SlideShare une entreprise Scribd logo
1  sur  61
Can We Make Maps from Videos?
~From AI Algorithm to Engineering for Continuous Improvement~
Kazuyuki Miyazawa Kosuke Kuzuoka
Agenda
Background
Computer Vision Technologies for Video-Based Map
Creation/Maintenance
Engineering for Continuous Improvement
1
2
3
Wrap Up4
Who am I?
Kazuyuki Miyazawa
Work Experience
• April 2019 - Present
AI Research Engineer @DeNA Co., Ltd.
• April 2010 - March 2019
Research Scientist @Mitsubishi Electric Corp.
Education
• PhD in Information Science @Tohoku Univ.
@kzykmyzw
Background
•Maps are an essential ingredient for every mobility service
•Higher & higher map quality is in demand to enable advanced services
(e.g., autonomous vehicle)
-1980s 1980s-20XXs 20XXs-
Problems for Current Map Creation/Maintenance
•Manual processes are labor-intensive and time-consuming
•Using a special measurement system (e.g., mobile mapping system) is costly and
difficult to scale to achieve high coverage for various types of mobility services
https://www.infradoctor.jp/details/detail20190313.pdf
https://www.google.com/streetview/explore/
What Can DeNA Do About It?
•Dashcams are becoming popular, and can capture a lot of useful information for maps
•Current AI shows an amazing performance for image/video analysis
•We are developing low-cost and rapid map creation (or maintenance) technology
using dashcam videos collected via cloud servers
2014 2015 2016 2017 2018
160
120
80
40
0
Dashcam sales volume (Japan)(million units)
GfKジャパン, “2018年ドライブレコーダーの販売動向,” 2019
https://www.gfk.com/fileadmin/user_upload/dyna_content/JP/20190328_drivinngrecorders.pdf
What Do We Need to Do?
MapImage
©️OpenStreetMap contributors
https://en.wikipedia.org/wiki/Geographic_coordinate_system
Want to place the newly
found object on the map
What Do We Need to Do?
Map
x
y
z
©️OpenStreetMap contributors
https://en.wikipedia.org/wiki/Geographic_coordinate_system
Need to know the 3D position
of the object!
Image
(x, y, z)
How Do We Know the 3D Position from a 2D
Image?
?
?
?
From a single 2D image, we cannot
decide the 3D position of the object
How Do We Know the 3D Position from 2D Images?
If we have two (or more) views, we can
decide the 3D object position as the
intersection of camera rays
Dashcam Video = Multi-View Images
time: t1
time: t2
time: t3
Dashcam video can be seen as a set of
multi-view images because the vehicle
moves while capturing
Dashcam Video = Multi-View Images
time: t1
time: t2
time: t3
Dashcam video can be seen as a set of
multi-view images because the vehicle
moves while capturing
Camera pose for each frame is
necessary to calculate the 3D
object position
Camera Pose Estimation from Video
•SfM*1 or Visual SLAM*2 is used as a core technology
•Estimate the camera poses by tracking salient points in the video
*1 Structure from Motion
*2 Simultaneous Localization And Mapping
Coordinate Conversion
Map
x
y
z
©️OpenStreetMap contributors
https://en.wikipedia.org/wiki/Geographic_coordinate_system
Convert the estimated object
position to the geospatial
coordinate system using the GNSS
signal received by dashcam
(x, y, z)
Image
(lat, lon, alt)
GNSS
Dataset Creation for Accuracy Evaluation
•Built our own dataset of dashcam videos and corresponding highly accurate 3D data
as ground truth for evaluation purposes
•Manually annotated various objects (e.g., traffic signs, lanes, etc.)
Videos from Dashcams 3D Point Clouds from LiDAR
Sample Results
Dashcam Video Estimated Position
Estimated camera positions
Estimated object position
Ground-truth object position
Error: 0.20m
Sample Results
Dashcam Video Estimated Position
Estimated camera positions
Estimated object position
Ground-truth object position
Error: 1.2m
Results Summary
0 0.5 1.0 1.5 2.0 2.5
Error [m]
Frequency
Average Error: 0.74m
Average error of object position estimation is below 1m!
Wait, How Do You Find Objects in Images?
MapImage
©️OpenStreetMap contributors
https://en.wikipedia.org/wiki/Geographic_coordinate_system
Want to place the newly
found object on the map
Of Course, Deep Learning!
R-FCN: Object Detection via Region-based Fully ConvolutionalNetworks
https://arxiv.org/pdf/1605.06409v2.pdf
OpenPose: RealtimeMulti-Person 2D Pose Estimation using Part AffinityFields
https://arxiv.org/pdf/1812.08008.pdf
Panoptic Segmentation
https://arxiv.org/pdf/1801.00868.pdf
Traffic Light/Sign Detection using CNN
• Use Faster R-CNN to detect traffic lights/signs in each frame of dashcam videos
• Faster R-CNN is one of the most successful object detection methods proposed in 2016
• Main drawback is speed, but acceptable for off-line applications
Classification
Regression
Traffic light
Stop
Speed limit
No right turn
Position
…
CNN
Region Proposals
https://youtu.be/7iZmOIN0wwI
Traffic Signal/Sign Detection Result
Q. Is It Easy to Achieve This?
Q. Is It Easy to Achieve This? A. NO!
Data
Preparation
Model
Training
Parameter
Tuning
Model
Verification
Deploy
Monitoring Data Analysis
Model
Development
Need to iterate again and again
Q. Is It Easy to Achieve This? A. NO!
Data
Preparation
Model
Training
Parameter
Tuning
Model
Verification
Deploy
Monitoring Data Analysis
Model
Development
Rapid iteration is the key
Who am I?
Profile
• Kosuke Kuzuoka (23)
• Love Tesla, Elon Musk and cats
Experience
• February 2020 - Present
Software Engineer, ML @Mercari, Inc.
• June 2018 – February 2020
AI Research Engineer @DeNA Co., Ltd.
• March 2017 – June 2018
R&D Manager @Photoruction, inc.
