperformance - Smart personalized service door het gebruik van Data Science
Teleperformance - Smart personalized service door het gebruik van Data Science BigDataExpo
 
FunXtion - Interactive Digital Fitness with Data Analytics
FunXtion - Interactive Digital Fitness with Data AnalyticsFunXtion - Interactive Digital Fitness with Data Analytics
FunXtion - Interactive Digital Fitness with Data AnalyticsBigDataExpo
 
fashionTrade - Vroeger noemde we dat Big Data
fashionTrade - Vroeger noemde we dat Big DatafashionTrade - Vroeger noemde we dat Big Data
fashionTrade - Vroeger noemde we dat Big DataBigDataExpo
 
BigData Republic - Industrializing data science: a view from the trenches
BigData Republic - Industrializing data science: a view from the trenchesBigData Republic - Industrializing data science: a view from the trenches
BigData Republic - Industrializing data science: a view from the trenchesBigDataExpo
 
Bicos - Hear how a top sportswear company produced cutting-edge data infrastr...
Bicos - Hear how a top sportswear company produced cutting-edge data infrastr...Bicos - Hear how a top sportswear company produced cutting-edge data infrastr...
Bicos - Hear how a top sportswear company produced cutting-edge data infrastr...BigDataExpo
 
Endrse - Next level online samenwerkingen tussen personalities en merken met ...
Endrse - Next level online samenwerkingen tussen personalities en merken met ...Endrse - Next level online samenwerkingen tussen personalities en merken met ...
Endrse - Next level online samenwerkingen tussen personalities en merken met ...BigDataExpo
 
Bovag - Refine-IT - Proces optimalisatie in de automotive sector
Bovag - Refine-IT - Proces optimalisatie in de automotive sectorBovag - Refine-IT - Proces optimalisatie in de automotive sector
Bovag - Refine-IT - Proces optimalisatie in de automotive sectorBigDataExpo
 
Schiphol - Optimale doorstroom van passagiers op Schiphol dankzij slimme data...
Schiphol - Optimale doorstroom van passagiers op Schiphol dankzij slimme data...Schiphol - Optimale doorstroom van passagiers op Schiphol dankzij slimme data...
Schiphol - Optimale doorstroom van passagiers op Schiphol dankzij slimme data...BigDataExpo
 
Veco - Big Data in de Supply Chain: Hoe Process Mining kan helpen kosten te r...
Veco - Big Data in de Supply Chain: Hoe Process Mining kan helpen kosten te r...Veco - Big Data in de Supply Chain: Hoe Process Mining kan helpen kosten te r...
Veco - Big Data in de Supply Chain: Hoe Process Mining kan helpen kosten te r...BigDataExpo
 
Rabobank - There is something about Data
Rabobank - There is something about DataRabobank - There is something about Data
Rabobank - There is something about DataBigDataExpo
 
VU Amsterdam - Big data en datagedreven waardecreatie: valt er nog iets te ki...
VU Amsterdam - Big data en datagedreven waardecreatie: valt er nog iets te ki...VU Amsterdam - Big data en datagedreven waardecreatie: valt er nog iets te ki...
VU Amsterdam - Big data en datagedreven waardecreatie: valt er nog iets te ki...BigDataExpo
 
Booking.com - Data science and experimentation at Booking.com: a data-driven ...
Booking.com - Data science and experimentation at Booking.com: a data-driven ...Booking.com - Data science and experimentation at Booking.com: a data-driven ...
Booking.com - Data science and experimentation at Booking.com: a data-driven ...BigDataExpo
 

More from BigDataExpo (20)

Centric - Jaap huisprijzen, GTST, The Bold, IKEA en IENS. Zomaar wat toepassi...
Centric - Jaap huisprijzen, GTST, The Bold, IKEA en IENS. Zomaar wat toepassi...Centric - Jaap huisprijzen, GTST, The Bold, IKEA en IENS. Zomaar wat toepassi...
Centric - Jaap huisprijzen, GTST, The Bold, IKEA en IENS. Zomaar wat toepassi...
 
