SlideShare une entreprise Scribd logo
1  sur  19
Copyright © 2016 Itseez 1
Real-World Vision Systems Design
Challenges and Techniques
Yury Gorbachev
May 3, 2016
Copyright © 2016 Itseez 2
• Computer vision experts, 10 years on market
• Maintainers of OpenCV library
• Own products
• ADAS algorithms suite
• Facence (Face detection, recognition and analysis)
• 3D Scanning (Itseez3D)
• Accelerated CV (Optimized Computer Vision functions)
• Consulting in CV area
• Lot of Proof of Concept work per customer requests
Itseez at Glance
Copyright © 2016 Itseez 3
• Specific handling of requirements for vision projects
• Underestimated role of data
• Compute platform selection fallacies
• Hardware assisted vision algorithms
• Planning for customer feedback
• Functionality for easier product maintenance
Topics to Cover
Copyright © 2016 Itseez 4
• Requirements for vision products require special handling
• Not always possible to predict data variation upfront
• Specific cases will appear during design or test
• Missed scenarios
• Lighting conditions, blur and glare effects, etc.
• Impact can be pretty substantial
• More scenarios to handle — increase in algorithm complexity
• Additional data could be required
Requirements for Vision Products
Copyright © 2016 Itseez 5
• Initial requirement — detect speed limits in Europe
• Standards describe signs pretty well (size, color, etc.)
• Pretty easy to put into requirements
• Some things are not so straightforward to predict though
Example — Speed Limit Sign Detection
Copyright © 2016 Itseez 6
• Computer vision heavily depends on data for training and test
• Innovative products require specific data
• Usually not available in public datasets
• Data collection stage is needed prior to algorithm design
• Collect videos/images, preferably with variation and target HW
• Annotate collected data. At first stages done manually
• This is not always well understood by non-vision related customers
• Not always correctly planned within a project
Good Dataset is a Major Part of Solution
Copyright © 2016 Itseez 7
• Statistics from road sign dataset used at Itseez ADAS
• Not considering different sign types, weather and lighting conditions
• Annotation will take even more
Example — Speed Limit Signs Dataset
Copyright © 2016 Itseez 8
• Plenty of options for compute platform selection
• GPU, DSP and SIMD-enabled SoCs
• Frequently hardware selection is separated from software design
• Could be even pre-selected already before project start
• FACT: Not all compute platforms fit all algorithms
• Separated selection usually results in suboptimal systems
• Higher power consumption & unnecessary complicated algorithms
Premature Compute Platform Selection
Copyright © 2016 Itseez 9
• Vectorization is commonly seen as a solution for most of the problems
• Some SoCs sport few vector units with low frequency and few cores
• Obvious choice, perfect fit for vision!
• Not really… Following algorithm will have almost no benefit from SIMD
Example — Suboptimal Hardware Selection
Keypoint
search
External
sensor
Detailed
search
(Cascade)
ROIs Candidates
Candidate
analysis
Copyright © 2016 Itseez 10
• Optics and sensors should be selected for a given task
• Color vs. grayscale imagers, FOV vs. distance
• Some tasks are significantly simpler when depth information is available
• E.g., stairway detection for robotics
• Vision algorithm can benefit from other sensor systems
• IMU to consider motion and position (e.g., visual odometry)
• LIDAR like cheap sensors in ADAS to limit search range
• Consider cloud for heavy offline processing if no latency requirements
Missed Opportunities for HW Assisted Vision
Copyright © 2016 Itseez 11
• Algorithm working on RGBD is much easier comparing to RGB
• Consider following inputs
Example — Staircase Detection
RGBD image courtesy of: Reza Farid. Region growing planar segmentation for robot action planning
Copyright © 2016 Itseez 12
• Prototype algorithms prior to major work and HW selection
• Understand bottlenecks and challenges  update requirements
• Perform HW selection considering algorithm specifics
• Plan for sync between HW and SW during development
Possible Vision Product Design Model
Algorithm
PoC design Prototype
results
Hardware
approach selection
Hardware
Arch.
Software
drop
Algorithm
development
Hardware
drop
HW
Design
Final
product
Original reqs
Updated
reqs
Copyright © 2016 Itseez 13
• Vision in products is still pretty new to consumers
• Designers of the product create it with some use cases in mind
• Consumers usually use them differently
• This gap need attention prior to product release
• Target group testing, people outside of CV area
• Leave some time for corrective actions
• Algorithm enhancements and changes
• Documentation updates, tutorial videos, etc.
Customer Acceptance Need Some Work
Copyright © 2016 Itseez 14
• Itseez3D application
• Freely available on iPad, needs sensor (Occipital)
• Just walk around a person and scan to get 3D model
• Consumer use cases needed attention
• Tracking from sensor SDK did not support scan interruption
• Own enhanced tracking was implemented
• UI enhancements and video tutorials were done
• Currently about 300 scans per day
Example — Full Body Scanning
Copyright © 2016 Itseez 15
• Most vision products require calibration
• Re-calibration might be needed after some time
• Surveillance cameras change position due to wind/shaking
• Focus/visibility loss in optics due to harsh conditions
• Product tampering
• E.g., cover optics intentionally for some time periods
• Always good to be able to detect those things in software
• Blur & sharp edges detection, circular buffer recording
Maintenance Issues in Vision Products
Copyright © 2016 Itseez 16
One Video Tells More Than Few Slides
• Two problems here
• Optics needs maintenance (algorithm works though)
• Low sales figures...
Copyright © 2016 Itseez 17
• Do not consider requirements as final
• Periodically update with findings, exceptions
• For complicated algorithms perform PoC and iterate planning
• Perform analysis of existing datasets  plan for dataset collection
• Investigate/prototype algorithm prior to hardware selection if possible
• Consider additional sensors as help to vision algorithms
• Ask for customer feedback prior product release
• Place frame source checks in software to detect maintenance issues
Conclusion: Useful Hints
Copyright © 2016 Itseez 18
Q&A
Copyright © 2016 Itseez 19
• Itseez Web — http://www.itseez.com
• Itseez3D Scanning app — http://www.itseez3d.com
• Contact me: yury.gorbachev@itseez.com
Resources and Contacts