Brief Intro to Object Detection
• An active research area among
computer vision community
• Task is detecting objects
(like cats) in an image
• Modern algorithms heavily
rely on deep learning
• Takes hours to train a model
Photo by Paul Hanaoka on Unsplash
Photo by Paul Hanaoka on Unsplash
A cat is detected as a cat,
hence it’s a true positive.
Wrongly detected as cats,
hence they are false positives
Problems in Development Processes
1. Train, validate and test models (computationally expensive)
2. Evaluate, visualize and analyze models (time consuming)
3. Adjust hyper-param, then go back to 1
Problems in Development Processes
1. Train, validate and test models (computationally expensive)
2. Evaluate, visualize and analyze models (time consuming)
3. Adjust hyper-param, then go back to 1
Problems in Development Processes
1. Train, validate and test models (computationally expensive)
2. Evaluate, visualize and analyze models (time consuming)
3. Adjust hyper-param, then go back to 1
Problems in Development Processes
1. Train, validate and test models (computationally expensive)
2. Evaluate, visualize and analyze models (time consuming)
3. Adjust hyper-param, then go back to 1
Problems in Development Processes
1. Train, validate and test models (computationally expensive)
2. Evaluate, visualize and analyze models (time consuming)
3. Adjust hyper-param, then go back to 1
Not essential, yet
very important...
Some of Problems are:
• Error-prone process (misspelling commands, etc.)
• Going back and forth between EC2 instances…
• Inefficient process, like drawing boxes, uploading
to third party app for visualization etc.
• Researchers not being able to focus on essential
work (developing models etc.)
Solutions!
• Work harder and harder...
• Automating tasks via workflow engine
• Flexible internal tool to evaluate,
visualize and analyze models
Solutions!
• Work harder and harder...
• Automating tasks via workflow engine
• Flexible internal tool to evaluate,
visualize and analyze models But I’m busy
with AI dev...
What We Wanted...
• A system that automatically evaluates,
visualizes and analyzes models and datasets.
• A tool that lets researchers focus on
essential work (parameter tuning etc.)
• User-friendly web app
• Easy to develop
• Easy to collaborate
• Good performance
• AI engineer friendly
(Python… )
Yet, We Want It to Be:
Going Serverless!
• Easy to deploy and maintain
• Collaborations made easy
• Cost effective, yet performant
• You can use Python
Image source: https://serverless.com/
Serverless Computing
• No need to manage servers,
cloud providers do it for you!
• Consists of small deployable
unit of functions
• Scales as your app grows
• No idle fee, pay as you go
• No need to manage servers,
cloud providers do it for you!
• Consists of small deployable
unit of functions
• Scales as your app grows
• No idle fee, pay as you go
Serverless Computing
Image source: https://aws.amazon.com/
• No need to manage servers,
cloud providers do it for you!
• Consists of small deployable
unit of functions
• Scales as your app grows
• No idle fee, pay as you go
Serverless Computing
• No need to manage servers,
cloud providers do it for you!
• Consists of small deployable
unit of functions
• Scales as your app grows
• No idle fee, pay as you go
Serverless Computing
Serverless Computing
• No need to manage servers,
cloud providers do it for you!
• Consists of small deployable
unit of functions
• Scales as your app grows
• No idle fee, pay as you go
Introducing Kaiseki-Kun
Kaiseki-Kun Architecture
1. Prediction JSON from GPU instance
2. Evaluation begins, store results
3. Users can see results &
run evaluations
Kaiseki-Kun Architecture
1. Prediction JSON from GPU instance
2. Evaluation begins, store results
3. Users can see results &
run evaluations
1. Prediction JSON from GPU instance
2. Evaluation begins, store results
3. Users can see results &
run evaluations
Kaiseki-Kun Architecture
1. Prediction JSON from GPU instance
2. Evaluation begins, store results
3. Users can see results &
run evaluations
Kaiseki-Kun Architecture
Kaiseki-Kun Tech Stack
• Backend app made of
100% serverless
• Front app made of
React app
Kaiseki-Kun Tech Stack
• Backend app made of
100% serverless app
• Front app made of
React app
53
54
Hmm, there is a FN in Red Box.
What if we adjust the threshold?
55
Ta-da! Perhaps, the model wasn’t
confident enough?
Model is missing lots of small
objects. We need more data!
Evaluation with different config
is as easy as pushing a button
More Functionalities On Its Way...
• Model version control
• Dataset analysis and version control
• Automating training and testing
Summing It Up
• Speed is important. You don’t want to
spend too much time on an internal tool
• Collaboration should be easy. Every
engineer should be able to contribute
• With little effort, researchers can focus
on more essential work
Wrap Up
AI Technologies for Map Creation/Maintenance
• Dashcam videos contain a lot of useful information for maps
• Develop computer vision technology to estimate objects’ positions
• Experimental evaluation shows the estimation error is less than 1m
Engineering for Continuous Improvement
• Rapid development cycle is important
• Serverless architecture is a cost-effective choice to develop and maintain
support tools for continuous improvement of AI
Can We Make Maps from Videos? ~From AI Algorithm to Engineering for Continuous Improvement~【DeNA TechCon 2020 ライブ配信】