Google Cloud - Google's vision on AI
Google Cloud - Google's vision on AIGoogle Cloud - Google's vision on AI
Google Cloud - Google's vision on AI
 
Pacmed - Machine Learning in health care: opportunities and challanges in pra...
Pacmed - Machine Learning in health care: opportunities and challanges in pra...Pacmed - Machine Learning in health care: opportunities and challanges in pra...
Pacmed - Machine Learning in health care: opportunities and challanges in pra...
 
PGGM - The Future Explore
PGGM - The Future ExplorePGGM - The Future Explore
PGGM - The Future Explore
 
Universiteit Utrecht & gghdc - Wat zijn de gezondheidseffecten van omgeving e...
Universiteit Utrecht & gghdc - Wat zijn de gezondheidseffecten van omgeving e...Universiteit Utrecht & gghdc - Wat zijn de gezondheidseffecten van omgeving e...
Universiteit Utrecht & gghdc - Wat zijn de gezondheidseffecten van omgeving e...
 
Rob van Kranenburg - Kunnen we ons een sociaal krediet systeem zoals in het o...
Rob van Kranenburg - Kunnen we ons een sociaal krediet systeem zoals in het o...Rob van Kranenburg - Kunnen we ons een sociaal krediet systeem zoals in het o...
Rob van Kranenburg - Kunnen we ons een sociaal krediet systeem zoals in het o...
 
OrangeNXT - High accuracy mapping from videos for efficient fiber optic cable...
OrangeNXT - High accuracy mapping from videos for efficient fiber optic cable...OrangeNXT - High accuracy mapping from videos for efficient fiber optic cable...
OrangeNXT - High accuracy mapping from videos for efficient fiber optic cable...
 
Dynniq & GoDataDriven - Shaping the future of traffic with IoT and AI
Dynniq & GoDataDriven - Shaping the future of traffic with IoT and AIDynniq & GoDataDriven - Shaping the future of traffic with IoT and AI
Dynniq & GoDataDriven - Shaping the future of traffic with IoT and AI
 
Teleperformance - Smart personalized service door het gebruik van Data Science
Teleperformance - Smart personalized service door het gebruik van Data Science Teleperformance - Smart personalized service door het gebruik van Data Science
Teleperformance - Smart personalized service door het gebruik van Data Science
 
FunXtion - Interactive Digital Fitness with Data Analytics
FunXtion - Interactive Digital Fitness with Data AnalyticsFunXtion - Interactive Digital Fitness with Data Analytics
FunXtion - Interactive Digital Fitness with Data Analytics
 
fashionTrade - Vroeger noemde we dat Big Data
fashionTrade - Vroeger noemde we dat Big DatafashionTrade - Vroeger noemde we dat Big Data
fashionTrade - Vroeger noemde we dat Big Data
 
BigData Republic - Industrializing data science: a view from the trenches
BigData Republic - Industrializing data science: a view from the trenchesBigData Republic - Industrializing data science: a view from the trenches
BigData Republic - Industrializing data science: a view from the trenches
 
Bicos - Hear how a top sportswear company produced cutting-edge data infrastr...
Bicos - Hear how a top sportswear company produced cutting-edge data infrastr...Bicos - Hear how a top sportswear company produced cutting-edge data infrastr...
Bicos - Hear how a top sportswear company produced cutting-edge data infrastr...
 
Endrse - Next level online samenwerkingen tussen personalities en merken met ...
Endrse - Next level online samenwerkingen tussen personalities en merken met ...Endrse - Next level online samenwerkingen tussen personalities en merken met ...
Endrse - Next level online samenwerkingen tussen personalities en merken met ...
 
Bovag - Refine-IT - Proces optimalisatie in de automotive sector
Bovag - Refine-IT - Proces optimalisatie in de automotive sectorBovag - Refine-IT - Proces optimalisatie in de automotive sector
Bovag - Refine-IT - Proces optimalisatie in de automotive sector
 
Schiphol - Optimale doorstroom van passagiers op Schiphol dankzij slimme data...
Schiphol - Optimale doorstroom van passagiers op Schiphol dankzij slimme data...Schiphol - Optimale doorstroom van passagiers op Schiphol dankzij slimme data...
Schiphol - Optimale doorstroom van passagiers op Schiphol dankzij slimme data...
 