Contenu connexe

Tendances

"The Vision API Maze: Options and Trade-offs," a Presentation from the Khrono...
"The Vision API Maze: Options and Trade-offs," a Presentation from the Khrono..."The Vision API Maze: Options and Trade-offs," a Presentation from the Khrono...
"The Vision API Maze: Options and Trade-offs," a Presentation from the Khrono...Edge AI and Vision Alliance
 
"Real-world Vision Systems Design: Challenges and Techniques," a Presentation...
"Real-world Vision Systems Design: Challenges and Techniques," a Presentation..."Real-world Vision Systems Design: Challenges and Techniques," a Presentation...
"Real-world Vision Systems Design: Challenges and Techniques," a Presentation...Edge AI and Vision Alliance
 
Design and Optimize your code for high-performance with Intel® Advisor and I...
Design and Optimize your code for high-performance with Intel®  Advisor and I...Design and Optimize your code for high-performance with Intel®  Advisor and I...
Design and Optimize your code for high-performance with Intel® Advisor and I...Tyrone Systems
 
Tyrone-Intel oneAPI Webinar: Optimized Tools for Performance-Driven, Cross-Ar...
Tyrone-Intel oneAPI Webinar: Optimized Tools for Performance-Driven, Cross-Ar...Tyrone-Intel oneAPI Webinar: Optimized Tools for Performance-Driven, Cross-Ar...
Tyrone-Intel oneAPI Webinar: Optimized Tools for Performance-Driven, Cross-Ar...Tyrone Systems
 
oneAPI: Industry Initiative & Intel Product
oneAPI: Industry Initiative & Intel ProductoneAPI: Industry Initiative & Intel Product
oneAPI: Industry Initiative & Intel ProductTyrone Systems
 
Advanced Single Instruction Multiple Data (SIMD) Programming with Intel® Impl...
Advanced Single Instruction Multiple Data (SIMD) Programming with Intel® Impl...Advanced Single Instruction Multiple Data (SIMD) Programming with Intel® Impl...
Advanced Single Instruction Multiple Data (SIMD) Programming with Intel® Impl...Intel® Software
 
Altair on Intel Xeon Phi: Optimizing HPC for Breakthrough Performance
Altair on Intel Xeon Phi:  Optimizing HPC for Breakthrough PerformanceAltair on Intel Xeon Phi:  Optimizing HPC for Breakthrough Performance
Altair on Intel Xeon Phi: Optimizing HPC for Breakthrough PerformanceIntel IT Center
 
Using the Cypress PSoC Processor
Using the Cypress PSoC ProcessorUsing the Cypress PSoC Processor
Using the Cypress PSoC ProcessorLloydMoore
 
GMG204 TinyCo’s Best Practices for Developing, Scaling, and Monetizing Games ...
GMG204 TinyCo’s Best Practices for Developing, Scaling, and Monetizing Games ...GMG204 TinyCo’s Best Practices for Developing, Scaling, and Monetizing Games ...
GMG204 TinyCo’s Best Practices for Developing, Scaling, and Monetizing Games ...Amazon Web Services
 
GTC15-Manoj-Roge-OpenPOWER
GTC15-Manoj-Roge-OpenPOWERGTC15-Manoj-Roge-OpenPOWER
GTC15-Manoj-Roge-OpenPOWERAchronix
 
!Zpx Overview New
!Zpx Overview New!Zpx Overview New
!Zpx Overview Newcynthiabro
 
Build a Deep Learning Video Analytics Framework | SIGGRAPH 2019 Technical Ses...
Build a Deep Learning Video Analytics Framework | SIGGRAPH 2019 Technical Ses...Build a Deep Learning Video Analytics Framework | SIGGRAPH 2019 Technical Ses...
Build a Deep Learning Video Analytics Framework | SIGGRAPH 2019 Technical Ses...Intel® Software
 
ScilabTEC 2015 - Noesis Solutions
ScilabTEC 2015 - Noesis SolutionsScilabTEC 2015 - Noesis Solutions
ScilabTEC 2015 - Noesis SolutionsScilab
 
Srikanth_PILLI_CV_latest
Srikanth_PILLI_CV_latestSrikanth_PILLI_CV_latest
Srikanth_PILLI_CV_latestSrikanth Pilli
 
Validating Next Generation CPUs
Validating Next Generation CPUsValidating Next Generation CPUs
Validating Next Generation CPUsDVClub
 

Tendances (20)

"The Vision API Maze: Options and Trade-offs," a Presentation from the Khrono...
"The Vision API Maze: Options and Trade-offs," a Presentation from the Khrono..."The Vision API Maze: Options and Trade-offs," a Presentation from the Khrono...
"The Vision API Maze: Options and Trade-offs," a Presentation from the Khrono...
 
"Real-world Vision Systems Design: Challenges and Techniques," a Presentation...
"Real-world Vision Systems Design: Challenges and Techniques," a Presentation..."Real-world Vision Systems Design: Challenges and Techniques," a Presentation...
"Real-world Vision Systems Design: Challenges and Techniques," a Presentation...
 
Design and Optimize your code for high-performance with Intel® Advisor and I...
Design and Optimize your code for high-performance with Intel®  Advisor and I...Design and Optimize your code for high-performance with Intel®  Advisor and I...
Design and Optimize your code for high-performance with Intel® Advisor and I...
 