Contenu connexe

Tendances

Devops at Netflix (re:Invent)
Devops at Netflix (re:Invent)Devops at Netflix (re:Invent)
Devops at Netflix (re:Invent)Jeremy Edberg
 
Infrastructure as Code
Infrastructure as CodeInfrastructure as Code
Infrastructure as CodePrasant Kumar
 
Performance Monitoring with AOP and Amazon CloudWatch
Performance Monitoring with AOP and Amazon CloudWatchPerformance Monitoring with AOP and Amazon CloudWatch
Performance Monitoring with AOP and Amazon CloudWatchYan Cui
 
Cloud Foundry at Rakuten
Cloud Foundry at RakutenCloud Foundry at Rakuten
Cloud Foundry at RakutenPlatform CF
 
FaaS or not to FaaS. Visible and invisible benefits of the Serverless paradig...
FaaS or not to FaaS. Visible and invisible benefits of the Serverless paradig...FaaS or not to FaaS. Visible and invisible benefits of the Serverless paradig...
FaaS or not to FaaS. Visible and invisible benefits of the Serverless paradig...Vadym Kazulkin
 
OpenCV for Embedded: Lessons Learned
OpenCV for Embedded: Lessons LearnedOpenCV for Embedded: Lessons Learned
OpenCV for Embedded: Lessons LearnedYury Gorbachev
 
IaC? VSTS to the rescue! Abbreviations explained
IaC? VSTS to the rescue! Abbreviations explainedIaC? VSTS to the rescue! Abbreviations explained
IaC? VSTS to the rescue! Abbreviations explainedJeroen Niesen
 
Web jobs, Azure Functions and Serverless Computing
Web jobs, Azure Functions and Serverless ComputingWeb jobs, Azure Functions and Serverless Computing
Web jobs, Azure Functions and Serverless ComputingParis Polyzos
 
The Netflix API Platform for Server-Side Scripting
The Netflix API Platform for Server-Side ScriptingThe Netflix API Platform for Server-Side Scripting
The Netflix API Platform for Server-Side ScriptingKatharina Probst
 
Spring: Your Next Java Micro-Framework
Spring: Your Next Java Micro-FrameworkSpring: Your Next Java Micro-Framework
Spring: Your Next Java Micro-FrameworkVMware Tanzu
 
Building a Running App With react-native
Building a Running App With react-nativeBuilding a Running App With react-native
Building a Running App With react-nativeHein Rutjes
 
PyCon APAC 2016: Django, Flask 고민없이 개발하고 서비스하는 PaaS, IBM Bluemix
PyCon APAC 2016: Django, Flask 고민없이 개발하고 서비스하는 PaaS, IBM BluemixPyCon APAC 2016: Django, Flask 고민없이 개발하고 서비스하는 PaaS, IBM Bluemix
PyCon APAC 2016: Django, Flask 고민없이 개발하고 서비스하는 PaaS, IBM BluemixJin Gi Kong
 
Iterative Development with Swagger on the JDK
Iterative Development with Swagger on the JDKIterative Development with Swagger on the JDK
Iterative Development with Swagger on the JDKSwagger API
 
Infrastructure as Code @BuildStuff2013
Infrastructure as Code @BuildStuff2013Infrastructure as Code @BuildStuff2013
Infrastructure as Code @BuildStuff2013Mantas Klasavicius
 
Building Universal Servers (On-prem meets Azure PAAS)
Building Universal Servers (On-prem meets Azure PAAS)Building Universal Servers (On-prem meets Azure PAAS)
Building Universal Servers (On-prem meets Azure PAAS)adamcarmi
 
Infrastructure as Code
Infrastructure as CodeInfrastructure as Code
Infrastructure as CodeLeandro Rosa
 
Canada DevOps Summit 2020 Presentation Nov_03_2020
Canada DevOps Summit 2020 Presentation Nov_03_2020Canada DevOps Summit 2020 Presentation Nov_03_2020
Canada DevOps Summit 2020 Presentation Nov_03_2020Varun Manik
 

Tendances (20)

Devops at Netflix (re:Invent)
Devops at Netflix (re:Invent)Devops at Netflix (re:Invent)
Devops at Netflix (re:Invent)
 
Infrastructure as Code
Infrastructure as CodeInfrastructure as Code
Infrastructure as Code
 
Performance Monitoring with AOP and Amazon CloudWatch
Performance Monitoring with AOP and Amazon CloudWatchPerformance Monitoring with AOP and Amazon CloudWatch
Performance Monitoring with AOP and Amazon CloudWatch
 
Serverless Spring 오충현
Serverless Spring 오충현Serverless Spring 오충현
Serverless Spring 오충현
 
Evolving the Netflix API
Evolving the Netflix APIEvolving the Netflix API
Evolving the Netflix API
 
Cloud Foundry at Rakuten
Cloud Foundry at RakutenCloud Foundry at Rakuten
Cloud Foundry at Rakuten
 
FaaS or not to FaaS. Visible and invisible benefits of the Serverless paradig...
FaaS or not to FaaS. Visible and invisible benefits of the Serverless paradig...FaaS or not to FaaS. Visible and invisible benefits of the Serverless paradig...
FaaS or not to FaaS. Visible and invisible benefits of the Serverless paradig...
 