Veco - Big Data in de Supply Chain: Hoe Process Mining kan helpen kosten te r...
Veco - Big Data in de Supply Chain: Hoe Process Mining kan helpen kosten te r...Veco - Big Data in de Supply Chain: Hoe Process Mining kan helpen kosten te r...
Veco - Big Data in de Supply Chain: Hoe Process Mining kan helpen kosten te r...
 
Rabobank - There is something about Data
Rabobank - There is something about DataRabobank - There is something about Data
Rabobank - There is something about Data
 
VU Amsterdam - Big data en datagedreven waardecreatie: valt er nog iets te ki...
VU Amsterdam - Big data en datagedreven waardecreatie: valt er nog iets te ki...VU Amsterdam - Big data en datagedreven waardecreatie: valt er nog iets te ki...
VU Amsterdam - Big data en datagedreven waardecreatie: valt er nog iets te ki...
 
Booking.com - Data science and experimentation at Booking.com: a data-driven ...
Booking.com - Data science and experimentation at Booking.com: a data-driven ...Booking.com - Data science and experimentation at Booking.com: a data-driven ...
Booking.com - Data science and experimentation at Booking.com: a data-driven ...
 

Recently uploaded

Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceSapana Sha
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...Boston Institute of Analytics
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfJohn Sterrett
 
RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.natarajan8993
 
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degreeyuu sss
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDRafezzaman
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPramod Kumar Srivastava
 
Biometric Authentication: The Evolution, Applications, Benefits and Challenge...
Biometric Authentication: The Evolution, Applications, Benefits and Challenge...Biometric Authentication: The Evolution, Applications, Benefits and Challenge...
Biometric Authentication: The Evolution, Applications, Benefits and Challenge...GQ Research
 
Defining Constituents, Data Vizzes and Telling a Data Story
Defining Constituents, Data Vizzes and Telling a Data StoryDefining Constituents, Data Vizzes and Telling a Data Story
Defining Constituents, Data Vizzes and Telling a Data StoryJeremy Anderson
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改yuu sss
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdfHuman37
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一F sss
 
Machine learning classification ppt.ppt
Machine learning classification  ppt.pptMachine learning classification  ppt.ppt
Machine learning classification ppt.pptamreenkhanum0307
 
Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Cathrine Wilhelmsen
 
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样vhwb25kk
 
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...Amil Baba Dawood bangali
 
Learn How Data Science Changes Our World
Learn How Data Science Changes Our WorldLearn How Data Science Changes Our World
Learn How Data Science Changes Our WorldEduminds Learning
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Cantervoginip
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFAAndrei Kaleshka
 
Student Profile Sample report on improving academic performance by uniting gr...
Student Profile Sample report on improving academic performance by uniting gr...Student Profile Sample report on improving academic performance by uniting gr...
Student Profile Sample report on improving academic performance by uniting gr...Seán Kennedy
 

Recently uploaded (20)

Call Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts ServiceCall Girls In Dwarka 9654467111 Escorts Service
Call Girls In Dwarka 9654467111 Escorts Service
 
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
NLP Data Science Project Presentation:Predicting Heart Disease with NLP Data ...
 
DBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdfDBA Basics: Getting Started with Performance Tuning.pdf
DBA Basics: Getting Started with Performance Tuning.pdf
 
RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.RABBIT: A CLI tool for identifying bots based on their GitHub events.
RABBIT: A CLI tool for identifying bots based on their GitHub events.
 
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
毕业文凭制作#回国入职#diploma#degree澳洲中央昆士兰大学毕业证成绩单pdf电子版制作修改#毕业文凭制作#回国入职#diploma#degree
 
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTDINTERNSHIP ON PURBASHA COMPOSITE TEX LTD
INTERNSHIP ON PURBASHA COMPOSITE TEX LTD
 
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptxPKS-TGC-1084-630 - Stage 1 Proposal.pptx
PKS-TGC-1084-630 - Stage 1 Proposal.pptx
 
Biometric Authentication: The Evolution, Applications, Benefits and Challenge...
Biometric Authentication: The Evolution, Applications, Benefits and Challenge...Biometric Authentication: The Evolution, Applications, Benefits and Challenge...
Biometric Authentication: The Evolution, Applications, Benefits and Challenge...
 