Tyrone-Intel oneAPI Webinar: Optimized Tools for Performance-Driven, Cross-Ar...
Tyrone-Intel oneAPI Webinar: Optimized Tools for Performance-Driven, Cross-Ar...Tyrone-Intel oneAPI Webinar: Optimized Tools for Performance-Driven, Cross-Ar...
Tyrone-Intel oneAPI Webinar: Optimized Tools for Performance-Driven, Cross-Ar...
 
oneAPI: Industry Initiative & Intel Product
oneAPI: Industry Initiative & Intel ProductoneAPI: Industry Initiative & Intel Product
oneAPI: Industry Initiative & Intel Product
 
Intel Developer Program
Intel Developer ProgramIntel Developer Program
Intel Developer Program
 
Advanced Single Instruction Multiple Data (SIMD) Programming with Intel® Impl...
Advanced Single Instruction Multiple Data (SIMD) Programming with Intel® Impl...Advanced Single Instruction Multiple Data (SIMD) Programming with Intel® Impl...
Advanced Single Instruction Multiple Data (SIMD) Programming with Intel® Impl...
 
Altair on Intel Xeon Phi: Optimizing HPC for Breakthrough Performance
Altair on Intel Xeon Phi:  Optimizing HPC for Breakthrough PerformanceAltair on Intel Xeon Phi:  Optimizing HPC for Breakthrough Performance
Altair on Intel Xeon Phi: Optimizing HPC for Breakthrough Performance
 
Using the Cypress PSoC Processor
Using the Cypress PSoC ProcessorUsing the Cypress PSoC Processor
Using the Cypress PSoC Processor
 
GMG204 TinyCo’s Best Practices for Developing, Scaling, and Monetizing Games ...
GMG204 TinyCo’s Best Practices for Developing, Scaling, and Monetizing Games ...GMG204 TinyCo’s Best Practices for Developing, Scaling, and Monetizing Games ...
GMG204 TinyCo’s Best Practices for Developing, Scaling, and Monetizing Games ...
 
GTC15-Manoj-Roge-OpenPOWER
GTC15-Manoj-Roge-OpenPOWERGTC15-Manoj-Roge-OpenPOWER
GTC15-Manoj-Roge-OpenPOWER
 
!Zpx Overview New
!Zpx Overview New!Zpx Overview New
!Zpx Overview New
 
Build a Deep Learning Video Analytics Framework | SIGGRAPH 2019 Technical Ses...
Build a Deep Learning Video Analytics Framework | SIGGRAPH 2019 Technical Ses...Build a Deep Learning Video Analytics Framework | SIGGRAPH 2019 Technical Ses...
Build a Deep Learning Video Analytics Framework | SIGGRAPH 2019 Technical Ses...
 
ScilabTEC 2015 - Noesis Solutions
ScilabTEC 2015 - Noesis SolutionsScilabTEC 2015 - Noesis Solutions
ScilabTEC 2015 - Noesis Solutions
 
Introduction to usability
Introduction to usabilityIntroduction to usability
Introduction to usability
 
Zehr dv club_12052006
Zehr dv club_12052006Zehr dv club_12052006
Zehr dv club_12052006
 
Srikanth_PILLI_CV_latest
Srikanth_PILLI_CV_latestSrikanth_PILLI_CV_latest
Srikanth_PILLI_CV_latest
 
Validating Next Generation CPUs
Validating Next Generation CPUsValidating Next Generation CPUs
Validating Next Generation CPUs
 
Physical Design Services
Physical Design ServicesPhysical Design Services
Physical Design Services
 
Tinychip PSoC Workshop
Tinychip PSoC WorkshopTinychip PSoC Workshop
Tinychip PSoC Workshop
 

En vedette

Challenges in Designing a Menu System with Touch-less Technology
Challenges in Designing a Menu System with Touch-less TechnologyChallenges in Designing a Menu System with Touch-less Technology
Challenges in Designing a Menu System with Touch-less TechnologyOmek Interactive
 
Activity Recognition using RGBD
Activity Recognition using RGBDActivity Recognition using RGBD
Activity Recognition using RGBDnazlitemu
 
Piloting Mixed Reality in ICT Networking to Visualize Complex Theoretical Mul...
Piloting Mixed Reality in ICT Networking to Visualize Complex Theoretical Mul...Piloting Mixed Reality in ICT Networking to Visualize Complex Theoretical Mul...
Piloting Mixed Reality in ICT Networking to Visualize Complex Theoretical Mul...Bond University
 
"Don’t Freeze! Survive the Ethics of a Mixed Reality Escape Room" by Sherry J...
"Don’t Freeze! Survive the Ethics of a Mixed Reality Escape Room" by Sherry J..."Don’t Freeze! Survive the Ethics of a Mixed Reality Escape Room" by Sherry J...
"Don’t Freeze! Survive the Ethics of a Mixed Reality Escape Room" by Sherry J...Sherry Jones
 
Life in 2100: Focused on Mixed Reality
Life in 2100: Focused on Mixed RealityLife in 2100: Focused on Mixed Reality
Life in 2100: Focused on Mixed RealitySangeetha Mathew
 
Interactive Mixed Reality for Enhanced Learning, Skills and Engagement
Interactive Mixed Reality for Enhanced Learning, Skills and EngagementInteractive Mixed Reality for Enhanced Learning, Skills and Engagement
Interactive Mixed Reality for Enhanced Learning, Skills and EngagementBond University
 
Jared Finder (Google) Creating Mixed Reality Apps and Games with Project Tango
Jared Finder (Google) Creating Mixed Reality Apps and Games with Project TangoJared Finder (Google) Creating Mixed Reality Apps and Games with Project Tango
Jared Finder (Google) Creating Mixed Reality Apps and Games with Project TangoAugmentedWorldExpo
 