Swagger code motion talk
Swagger code motion talkSwagger code motion talk
Swagger code motion talk
 
OpenCV for Embedded: Lessons Learned
OpenCV for Embedded: Lessons LearnedOpenCV for Embedded: Lessons Learned
OpenCV for Embedded: Lessons Learned
 
IaC? VSTS to the rescue! Abbreviations explained
IaC? VSTS to the rescue! Abbreviations explainedIaC? VSTS to the rescue! Abbreviations explained
IaC? VSTS to the rescue! Abbreviations explained
 
Web jobs, Azure Functions and Serverless Computing
Web jobs, Azure Functions and Serverless ComputingWeb jobs, Azure Functions and Serverless Computing
Web jobs, Azure Functions and Serverless Computing
 
The Netflix API Platform for Server-Side Scripting
The Netflix API Platform for Server-Side ScriptingThe Netflix API Platform for Server-Side Scripting
The Netflix API Platform for Server-Side Scripting
 
Spring: Your Next Java Micro-Framework
Spring: Your Next Java Micro-FrameworkSpring: Your Next Java Micro-Framework
Spring: Your Next Java Micro-Framework
 
Building a Running App With react-native
Building a Running App With react-nativeBuilding a Running App With react-native
Building a Running App With react-native
 
PyCon APAC 2016: Django, Flask 고민없이 개발하고 서비스하는 PaaS, IBM Bluemix
PyCon APAC 2016: Django, Flask 고민없이 개발하고 서비스하는 PaaS, IBM BluemixPyCon APAC 2016: Django, Flask 고민없이 개발하고 서비스하는 PaaS, IBM Bluemix
PyCon APAC 2016: Django, Flask 고민없이 개발하고 서비스하는 PaaS, IBM Bluemix
 
Iterative Development with Swagger on the JDK
Iterative Development with Swagger on the JDKIterative Development with Swagger on the JDK
Iterative Development with Swagger on the JDK
 
Infrastructure as Code @BuildStuff2013
Infrastructure as Code @BuildStuff2013Infrastructure as Code @BuildStuff2013
Infrastructure as Code @BuildStuff2013
 
Building Universal Servers (On-prem meets Azure PAAS)
Building Universal Servers (On-prem meets Azure PAAS)Building Universal Servers (On-prem meets Azure PAAS)
Building Universal Servers (On-prem meets Azure PAAS)
 
Infrastructure as Code
Infrastructure as CodeInfrastructure as Code
Infrastructure as Code
 
Canada DevOps Summit 2020 Presentation Nov_03_2020
Canada DevOps Summit 2020 Presentation Nov_03_2020Canada DevOps Summit 2020 Presentation Nov_03_2020
Canada DevOps Summit 2020 Presentation Nov_03_2020
 

Similaire à Can We Make Maps from Videos? ~From AI Algorithm to Engineering for Continuous Improvement~【DeNA TechCon 2020 ライブ配信】

Build and Host Real-world Machine Learning Services from Scratch @ pycontw2019
Build and Host Real-world Machine Learning Services from Scratch @ pycontw2019 Build and Host Real-world Machine Learning Services from Scratch @ pycontw2019
Build and Host Real-world Machine Learning Services from Scratch @ pycontw2019 Chun-Yu Tseng
 
課題ドリブン、フルスタックAI開発術 [MOBILITY:dev]
課題ドリブン、フルスタックAI開発術 [MOBILITY:dev]課題ドリブン、フルスタックAI開発術 [MOBILITY:dev]
課題ドリブン、フルスタックAI開発術 [MOBILITY:dev]DeNA
 
82_PHOTOLAB-----Project PPT.pdfhejeenejsn
82_PHOTOLAB-----Project PPT.pdfhejeenejsn82_PHOTOLAB-----Project PPT.pdfhejeenejsn
82_PHOTOLAB-----Project PPT.pdfhejeenejsnshivam003d
 
lokesh_UX_Designer_v5
lokesh_UX_Designer_v5lokesh_UX_Designer_v5
lokesh_UX_Designer_v5Lokesh S
 
Real Time Moving Object Detection for Day-Night Surveillance using AI
Real Time Moving Object Detection for Day-Night Surveillance using AIReal Time Moving Object Detection for Day-Night Surveillance using AI
Real Time Moving Object Detection for Day-Night Surveillance using AIIRJET Journal
 
Marwa_Ezzatt_Ahmed_CV
Marwa_Ezzatt_Ahmed_CVMarwa_Ezzatt_Ahmed_CV
Marwa_Ezzatt_Ahmed_CVMarwa Ezzat
 