Defining Constituents, Data Vizzes and Telling a Data Story
Defining Constituents, Data Vizzes and Telling a Data StoryDefining Constituents, Data Vizzes and Telling a Data Story
Defining Constituents, Data Vizzes and Telling a Data Story
 
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
专业一比一美国俄亥俄大学毕业证成绩单pdf电子版制作修改
 
20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf20240419 - Measurecamp Amsterdam - SAM.pdf
20240419 - Measurecamp Amsterdam - SAM.pdf
 
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
办理学位证中佛罗里达大学毕业证,UCF成绩单原版一比一
 
Machine learning classification ppt.ppt
Machine learning classification  ppt.pptMachine learning classification  ppt.ppt
Machine learning classification ppt.ppt
 
Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)Data Factory in Microsoft Fabric (MsBIP #82)
Data Factory in Microsoft Fabric (MsBIP #82)
 
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
1:1定制(UQ毕业证)昆士兰大学毕业证成绩单修改留信学历认证原版一模一样
 
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
NO1 Certified Black Magic Specialist Expert Amil baba in Lahore Islamabad Raw...
 
Learn How Data Science Changes Our World
Learn How Data Science Changes Our WorldLearn How Data Science Changes Our World
Learn How Data Science Changes Our World
 
ASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel CanterASML's Taxonomy Adventure by Daniel Canter
ASML's Taxonomy Adventure by Daniel Canter
 
How we prevented account sharing with MFA
How we prevented account sharing with MFAHow we prevented account sharing with MFA
How we prevented account sharing with MFA
 
Student Profile Sample report on improving academic performance by uniting gr...
Student Profile Sample report on improving academic performance by uniting gr...Student Profile Sample report on improving academic performance by uniting gr...
Student Profile Sample report on improving academic performance by uniting gr...
 

Big Data Expo 2015 - Anchormen Distributed video analysis

  • 2. Data is important innovation driverLooking forward is key Access all information in order to make decisions and achieve their objectives Grow Live!
  • 3. Low risk, High Impact Sprin t PoC Sprin t Sprin t Sprin t Tim e Value WS Proof of Concept: • Small 50 - 200hrs • Fast 4/6 weeks Sprint: • Short period (2 weeks) • Business value after sprint • Reality check and go/no-go after each sprint. Workshop: • Identification and Big Data use case • 0,5 day Low risk High impact Fast earnback Up-and-running GROW LIVE
  • 4. Consumer 360° : the right presence
  • 5. 24/7 business : prevent risks & reduce data-to-action cycle
  • 7. More and more video! 5-10-2015 7 Online SecurityTelevision Inspection Retail Sport analysis
  • 8. Most is done manually 5-10-2015 8 Automating (parts of) the process: • Man-machine cooperation • Fast(er) insights • Reduce costs • Easier to scale up
  • 11. Solutions still largely in the lab 5-10-2015 11 Lots of case studies: OCR (Pythian) X-ray analysis (ETH Zurich) Surveillance (Pivotal) Image tagging (Flickr) … Some software: Hadoop Image Processing Interface (HIPI) 4Quant: Spark Imaging Layer StormCV: Apache Storm + OpenCV …
  • 12. Challenges • Computationally expensive (state-full) algorithms • Large volumes, even when encoded • Requires video/image connectors and serializers • Bindings needed for CV libraries (often C/C++) 5-10-2015 12
  • 13. StormCV = Apache Storm + OpenCV • Open source https://github.com/sensorstorm/StormCV • Designed for video streams but can also process files • Specific model (frames, features etc.) and serialization for these objects • Supports the use of the OpenCV library (through JNI interface) • Scales by defining the number of operations • Runs on standard Apache Storm cluster 5-10-2015 13 Operation 1 Operation 2 Operation 3Operation 2 Operation 2 Operation 3
  • 14. An example 5-10-2015 14 Moving object & keypoint detection
  • 15. An example: the processing pipeline 5-10-2015 15 Decode video SIFT extraction Backgroun d subtraction Drawer Streamer
  • 16. Chaining (minimizes I/O) 5-10-2015 16 Decode video SIFT extraction Backgroun d subtraction Drawer Streamer
  • 17. Demo/video • 18 streams • 9 readers • 18 detectors • 1 streamer • 28 cores total • Storm 0.9.3 on AWS cluster
  • 18. To conclude • We love pixels… but they are a challenge to crunch • Automating video processing can improve speed, reduce costs and easer to scale up and down when needed • Some specific video solutions exist, no doubt there are more to come! 5-10-2015 18