3DTV Transmission Aspects
3DTV Transmission Aspects3DTV Transmission Aspects
3DTV Transmission AspectsRaoni Lourenço
 
Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...
Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...
Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...Norishige Fukushima
 
KaoNet: Face Recognition and Generation App using Deep Learning
KaoNet: Face Recognition and Generation App using Deep LearningKaoNet: Face Recognition and Generation App using Deep Learning
KaoNet: Face Recognition and Generation App using Deep LearningVan Huy
 
"The OpenCV Open Source Computer Vision Library: Latest Developments," a Pres...
"The OpenCV Open Source Computer Vision Library: Latest Developments," a Pres..."The OpenCV Open Source Computer Vision Library: Latest Developments," a Pres...
"The OpenCV Open Source Computer Vision Library: Latest Developments," a Pres...Edge AI and Vision Alliance
 
Tangible Interfaces & Mixed Reality : A step toward digital augmented enviro...
Tangible Interfaces & Mixed Reality :  A step toward digital augmented enviro...Tangible Interfaces & Mixed Reality :  A step toward digital augmented enviro...
Tangible Interfaces & Mixed Reality : A step toward digital augmented enviro...lecolededesign
 
Intro to HoloLens Development + Windows Mixed Reality
Intro to HoloLens Development + Windows Mixed RealityIntro to HoloLens Development + Windows Mixed Reality
Intro to HoloLens Development + Windows Mixed RealityShahed Chowdhuri
 
Computer Vision, Deep Learning, OpenCV
Computer Vision, Deep Learning, OpenCVComputer Vision, Deep Learning, OpenCV
Computer Vision, Deep Learning, OpenCVFarshid Pirahansiah
 
Virtual, Augmented & Mixed Reality Matrix: Brand Reach & User Immersion
Virtual, Augmented & Mixed Reality Matrix: Brand Reach & User ImmersionVirtual, Augmented & Mixed Reality Matrix: Brand Reach & User Immersion
Virtual, Augmented & Mixed Reality Matrix: Brand Reach & User ImmersionRori DuBoff
 
The Rise Of Mixed Reality Advertising + Digital Signage
The Rise Of Mixed Reality Advertising + Digital SignageThe Rise Of Mixed Reality Advertising + Digital Signage
The Rise Of Mixed Reality Advertising + Digital SignageVassilis Bakopoulos
 
Mixed Reality met Microsoft HoloLens
Mixed Reality met Microsoft HoloLensMixed Reality met Microsoft HoloLens
Mixed Reality met Microsoft HoloLensAvanade Nederland
 

En vedette (20)

Challenges in Designing a Menu System with Touch-less Technology
Challenges in Designing a Menu System with Touch-less TechnologyChallenges in Designing a Menu System with Touch-less Technology
Challenges in Designing a Menu System with Touch-less Technology
 
Mixed Reality Project
Mixed Reality ProjectMixed Reality Project
Mixed Reality Project
 
Activity Recognition using RGBD
Activity Recognition using RGBDActivity Recognition using RGBD
Activity Recognition using RGBD
 
Piloting Mixed Reality in ICT Networking to Visualize Complex Theoretical Mul...
Piloting Mixed Reality in ICT Networking to Visualize Complex Theoretical Mul...Piloting Mixed Reality in ICT Networking to Visualize Complex Theoretical Mul...
Piloting Mixed Reality in ICT Networking to Visualize Complex Theoretical Mul...
 
"Don’t Freeze! Survive the Ethics of a Mixed Reality Escape Room" by Sherry J...
"Don’t Freeze! Survive the Ethics of a Mixed Reality Escape Room" by Sherry J..."Don’t Freeze! Survive the Ethics of a Mixed Reality Escape Room" by Sherry J...
"Don’t Freeze! Survive the Ethics of a Mixed Reality Escape Room" by Sherry J...
 
Life in 2100: Focused on Mixed Reality
Life in 2100: Focused on Mixed RealityLife in 2100: Focused on Mixed Reality
Life in 2100: Focused on Mixed Reality
 
Interactive Mixed Reality for Enhanced Learning, Skills and Engagement
Interactive Mixed Reality for Enhanced Learning, Skills and EngagementInteractive Mixed Reality for Enhanced Learning, Skills and Engagement
Interactive Mixed Reality for Enhanced Learning, Skills and Engagement
 
Jared Finder (Google) Creating Mixed Reality Apps and Games with Project Tango
Jared Finder (Google) Creating Mixed Reality Apps and Games with Project TangoJared Finder (Google) Creating Mixed Reality Apps and Games with Project Tango
Jared Finder (Google) Creating Mixed Reality Apps and Games with Project Tango
 
Laurel Fitts - The Power of Mixed Reality
Laurel Fitts - The Power of Mixed RealityLaurel Fitts - The Power of Mixed Reality
Laurel Fitts - The Power of Mixed Reality
 
3DTV Transmission Aspects
3DTV Transmission Aspects3DTV Transmission Aspects
3DTV Transmission Aspects
 
Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...
Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...
Non-essentiality of Correlation between Image and Depth Map in Free Viewpoin...
 
KaoNet: Face Recognition and Generation App using Deep Learning
KaoNet: Face Recognition and Generation App using Deep LearningKaoNet: Face Recognition and Generation App using Deep Learning
KaoNet: Face Recognition and Generation App using Deep Learning
 
"The OpenCV Open Source Computer Vision Library: Latest Developments," a Pres...
"The OpenCV Open Source Computer Vision Library: Latest Developments," a Pres..."The OpenCV Open Source Computer Vision Library: Latest Developments," a Pres...
"The OpenCV Open Source Computer Vision Library: Latest Developments," a Pres...
 