Cutting Edge Computer Vision for Everyone
Cutting Edge Computer Vision for EveryoneCutting Edge Computer Vision for Everyone
Cutting Edge Computer Vision for EveryoneIvo Andreev
 
Collin Stocks 2016-09-06
Collin Stocks 2016-09-06Collin Stocks 2016-09-06
Collin Stocks 2016-09-06Collin Stocks
 
Evolving Infrastructure
Evolving InfrastructureEvolving Infrastructure
Evolving Infrastructurelouisadunne
 
MODEL-DRIVEN ENGINEERING (MDE) in Practice
MODEL-DRIVEN ENGINEERING (MDE) in PracticeMODEL-DRIVEN ENGINEERING (MDE) in Practice
MODEL-DRIVEN ENGINEERING (MDE) in PracticeHussein Alshkhir
 
What Is Your PLM Challenge - Decrease downtime and minimize production problems
What Is Your PLM Challenge - Decrease downtime and minimize production problemsWhat Is Your PLM Challenge - Decrease downtime and minimize production problems
What Is Your PLM Challenge - Decrease downtime and minimize production problemsDawn Collins
 
Evolving Services Into A Cloud Native World
Evolving Services Into A Cloud Native WorldEvolving Services Into A Cloud Native World
Evolving Services Into A Cloud Native WorldIain Hull
 
_Python Ireland Meetup - Serverless ML - Dowling.pdf
_Python Ireland Meetup - Serverless ML - Dowling.pdf_Python Ireland Meetup - Serverless ML - Dowling.pdf
_Python Ireland Meetup - Serverless ML - Dowling.pdfJim Dowling
 
Application assessment for cloud affinity definition
Application assessment for cloud affinity definitionApplication assessment for cloud affinity definition
Application assessment for cloud affinity definitionDavide Veronese
 
Application Architecture Summit - Monitoring the Dynamic Cloud
Application Architecture Summit - Monitoring the Dynamic Cloud Application Architecture Summit - Monitoring the Dynamic Cloud
Application Architecture Summit - Monitoring the Dynamic Cloud New Relic
 

Similaire à Can We Make Maps from Videos? ~From AI Algorithm to Engineering for Continuous Improvement~【DeNA TechCon 2020 ライブ配信】 (20)

Build and Host Real-world Machine Learning Services from Scratch @ pycontw2019
Build and Host Real-world Machine Learning Services from Scratch @ pycontw2019 Build and Host Real-world Machine Learning Services from Scratch @ pycontw2019
Build and Host Real-world Machine Learning Services from Scratch @ pycontw2019
 
課題ドリブン、フルスタックAI開発術 [MOBILITY:dev]
課題ドリブン、フルスタックAI開発術 [MOBILITY:dev]課題ドリブン、フルスタックAI開発術 [MOBILITY:dev]
課題ドリブン、フルスタックAI開発術 [MOBILITY:dev]
 
82_PHOTOLAB-----Project PPT.pdfhejeenejsn
82_PHOTOLAB-----Project PPT.pdfhejeenejsn82_PHOTOLAB-----Project PPT.pdfhejeenejsn
82_PHOTOLAB-----Project PPT.pdfhejeenejsn
 
Google App engine
Google App engineGoogle App engine
Google App engine
 
lokesh_UX_Designer_v5
lokesh_UX_Designer_v5lokesh_UX_Designer_v5
lokesh_UX_Designer_v5
 
Real Time Moving Object Detection for Day-Night Surveillance using AI
Real Time Moving Object Detection for Day-Night Surveillance using AIReal Time Moving Object Detection for Day-Night Surveillance using AI
Real Time Moving Object Detection for Day-Night Surveillance using AI
 
Marwa_Ezzatt_Ahmed_CV
Marwa_Ezzatt_Ahmed_CVMarwa_Ezzatt_Ahmed_CV
Marwa_Ezzatt_Ahmed_CV
 
Cutting Edge Computer Vision for Everyone
Cutting Edge Computer Vision for EveryoneCutting Edge Computer Vision for Everyone
Cutting Edge Computer Vision for Everyone
 
Collin Stocks 2016-09-06
Collin Stocks 2016-09-06Collin Stocks 2016-09-06
Collin Stocks 2016-09-06
 
Evolving Infrastructure
Evolving InfrastructureEvolving Infrastructure
Evolving Infrastructure
 
MODEL-DRIVEN ENGINEERING (MDE) in Practice
MODEL-DRIVEN ENGINEERING (MDE) in PracticeMODEL-DRIVEN ENGINEERING (MDE) in Practice
MODEL-DRIVEN ENGINEERING (MDE) in Practice
 
What Is Your PLM Challenge - Decrease downtime and minimize production problems
What Is Your PLM Challenge - Decrease downtime and minimize production problemsWhat Is Your PLM Challenge - Decrease downtime and minimize production problems
What Is Your PLM Challenge - Decrease downtime and minimize production problems
 
Evolving Services Into A Cloud Native World
Evolving Services Into A Cloud Native WorldEvolving Services Into A Cloud Native World
Evolving Services Into A Cloud Native World
 