Editor's Notes

  1. Anchormen gelooft dat bedrijven op het juiste moment en op de juiste manier kunnen handelen. Omdat wij vernieuwend denken over het genereren van inzicht, weten we zeker dat we dit geloof met onze oplossingen kunnen waarmaken. Digitalisering verandert de wereld razendsnel. Naast terugkijken, moeten bedrijven weten wat er nu speelt en anticiperen op wat er gaat gebeuren. Datavolumes, dataverscheidenheid en de snelheid van data nemen alleen maar toe en het is dan ook onze missie om organisaties van zoveel mogelijk relevante en waardevolle informatie te voorzien. Dit is wat we doen Als experts in data excellence leveren we diensten als business innovatie consultancy, data science, data architectuur, engineering, training en support. We bedenken en implementeren unieke data gedreven scenario’s waarmee bedrijven sneller en effectiever kunnen handelen. Concreet gezegd zorgen we ervoor dat data ontsloten wordt zodat deze samengebracht kunnen worden met andere data. Vervolgens extraheren we hier bruikbare informatie uit waarmee de juiste beslissingen genomen kunnen worden. Anchormen bestaat uit een enthousiast en gedreven team. Het Anchormen team is klein, maar dat biedt in onze ogen meer voordelen dan nadelen. We zijn allesbehalve een logge organisatie en projecten worden daardoor snel doorgevoerd. Ook zijn we zeer flexibel en efficiënt ten opzichte van de grotere IT-spelers. Grow Live We werken aan de hand van onze Grow Live aanpak. Dit betekent dat we altijd klein starten met een project. Aan de hand van workshops en proof concepts laten we de impact van onze oplossingen zien. Pas daarna starten we met de ontwikkeling. Die ontwikkeling delen we dan weer op in korte sprints waarbij we tweewekelijks onderdelen opleveren. Zo voegen we regelmatig direct inzetbare waarde toe en kunnen we plannen steeds bijsturen om ervoor te zorgen dat we altijd werkzaamheden uitvoeren die aansluiten bij de vraag van onze klant.
  2. Overall Results: Low Risk: small investment steps. Continuous evaluation Quality: Solution aligned with reality Business has earned back part of the investment Customers is up and running Grow Live Bij grote IT-leveranciers worden ICT-projecten vaak in één keer opgeleverd. Na een lang ontwikkelingstraject krijgen bedrijven eindelijk resultaten te zien, maar juist die lange tijd tussen het geven van de opdracht en het opleveren van de opdracht zorgt vaak voor problemen. Zo kan de markt in de tussentijd alweer veranderd zijn waardoor de behoeften van het bedrijf mee veranderen. Daarnaast kunnen er ook fouten gemaakt zijn die pas na de oplevering aan het licht komen en daardoor moeilijk te herstellen zijn. Anchormen doet er alles aan om bovenstaande risico’s te verlagen. Wij werken daarom volgens ons eigen Grow Live principe. Doordat we onze klanten steeds betrekken bij onze data excellence projecten groeien we mee met het proces van onze klant. Dat meegroeien houdt in dat we klein starten. Aan de hand van workshops en een proof of concept laten we de klant eerst zien wat Anchormen te bieden heeft. Pas nadat er een gedegen plan staat, start de ontwikkeling. Bedrijven zijn dan vrij om te kiezen voor het wel of niet onderbrengen van data in de cloud. Wel zijn er veel voordelen van het opslaan van data in de cloud. Ten eerste ontstaat er snel inzicht in de beschikbare data en ten tweede hoeft er vaak bijna niet direct geïnvesteerd te worden in hard- en software. De gehele ontwikkeling van de oplossing delen we op in korte sprints. Elke twee weken leveren we een deel van de oplossing op. We voegen zo niet alleen regelmatig direct inzetbare waarde toe, ook zijn de risico’s hierdoor zeer laag, want we kunnen de plannen elk moment bijsturen.