Tangible Interfaces & Mixed Reality : A step toward digital augmented enviro...
Tangible Interfaces & Mixed Reality :  A step toward digital augmented enviro...Tangible Interfaces & Mixed Reality :  A step toward digital augmented enviro...
Tangible Interfaces & Mixed Reality : A step toward digital augmented enviro...
 
Intro to HoloLens Development + Windows Mixed Reality
Intro to HoloLens Development + Windows Mixed RealityIntro to HoloLens Development + Windows Mixed Reality
Intro to HoloLens Development + Windows Mixed Reality
 
Computer Vision, Deep Learning, OpenCV
Computer Vision, Deep Learning, OpenCVComputer Vision, Deep Learning, OpenCV
Computer Vision, Deep Learning, OpenCV
 
Mixed reality
Mixed realityMixed reality
Mixed reality
 
Virtual, Augmented & Mixed Reality Matrix: Brand Reach & User Immersion
Virtual, Augmented & Mixed Reality Matrix: Brand Reach & User ImmersionVirtual, Augmented & Mixed Reality Matrix: Brand Reach & User Immersion
Virtual, Augmented & Mixed Reality Matrix: Brand Reach & User Immersion
 
The Rise Of Mixed Reality Advertising + Digital Signage
The Rise Of Mixed Reality Advertising + Digital SignageThe Rise Of Mixed Reality Advertising + Digital Signage
The Rise Of Mixed Reality Advertising + Digital Signage
 
Mixed Reality met Microsoft HoloLens
Mixed Reality met Microsoft HoloLensMixed Reality met Microsoft HoloLens
Mixed Reality met Microsoft HoloLens
 

Similaire à Real-world Vision Systems Design: Challenges and Techniques

Predictive Maintenance - Predict the Unpredictable
Predictive Maintenance - Predict the UnpredictablePredictive Maintenance - Predict the Unpredictable
Predictive Maintenance - Predict the UnpredictableIvo Andreev
 
"Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio...
"Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio..."Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio...
"Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio...Edge AI and Vision Alliance
 
HSA-4146, Creating Smarter Applications and Systems Through Visual Intelligen...
HSA-4146, Creating Smarter Applications and Systems Through Visual Intelligen...HSA-4146, Creating Smarter Applications and Systems Through Visual Intelligen...
HSA-4146, Creating Smarter Applications and Systems Through Visual Intelligen...AMD Developer Central
 
Debugging,Troubleshooting & Monitoring Distributed Web & Cloud Applications a...
Debugging,Troubleshooting & Monitoring Distributed Web & Cloud Applications a...Debugging,Troubleshooting & Monitoring Distributed Web & Cloud Applications a...
Debugging,Troubleshooting & Monitoring Distributed Web & Cloud Applications a...Theo Jungeblut
 
AWS Webcast - Neudesic Data Centermigrationtoaws
AWS Webcast - Neudesic Data CentermigrationtoawsAWS Webcast - Neudesic Data Centermigrationtoaws
AWS Webcast - Neudesic Data CentermigrationtoawsAmazon Web Services
 
Decision Matrix for IoT Product Development
Decision Matrix for IoT Product DevelopmentDecision Matrix for IoT Product Development
Decision Matrix for IoT Product DevelopmentAlexey Pyshkin
 
Introduction to the IBM Java Tools
Introduction to the IBM Java ToolsIntroduction to the IBM Java Tools
Introduction to the IBM Java ToolsChris Bailey
 
"Implementing Eye Tracking for Medical, Automotive and Headset Applications,"...
"Implementing Eye Tracking for Medical, Automotive and Headset Applications,"..."Implementing Eye Tracking for Medical, Automotive and Headset Applications,"...
"Implementing Eye Tracking for Medical, Automotive and Headset Applications,"...Edge AI and Vision Alliance
 
lokesh_UX_Designer_v5
lokesh_UX_Designer_v5lokesh_UX_Designer_v5
lokesh_UX_Designer_v5Lokesh S
 
Application Deployment Patterns in the Cloud - NOVA Cloud and Software Engine...
Application Deployment Patterns in the Cloud - NOVA Cloud and Software Engine...Application Deployment Patterns in the Cloud - NOVA Cloud and Software Engine...
Application Deployment Patterns in the Cloud - NOVA Cloud and Software Engine...Derek Ashmore
 
Design Summit - User stories from the field - Chris Jung
Design Summit - User stories from the field - Chris JungDesign Summit - User stories from the field - Chris Jung
Design Summit - User stories from the field - Chris JungManageIQ
 
10 Steps to Architecting a Sustainable SCADA System
10 Steps to Architecting a Sustainable SCADA System10 Steps to Architecting a Sustainable SCADA System
10 Steps to Architecting a Sustainable SCADA SystemInductive Automation
 
Building ADAS system from scratch
Building ADAS system from scratchBuilding ADAS system from scratch
Building ADAS system from scratchYury Gorbachev
 
Preventative Maintenance of Robots in Automotive Industry
Preventative Maintenance of Robots in Automotive IndustryPreventative Maintenance of Robots in Automotive Industry
Preventative Maintenance of Robots in Automotive IndustryDataWorks Summit/Hadoop Summit
 
CGM (Computer Graphics Metafile) v SVG (Scalable Vector Graphic)
CGM (Computer Graphics Metafile) v SVG (Scalable Vector Graphic)CGM (Computer Graphics Metafile) v SVG (Scalable Vector Graphic)
CGM (Computer Graphics Metafile) v SVG (Scalable Vector Graphic)Vizualsite LLC
 
Computer Vision Technology and Expertise
Computer Vision Technology and ExpertiseComputer Vision Technology and Expertise
Computer Vision Technology and ExpertiseRhonda Software
 
Pose extraction for real time workout assistant - milestone 1
Pose extraction for real time workout assistant - milestone 1Pose extraction for real time workout assistant - milestone 1
Pose extraction for real time workout assistant - milestone 1Zachary Christmas
 
Fundamentals of computer systems
Fundamentals of computer systemsFundamentals of computer systems
Fundamentals of computer systemsSajitha Pathirana
 

Similaire à Real-world Vision Systems Design: Challenges and Techniques (20)

Predictive Maintenance - Predict the Unpredictable
Predictive Maintenance - Predict the UnpredictablePredictive Maintenance - Predict the Unpredictable
Predictive Maintenance - Predict the Unpredictable
 
"Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio...
"Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio..."Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio...
"Multiple Uses of Pipelined Video Pre-Processor Hardware in Vision Applicatio...
 