_Python Ireland Meetup - Serverless ML - Dowling.pdf
_Python Ireland Meetup - Serverless ML - Dowling.pdf_Python Ireland Meetup - Serverless ML - Dowling.pdf
_Python Ireland Meetup - Serverless ML - Dowling.pdf
 
OOSE UNIT-1.pdf
OOSE UNIT-1.pdfOOSE UNIT-1.pdf
OOSE UNIT-1.pdf
 
Arc solutions powerpoint
Arc solutions powerpointArc solutions powerpoint
Arc solutions powerpoint
 
Super charged prototyping
Super charged prototypingSuper charged prototyping
Super charged prototyping
 
Application assessment for cloud affinity definition
Application assessment for cloud affinity definitionApplication assessment for cloud affinity definition
Application assessment for cloud affinity definition
 
Application Architecture Summit - Monitoring the Dynamic Cloud
Application Architecture Summit - Monitoring the Dynamic Cloud Application Architecture Summit - Monitoring the Dynamic Cloud
Application Architecture Summit - Monitoring the Dynamic Cloud
 
slide-171212080528.pptx
slide-171212080528.pptxslide-171212080528.pptx
slide-171212080528.pptx
 

Plus de DeNA

DRIVE CHARTの裏側 〜 AI ☓ IoT ☓ ビッグデータを 支えるアーキテクチャ 〜
DRIVE CHARTの裏側  〜 AI ☓ IoT ☓ ビッグデータを 支えるアーキテクチャ 〜DRIVE CHARTの裏側  〜 AI ☓ IoT ☓ ビッグデータを 支えるアーキテクチャ 〜
DRIVE CHARTの裏側 〜 AI ☓ IoT ☓ ビッグデータを 支えるアーキテクチャ 〜DeNA
 
IoTと業務システムをつなぐgRPC/RESTサービスの開発と運用
IoTと業務システムをつなぐgRPC/RESTサービスの開発と運用IoTと業務システムをつなぐgRPC/RESTサービスの開発と運用
IoTと業務システムをつなぐgRPC/RESTサービスの開発と運用DeNA
 
SHOWROOMとDeNAで取り組んだライブ配信基盤刷新・超低遅延ライブ配信の裏側【DeNA TechCon 2020 ライブ配信】
SHOWROOMとDeNAで取り組んだライブ配信基盤刷新・超低遅延ライブ配信の裏側【DeNA TechCon 2020 ライブ配信】SHOWROOMとDeNAで取り組んだライブ配信基盤刷新・超低遅延ライブ配信の裏側【DeNA TechCon 2020 ライブ配信】
SHOWROOMとDeNAで取り組んだライブ配信基盤刷新・超低遅延ライブ配信の裏側【DeNA TechCon 2020 ライブ配信】DeNA
 
クラウド環境でのセキュリティ監査自動化【DeNA TechCon 2020 ライブ配信】
クラウド環境でのセキュリティ監査自動化【DeNA TechCon 2020 ライブ配信】クラウド環境でのセキュリティ監査自動化【DeNA TechCon 2020 ライブ配信】
クラウド環境でのセキュリティ監査自動化【DeNA TechCon 2020 ライブ配信】DeNA
 
DeClang 誕生!Clang ベースのハッキング対策コンパイラ【DeNA TechCon 2020 ライブ配信】
DeClang 誕生!Clang ベースのハッキング対策コンパイラ【DeNA TechCon 2020 ライブ配信】DeClang 誕生!Clang ベースのハッキング対策コンパイラ【DeNA TechCon 2020 ライブ配信】
DeClang 誕生!Clang ベースのハッキング対策コンパイラ【DeNA TechCon 2020 ライブ配信】DeNA
 
仕様起因の手戻りを減らして開発効率アップを目指すチャレンジ 【DeNA TechCon 2020 ライブ配信】
仕様起因の手戻りを減らして開発効率アップを目指すチャレンジ 【DeNA TechCon 2020 ライブ配信】仕様起因の手戻りを減らして開発効率アップを目指すチャレンジ 【DeNA TechCon 2020 ライブ配信】
仕様起因の手戻りを減らして開発効率アップを目指すチャレンジ 【DeNA TechCon 2020 ライブ配信】DeNA
 
DeNA データプラットフォームにおける 自由と統制のバランス【DeNA TechCon 2020 ライブ配信】
DeNA データプラットフォームにおける 自由と統制のバランス【DeNA TechCon 2020 ライブ配信】DeNA データプラットフォームにおける 自由と統制のバランス【DeNA TechCon 2020 ライブ配信】
DeNA データプラットフォームにおける 自由と統制のバランス【DeNA TechCon 2020 ライブ配信】DeNA
 
リアルタイムリモートデバッグ環境によるゲーム開発イテレーションの高速化【DeNA TechCon 2020 ライブ配信】
リアルタイムリモートデバッグ環境によるゲーム開発イテレーションの高速化【DeNA TechCon 2020 ライブ配信】リアルタイムリモートデバッグ環境によるゲーム開発イテレーションの高速化【DeNA TechCon 2020 ライブ配信】
リアルタイムリモートデバッグ環境によるゲーム開発イテレーションの高速化【DeNA TechCon 2020 ライブ配信】DeNA
 