  3. Met deze oplossing creëren B2C-bedrijven moeiteloos een 360˚ klantbeeld. Alles draait om het ontsluiten van databronnen. We brengen data uit die bronnen samen zodat hier informatie uitgehaald kan worden die op het juiste moment en in het juiste formaat beschikbaar gesteld wordt via het juiste kanaal.Organisaties kunnen zo op het juiste moment de juiste beslissingen nemen. Op een relevante manier verbinden en communiceren op basis van vertrouwen en persoonlijke interesse. Daar draait het volgens ons om. Digitalisering verandert de wereld razendsnel en de consumentenrevolutie is al lange tijd gaande. Klanten vinden bedrijven op allerlei verschillende manieren. Of ze nu bellen, websites bezoeken of gebruik maken van de social kanalen of apps, consumenten benaderen bedrijven op de manier die ze zelf prettig vinden. Belangrijk voor bedrijven is dus om overal aanwezig te zijn, maar dat is inmiddels geen nieuws meer. Het is immers nóg belangrijker om al die verschillende contactmomenten met de klant te gebruiken om te verbinden. Het verzamelen van data die vrijkomt bij al die contactmomenten en het omvormen van die data tot bruikbare informatie is daarbij noodzakelijk. Hierbij speelt Anchormen een belangrijke rol. Juiste beslissingen op het juiste moment Met de oplossing Consumer 360˚ zorgt Anchormen voor het ontsluiten van databronnen. Vanuit die verschillende bronnen worden data samengebracht zodat informatie op het juiste moment en in het juiste formaat via het juiste kanaal beschikbaar wordt gesteld. Bedrijven kunnen aan de hand van deze informatie op het juiste moment de juiste beslissingen maken. Dat is het doel. Bij Anchormen bouwen we graag een vertrouwensband op met onze klanten en we beginnen onze projecten daardoor altijd klein. Met onze Grow Live aanpak groeien we mee in het proces van onze klant. Anchormen biedt verschillende diensten zoals business innovatie consultancy, data science, data architectuur, engineering en training en support. Graag werken we als team binnen de organisatie van onze klanten. Zo kunnen we snel schakelen en behalen we snel resultaat. Geen investeringen in hard- en software Aan de hand van workshops en een proof of concept geven we inzicht in de impact van onze oplossingen. Pas daarna start de ontwikkeling. Omdat we data in de cloud onderbrengen start die ontwikkeling bijna nooit met grote investeringen in hard- en software. Daarnaast plannen we tweewekelijks innovatiemomenten waarbij we steeds delen van het project opleveren. Met deze korte sprints voorkomen we dat er één groot oplevermoment is aan het einde van traject. De essentie van Grow Live is dat we kleine, maar snelle stappen zetten. Bij elke stap voegen we direct inzetbare waarde toe aan het bedrijf. Belangrijk voordeel hierbij is dat we na elke stap kunnen bijsturen. Hierdoor verlagen we risico’s. Lees hier meer over onze Grow Live aanpak.
  4. Prevent risks B2B-bedrijven continuïteit en zekerheid bieden aan de hand van actueel procesmatig inzicht. Daar staat onze oplossing 24/7 Business voor. Met gebruik van relevante data krijgen bedrijven antwoorden op allerlei vraagstukken waardoor direct geschakeld kan worden. Een absolute must in het internet of things tijdperk waarin steeds meer machines met elkaar ‘praten’. De hoeveelheid data binnen bedrijven neemt alleen maar toe. Niet alleen stijgen de volumes van bijvoorbeeld logistieke en financiële data, ook machines binnen bedrijven zorgen tegenwoordig voor heel veel dataverkeer. Hierbij gaat het niet alleen om datavolume, maar ook om de verscheidenheid en de snelheid van data. Het is zeer wenselijk om al deze