HSA-4146, Creating Smarter Applications and Systems Through Visual Intelligen...
HSA-4146, Creating Smarter Applications and Systems Through Visual Intelligen...HSA-4146, Creating Smarter Applications and Systems Through Visual Intelligen...
HSA-4146, Creating Smarter Applications and Systems Through Visual Intelligen...
 
Debugging,Troubleshooting & Monitoring Distributed Web & Cloud Applications a...
Debugging,Troubleshooting & Monitoring Distributed Web & Cloud Applications a...Debugging,Troubleshooting & Monitoring Distributed Web & Cloud Applications a...
Debugging,Troubleshooting & Monitoring Distributed Web & Cloud Applications a...
 
AWS Webcast - Neudesic Data Centermigrationtoaws
AWS Webcast - Neudesic Data CentermigrationtoawsAWS Webcast - Neudesic Data Centermigrationtoaws
AWS Webcast - Neudesic Data Centermigrationtoaws
 
Decision Matrix for IoT Product Development
Decision Matrix for IoT Product DevelopmentDecision Matrix for IoT Product Development
Decision Matrix for IoT Product Development
 
Introduction to the IBM Java Tools
Introduction to the IBM Java ToolsIntroduction to the IBM Java Tools
Introduction to the IBM Java Tools
 
"Implementing Eye Tracking for Medical, Automotive and Headset Applications,"...
"Implementing Eye Tracking for Medical, Automotive and Headset Applications,"..."Implementing Eye Tracking for Medical, Automotive and Headset Applications,"...
"Implementing Eye Tracking for Medical, Automotive and Headset Applications,"...
 
lokesh_UX_Designer_v5
lokesh_UX_Designer_v5lokesh_UX_Designer_v5
lokesh_UX_Designer_v5
 
Application Deployment Patterns in the Cloud - NOVA Cloud and Software Engine...
Application Deployment Patterns in the Cloud - NOVA Cloud and Software Engine...Application Deployment Patterns in the Cloud - NOVA Cloud and Software Engine...
Application Deployment Patterns in the Cloud - NOVA Cloud and Software Engine...
 
Design Summit - User stories from the field - Chris Jung
Design Summit - User stories from the field - Chris JungDesign Summit - User stories from the field - Chris Jung
Design Summit - User stories from the field - Chris Jung
 
10 Steps to Architecting a Sustainable SCADA System
10 Steps to Architecting a Sustainable SCADA System10 Steps to Architecting a Sustainable SCADA System
10 Steps to Architecting a Sustainable SCADA System
 
Building ADAS system from scratch
Building ADAS system from scratchBuilding ADAS system from scratch
Building ADAS system from scratch
 
Jobsjobsjobs
JobsjobsjobsJobsjobsjobs
Jobsjobsjobs
 
Preventative Maintenance of Robots in Automotive Industry
Preventative Maintenance of Robots in Automotive IndustryPreventative Maintenance of Robots in Automotive Industry
Preventative Maintenance of Robots in Automotive Industry
 
CGM (Computer Graphics Metafile) v SVG (Scalable Vector Graphic)
CGM (Computer Graphics Metafile) v SVG (Scalable Vector Graphic)CGM (Computer Graphics Metafile) v SVG (Scalable Vector Graphic)
CGM (Computer Graphics Metafile) v SVG (Scalable Vector Graphic)
 
CGM versus SVG
CGM versus SVGCGM versus SVG
CGM versus SVG
 
Computer Vision Technology and Expertise
Computer Vision Technology and ExpertiseComputer Vision Technology and Expertise
Computer Vision Technology and Expertise
 
Pose extraction for real time workout assistant - milestone 1
Pose extraction for real time workout assistant - milestone 1Pose extraction for real time workout assistant - milestone 1
Pose extraction for real time workout assistant - milestone 1
 
Fundamentals of computer systems
Fundamentals of computer systemsFundamentals of computer systems
Fundamentals of computer systems
 

Dernier

VTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnVTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnAmarnathKambale
 
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdfAzure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdfryanfarris8
 
Direct Style Effect Systems - The Print[A] Example - A Comprehension Aid
Direct Style Effect Systems -The Print[A] Example- A Comprehension AidDirect Style Effect Systems -The Print[A] Example- A Comprehension Aid
Direct Style Effect Systems - The Print[A] Example - A Comprehension AidPhilip Schwarz
 
Sector 18, Noida Call girls :8448380779 Model Escorts | 100% verified
Sector 18, Noida Call girls :8448380779 Model Escorts | 100% verifiedSector 18, Noida Call girls :8448380779 Model Escorts | 100% verified
Sector 18, Noida Call girls :8448380779 Model Escorts | 100% verifiedDelhi Call girls
 
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️Delhi Call girls
 
A Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxA Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxComplianceQuest1
 
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...Shane Coughlan
 
LEVEL 5 - SESSION 1 2023 (1).pptx - PDF 123456
LEVEL 5   - SESSION 1 2023 (1).pptx - PDF 123456LEVEL 5   - SESSION 1 2023 (1).pptx - PDF 123456
LEVEL 5 - SESSION 1 2023 (1).pptx - PDF 123456KiaraTiradoMicha
 
The Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdfThe Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdfkalichargn70th171
 
ManageIQ - Sprint 236 Review - Slide Deck
ManageIQ - Sprint 236 Review - Slide DeckManageIQ - Sprint 236 Review - Slide Deck
ManageIQ - Sprint 236 Review - Slide DeckManageIQ
 
%in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park %in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park masabamasaba
 
Exploring the Best Video Editing App.pdf
Exploring the Best Video Editing App.pdfExploring the Best Video Editing App.pdf
Exploring the Best Video Editing App.pdfproinshot.com
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsArshad QA
 
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisamasabamasaba
 
Unlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language ModelsUnlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language Modelsaagamshah0812
 
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdfLearn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdfkalichargn70th171
 
Chinsurah Escorts ☎️8617697112 Starting From 5K to 15K High Profile Escorts ...
Chinsurah Escorts ☎️8617697112  Starting From 5K to 15K High Profile Escorts ...Chinsurah Escorts ☎️8617697112  Starting From 5K to 15K High Profile Escorts ...
Chinsurah Escorts ☎️8617697112 Starting From 5K to 15K High Profile Escorts ...Nitya salvi
 
Introducing Microsoft’s new Enterprise Work Management (EWM) Solution
Introducing Microsoft’s new Enterprise Work Management (EWM) SolutionIntroducing Microsoft’s new Enterprise Work Management (EWM) Solution
Introducing Microsoft’s new Enterprise Work Management (EWM) SolutionOnePlan Solutions
 
8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech students8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech studentsHimanshiGarg82
 

Dernier (20)

VTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learnVTU technical seminar 8Th Sem on Scikit-learn
VTU technical seminar 8Th Sem on Scikit-learn
 
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdfAzure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
Azure_Native_Qumulo_High_Performance_Compute_Benchmarks.pdf
 
Direct Style Effect Systems - The Print[A] Example - A Comprehension Aid
Direct Style Effect Systems -The Print[A] Example- A Comprehension AidDirect Style Effect Systems -The Print[A] Example- A Comprehension Aid
Direct Style Effect Systems - The Print[A] Example - A Comprehension Aid
 
Sector 18, Noida Call girls :8448380779 Model Escorts | 100% verified
Sector 18, Noida Call girls :8448380779 Model Escorts | 100% verifiedSector 18, Noida Call girls :8448380779 Model Escorts | 100% verified
Sector 18, Noida Call girls :8448380779 Model Escorts | 100% verified
 
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
call girls in Vaishali (Ghaziabad) 🔝 >༒8448380779 🔝 genuine Escort Service 🔝✔️✔️
 
A Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docxA Secure and Reliable Document Management System is Essential.docx
A Secure and Reliable Document Management System is Essential.docx
 
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
OpenChain - The Ramifications of ISO/IEC 5230 and ISO/IEC 18974 for Legal Pro...
 
LEVEL 5 - SESSION 1 2023 (1).pptx - PDF 123456
LEVEL 5   - SESSION 1 2023 (1).pptx - PDF 123456LEVEL 5   - SESSION 1 2023 (1).pptx - PDF 123456
LEVEL 5 - SESSION 1 2023 (1).pptx - PDF 123456
 
The Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdfThe Ultimate Test Automation Guide_ Best Practices and Tips.pdf
The Ultimate Test Automation Guide_ Best Practices and Tips.pdf
 
ManageIQ - Sprint 236 Review - Slide Deck
ManageIQ - Sprint 236 Review - Slide DeckManageIQ - Sprint 236 Review - Slide Deck
ManageIQ - Sprint 236 Review - Slide Deck
 
%in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park %in ivory park+277-882-255-28 abortion pills for sale in ivory park
%in ivory park+277-882-255-28 abortion pills for sale in ivory park
 
Exploring the Best Video Editing App.pdf
Exploring the Best Video Editing App.pdfExploring the Best Video Editing App.pdf
Exploring the Best Video Editing App.pdf
 
Software Quality Assurance Interview Questions
Software Quality Assurance Interview QuestionsSoftware Quality Assurance Interview Questions
Software Quality Assurance Interview Questions
 
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa%in tembisa+277-882-255-28 abortion pills for sale in tembisa
%in tembisa+277-882-255-28 abortion pills for sale in tembisa
 
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICECHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
CHEAP Call Girls in Pushp Vihar (-DELHI )🔝 9953056974🔝(=)/CALL GIRLS SERVICE
 
Unlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language ModelsUnlocking the Future of AI Agents with Large Language Models
Unlocking the Future of AI Agents with Large Language Models
 
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdfLearn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
Learn the Fundamentals of XCUITest Framework_ A Beginner's Guide.pdf
 
Chinsurah Escorts ☎️8617697112 Starting From 5K to 15K High Profile Escorts ...
Chinsurah Escorts ☎️8617697112  Starting From 5K to 15K High Profile Escorts ...Chinsurah Escorts ☎️8617697112  Starting From 5K to 15K High Profile Escorts ...
Chinsurah Escorts ☎️8617697112 Starting From 5K to 15K High Profile Escorts ...
 