MOV の機械学習システムを支える MLOps 実践【DeNA TechCon 2020 ライブ配信】
MOV の機械学習システムを支える MLOps 実践【DeNA TechCon 2020 ライブ配信】MOV の機械学習システムを支える MLOps 実践【DeNA TechCon 2020 ライブ配信】
MOV の機械学習システムを支える MLOps 実践【DeNA TechCon 2020 ライブ配信】DeNA
 
コンピュータビジョン技術の実応用〜DRIVE CHARTにおける脇見・車間距離不足検知〜【DeNA TechCon 2020 ライブ配信】
コンピュータビジョン技術の実応用〜DRIVE CHARTにおける脇見・車間距離不足検知〜【DeNA TechCon 2020 ライブ配信】コンピュータビジョン技術の実応用〜DRIVE CHARTにおける脇見・車間距離不足検知〜【DeNA TechCon 2020 ライブ配信】
コンピュータビジョン技術の実応用〜DRIVE CHARTにおける脇見・車間距離不足検知〜【DeNA TechCon 2020 ライブ配信】DeNA
 
DeNA の Slack 導入と活用の事例紹介
DeNA の Slack 導入と活用の事例紹介DeNA の Slack 導入と活用の事例紹介
DeNA の Slack 導入と活用の事例紹介DeNA
 
タクシーxAIを支えるKubernetesとAIデータパイプラインの信頼性の取り組みについて [SRE NEXT 2020]
タクシーxAIを支えるKubernetesとAIデータパイプラインの信頼性の取り組みについて [SRE NEXT 2020]タクシーxAIを支えるKubernetesとAIデータパイプラインの信頼性の取り組みについて [SRE NEXT 2020]
タクシーxAIを支えるKubernetesとAIデータパイプラインの信頼性の取り組みについて [SRE NEXT 2020]DeNA
 
オートモーティブ領域における 位置情報関連アルゴリズムあれこれ
オートモーティブ領域における 位置情報関連アルゴリズムあれこれオートモーティブ領域における 位置情報関連アルゴリズムあれこれ
オートモーティブ領域における 位置情報関連アルゴリズムあれこれDeNA
 
後部座席タブレットにおけるMaaS時代を見据えた半歩先のUX設計」 [MOBILITY:dev]
後部座席タブレットにおけるMaaS時代を見据えた半歩先のUX設計」 [MOBILITY:dev]後部座席タブレットにおけるMaaS時代を見据えた半歩先のUX設計」 [MOBILITY:dev]
後部座席タブレットにおけるMaaS時代を見据えた半歩先のUX設計」 [MOBILITY:dev]DeNA
 
ドライブレコーダ映像からの3次元空間認識 [MOBILITY:dev]
ドライブレコーダ映像からの3次元空間認識 [MOBILITY:dev]ドライブレコーダ映像からの3次元空間認識 [MOBILITY:dev]
ドライブレコーダ映像からの3次元空間認識 [MOBILITY:dev]DeNA
 
MOVで実践したサーバーAPI実装の超最適化について [MOBILITY:dev]
MOVで実践したサーバーAPI実装の超最適化について [MOBILITY:dev]MOVで実践したサーバーAPI実装の超最適化について [MOBILITY:dev]
MOVで実践したサーバーAPI実装の超最適化について [MOBILITY:dev]DeNA
 
MOV お客さま探索ナビの GCP ML開発フローについて
MOV お客さま探索ナビの GCP ML開発フローについてMOV お客さま探索ナビの GCP ML開発フローについて
MOV お客さま探索ナビの GCP ML開発フローについてDeNA
 
DeNA の AWS アカウント管理とセキュリティ監査自動化
DeNA の AWS アカウント管理とセキュリティ監査自動化DeNA の AWS アカウント管理とセキュリティ監査自動化
DeNA の AWS アカウント管理とセキュリティ監査自動化DeNA
 
DeNAのQCTマネジメント IaaS利用のベストプラクティス [AWS Summit Tokyo 2019]
DeNAのQCTマネジメント IaaS利用のベストプラクティス [AWS Summit Tokyo 2019]DeNAのQCTマネジメント IaaS利用のベストプラクティス [AWS Summit Tokyo 2019]
DeNAのQCTマネジメント IaaS利用のベストプラクティス [AWS Summit Tokyo 2019]DeNA
 
知っててもいいかもしれない知財のこと(抜粋版)
知っててもいいかもしれない知財のこと(抜粋版)知っててもいいかもしれない知財のこと(抜粋版)
知っててもいいかもしれない知財のこと(抜粋版)DeNA
 

Plus de DeNA (20)

DRIVE CHARTの裏側 〜 AI ☓ IoT ☓ ビッグデータを 支えるアーキテクチャ 〜
DRIVE CHARTの裏側  〜 AI ☓ IoT ☓ ビッグデータを 支えるアーキテクチャ 〜DRIVE CHARTの裏側  〜 AI ☓ IoT ☓ ビッグデータを 支えるアーキテクチャ 〜
DRIVE CHARTの裏側 〜 AI ☓ IoT ☓ ビッグデータを 支えるアーキテクチャ 〜
 
IoTと業務システムをつなぐgRPC/RESTサービスの開発と運用
IoTと業務システムをつなぐgRPC/RESTサービスの開発と運用IoTと業務システムをつなぐgRPC/RESTサービスの開発と運用
IoTと業務システムをつなぐgRPC/RESTサービスの開発と運用
 