machinedata te verzamelen en bruikbaar te maken. Risico’s voorkomen met realtime inzicht Onze oplossing 24/7 Business biedt bedrijven op elk moment helder inzicht in onder andere log-, event- en machinedata. Doordat we werken met realtime data, vinden er steeds vergelijkingen plaats met historische gegevens. Hierdoor ontstaat inzicht in uitzonderingen en risicofactoren. Door direct op deze uitzonderingen in te springen kunnen risico’s verlaagd of zelfs voorkomen worden. Een voorbeeld uit de praktijk: een bedrijf dat installaties bouwt voor bakkersfabrieken maakt gebruik van grote kostbare machines. Als zo’n machine problemen vertoont en niet meer gebruikt kan worden, duurt het vaak lang voordat onderdelen of de gehele machine vervangen kan worden. Door de vertraging die hierbij ontstaat lopen de kosten al snel op. Met 24/7 Business verkrijgen bedrijven diepgaande inzichten en hierbij ontstaat de mogelijkheid om te voorspellen wanneer een onderdeel kapot gaat. Hier kan dan op tijd op geanticipeerd worden om zo downtime tot een minimum te beperken. Grow Live aanpak Bij Anchormen bouwen we graag een vertrouwensband op met onze klanten en we beginnen onze projecten daarom altijd klein. Met onze Grow Live aanpak groeien we mee in het proces van onze klanten. Anchormen biedt verschillende diensten zoals business innovatie consultancy, data science, data architectuur, engineering en training en support. Graag werken we als team binnen de organisatie van onze klanten. Zo kunnen we niet alleen snel schakelen, ook behalen we snel resultaat. Aan de hand van workshops en een proof of concept geven we inzicht in de mogelijkheden van onze oplossingen. Pas daarna start de ontwikkeling en omdat we data in de cloud onderbrengen start die ontwikkeling bijna nooit met grote investeringen in hard- en software. Daarnaast plannen we tweewekelijks innovatiemomenten waarbij we steeds delen van het project opleveren. Hiermee voorkomen we dat er één groot oplevermoment is aan het einde van traject. Door deze kleinere oplevermomenten kunnen plannen steeds bijgestuurd worden en hierdoor verlagen we risico’s.
  5. Lots of video: - Youtube: 300 hours uploaded per minute, / 4 billion video’s watched per day (http://expandedramblings.com/index.php/youtube-statistics/) - as of 2014 adds on video provide more turnover than normal adds (https://gigaom.com/2011/01/24/online-video-ads-5b/) - flicker: 1275 photo’s uploaded per minute (https://www.flickr.com/photos/franckmichel/6855169886) - Instagram: 48.000 photos uploaded per minute (https://instagram.com/press/) - cameras on the streets http://www.cisco.com/c/en/us/solutions/collateral/service-provider/visual-networking-index-vni/VNI_Hyperconnectivity_WP.html -aantal cameras 2013: 204.441 (schiphol: 1400, ns: 4200, rijkswaterstaat: 2700) (http://sargasso.nl/cameratoezicht-in-nederland-hoeveel-cameras-zijn-er-eigenlijk/) - Higher resolution (HD  4K)
  6. Face detection and recognition Logo recognition Object/people tracking Subtitle OCR
  7. Most projects support a range of structured to unstructured data but very little support for video
  8. OCR: - http://www.slideshare.net/Hadoop_Summit/gardner-gorbachev-june27230pmroom230cv2 - https://www.youtube.com/watch?v=oKnq4EvpHHU Pivotal: - https://www.youtube.com/watch?v=uEjeMb81cQ0 - http://blog.pivotal.io/data-science-pivotal/features/large-scale-video-analytics-on-hadoop Hadoop summit: - https://www.youtube.com/watch?v=oKnq4EvpHHU Spark summit 2014: - https://spark-summit.org/2014/talk/scaling-up-fast-real-time-image-processing-and-analytics-using-spark Flickr: - http://code.flickr.net/2014/05/20/computer-vision-at-scale-with-hadoop-and-storm/