Introducing Microsoft’s new Enterprise Work Management (EWM) Solution
Introducing Microsoft’s new Enterprise Work Management (EWM) SolutionIntroducing Microsoft’s new Enterprise Work Management (EWM) Solution
Introducing Microsoft’s new Enterprise Work Management (EWM) Solution
 
8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech students8257 interfacing 2 in microprocessor for btech students
8257 interfacing 2 in microprocessor for btech students
 

Real-world Vision Systems Design: Challenges and Techniques

  • 1. Copyright © 2016 Itseez 1 Real-World Vision Systems Design Challenges and Techniques Yury Gorbachev May 3, 2016
  • 2. Copyright © 2016 Itseez 2 • Computer vision experts, 10 years on market • Maintainers of OpenCV library • Own products • ADAS algorithms suite • Facence (Face detection, recognition and analysis) • 3D Scanning (Itseez3D) • Accelerated CV (Optimized Computer Vision functions) • Consulting in CV area • Lot of Proof of Concept work per customer requests Itseez at Glance
  • 3. Copyright © 2016 Itseez 3 • Specific handling of requirements for vision projects • Underestimated role of data • Compute platform selection fallacies • Hardware assisted vision algorithms • Planning for customer feedback • Functionality for easier product maintenance Topics to Cover
  • 4. Copyright © 2016 Itseez 4 • Requirements for vision products require special handling • Not always possible to predict data variation upfront • Specific cases will appear during design or test • Missed scenarios • Lighting conditions, blur and glare effects, etc. • Impact can be pretty substantial • More scenarios to handle — increase in algorithm complexity • Additional data could be required Requirements for Vision Products
  • 5. Copyright © 2016 Itseez 5 • Initial requirement — detect speed limits in Europe • Standards describe signs pretty well (size, color, etc.) • Pretty easy to put into requirements • Some things are not so straightforward to predict though Example — Speed Limit Sign Detection
  • 6. Copyright © 2016 Itseez 6 • Computer vision heavily depends on data for training and test • Innovative products require specific data • Usually not available in public datasets • Data collection stage is needed prior to algorithm design • Collect videos/images, preferably with variation and target HW • Annotate collected data. At first stages done manually • This is not always well understood by non-vision related customers • Not always correctly planned within a project Good Dataset is a Major Part of Solution
  • 7. Copyright © 2016 Itseez 7 • Statistics from road sign dataset used at Itseez ADAS • Not considering different sign types, weather and lighting conditions • Annotation will take even more Example — Speed Limit Signs Dataset
  • 8. Copyright © 2016 Itseez 8 • Plenty of options for compute platform selection • GPU, DSP and SIMD-enabled SoCs • Frequently hardware selection is separated from software design • Could be even pre-selected already before project start • FACT: Not all compute platforms fit all algorithms • Separated selection usually results in suboptimal systems • Higher power consumption & unnecessary complicated algorithms Premature Compute Platform Selection
  • 9. Copyright © 2016 Itseez 9 • Vectorization is commonly seen as a solution for most of the problems • Some SoCs sport few vector units with low frequency and few cores • Obvious choice, perfect fit for vision! • Not really… Following algorithm will have almost no benefit from SIMD Example — Suboptimal Hardware Selection Keypoint search External sensor Detailed search (Cascade) ROIs Candidates Candidate analysis
  • 10. Copyright © 2016 Itseez 10 • Optics and sensors should be selected for a given task • Color vs. grayscale imagers, FOV vs. distance • Some tasks are significantly simpler when depth information is available • E.g., stairway detection for robotics • Vision algorithm can benefit from other sensor systems • IMU to consider motion and position (e.g., visual odometry) • LIDAR like cheap sensors in ADAS to limit search range • Consider cloud for heavy offline processing if no latency requirements Missed Opportunities for HW Assisted Vision
  • 11. Copyright © 2016 Itseez 11 • Algorithm working on RGBD is much easier comparing to RGB • Consider following inputs Example — Staircase Detection RGBD image courtesy of: Reza Farid. Region growing planar segmentation for robot action planning
  • 12. Copyright © 2016 Itseez 12 • Prototype algorithms prior to major work and HW selection • Understand bottlenecks and challenges  update requirements • Perform HW selection considering algorithm specifics • Plan for sync between HW and SW during development Possible Vision Product Design Model Algorithm PoC design Prototype results Hardware approach selection Hardware Arch. Software drop Algorithm development Hardware drop HW Design Final product Original reqs Updated reqs
  • 13. Copyright © 2016 Itseez 13 • Vision in products is still pretty new to consumers • Designers of the product create it with some use cases in mind • Consumers usually use them differently • This gap need attention prior to product release • Target group testing, people outside of CV area • Leave some time for corrective actions • Algorithm enhancements and changes • Documentation updates, tutorial videos, etc. Customer Acceptance Need Some Work
  • 14. Copyright © 2016 Itseez 14 • Itseez3D application • Freely available on iPad, needs sensor (Occipital) • Just walk around a person and scan to get 3D model • Consumer use cases needed attention • Tracking from sensor SDK did not support scan interruption • Own enhanced tracking was implemented • UI enhancements and video tutorials were done • Currently about 300 scans per day Example — Full Body Scanning
  • 15. Copyright © 2016 Itseez 15 • Most vision products require calibration • Re-calibration might be needed after some time • Surveillance cameras change position due to wind/shaking • Focus/visibility loss in optics due to harsh conditions • Product tampering • E.g., cover optics intentionally for some time periods • Always good to be able to detect those things in software • Blur & sharp edges detection, circular buffer recording Maintenance Issues in Vision Products
  • 16. Copyright © 2016 Itseez 16 One Video Tells More Than Few Slides • Two problems here • Optics needs maintenance (algorithm works though) • Low sales figures...
  • 17. Copyright © 2016 Itseez 17 • Do not consider requirements as final • Periodically update with findings, exceptions • For complicated algorithms perform PoC and iterate planning • Perform analysis of existing datasets  plan for dataset collection • Investigate/prototype algorithm prior to hardware selection if possible • Consider additional sensors as help to vision algorithms • Ask for customer feedback prior product release • Place frame source checks in software to detect maintenance issues Conclusion: Useful Hints
  • 18. Copyright © 2016 Itseez 18 Q&A
  • 19. Copyright © 2016 Itseez 19 • Itseez Web — http://www.itseez.com • Itseez3D Scanning app — http://www.itseez3d.com • Contact me: yury.gorbachev@itseez.com Resources and Contacts