SHOWROOMとDeNAで取り組んだライブ配信基盤刷新・超低遅延ライブ配信の裏側【DeNA TechCon 2020 ライブ配信】
SHOWROOMとDeNAで取り組んだライブ配信基盤刷新・超低遅延ライブ配信の裏側【DeNA TechCon 2020 ライブ配信】SHOWROOMとDeNAで取り組んだライブ配信基盤刷新・超低遅延ライブ配信の裏側【DeNA TechCon 2020 ライブ配信】
SHOWROOMとDeNAで取り組んだライブ配信基盤刷新・超低遅延ライブ配信の裏側【DeNA TechCon 2020 ライブ配信】
 
クラウド環境でのセキュリティ監査自動化【DeNA TechCon 2020 ライブ配信】
クラウド環境でのセキュリティ監査自動化【DeNA TechCon 2020 ライブ配信】クラウド環境でのセキュリティ監査自動化【DeNA TechCon 2020 ライブ配信】
クラウド環境でのセキュリティ監査自動化【DeNA TechCon 2020 ライブ配信】
 
DeClang 誕生!Clang ベースのハッキング対策コンパイラ【DeNA TechCon 2020 ライブ配信】
DeClang 誕生!Clang ベースのハッキング対策コンパイラ【DeNA TechCon 2020 ライブ配信】DeClang 誕生!Clang ベースのハッキング対策コンパイラ【DeNA TechCon 2020 ライブ配信】
DeClang 誕生!Clang ベースのハッキング対策コンパイラ【DeNA TechCon 2020 ライブ配信】
 
仕様起因の手戻りを減らして開発効率アップを目指すチャレンジ 【DeNA TechCon 2020 ライブ配信】
仕様起因の手戻りを減らして開発効率アップを目指すチャレンジ 【DeNA TechCon 2020 ライブ配信】仕様起因の手戻りを減らして開発効率アップを目指すチャレンジ 【DeNA TechCon 2020 ライブ配信】
仕様起因の手戻りを減らして開発効率アップを目指すチャレンジ 【DeNA TechCon 2020 ライブ配信】
 
DeNA データプラットフォームにおける 自由と統制のバランス【DeNA TechCon 2020 ライブ配信】
DeNA データプラットフォームにおける 自由と統制のバランス【DeNA TechCon 2020 ライブ配信】DeNA データプラットフォームにおける 自由と統制のバランス【DeNA TechCon 2020 ライブ配信】
DeNA データプラットフォームにおける 自由と統制のバランス【DeNA TechCon 2020 ライブ配信】
 
リアルタイムリモートデバッグ環境によるゲーム開発イテレーションの高速化【DeNA TechCon 2020 ライブ配信】
リアルタイムリモートデバッグ環境によるゲーム開発イテレーションの高速化【DeNA TechCon 2020 ライブ配信】リアルタイムリモートデバッグ環境によるゲーム開発イテレーションの高速化【DeNA TechCon 2020 ライブ配信】
リアルタイムリモートデバッグ環境によるゲーム開発イテレーションの高速化【DeNA TechCon 2020 ライブ配信】
 
MOV の機械学習システムを支える MLOps 実践【DeNA TechCon 2020 ライブ配信】
MOV の機械学習システムを支える MLOps 実践【DeNA TechCon 2020 ライブ配信】MOV の機械学習システムを支える MLOps 実践【DeNA TechCon 2020 ライブ配信】
MOV の機械学習システムを支える MLOps 実践【DeNA TechCon 2020 ライブ配信】
 
コンピュータビジョン技術の実応用〜DRIVE CHARTにおける脇見・車間距離不足検知〜【DeNA TechCon 2020 ライブ配信】
コンピュータビジョン技術の実応用〜DRIVE CHARTにおける脇見・車間距離不足検知〜【DeNA TechCon 2020 ライブ配信】コンピュータビジョン技術の実応用〜DRIVE CHARTにおける脇見・車間距離不足検知〜【DeNA TechCon 2020 ライブ配信】
コンピュータビジョン技術の実応用〜DRIVE CHARTにおける脇見・車間距離不足検知〜【DeNA TechCon 2020 ライブ配信】
 
DeNA の Slack 導入と活用の事例紹介
DeNA の Slack 導入と活用の事例紹介DeNA の Slack 導入と活用の事例紹介
DeNA の Slack 導入と活用の事例紹介
 
タクシーxAIを支えるKubernetesとAIデータパイプラインの信頼性の取り組みについて [SRE NEXT 2020]
タクシーxAIを支えるKubernetesとAIデータパイプラインの信頼性の取り組みについて [SRE NEXT 2020]タクシーxAIを支えるKubernetesとAIデータパイプラインの信頼性の取り組みについて [SRE NEXT 2020]
タクシーxAIを支えるKubernetesとAIデータパイプラインの信頼性の取り組みについて [SRE NEXT 2020]
 
オートモーティブ領域における 位置情報関連アルゴリズムあれこれ
オートモーティブ領域における 位置情報関連アルゴリズムあれこれオートモーティブ領域における 位置情報関連アルゴリズムあれこれ
オートモーティブ領域における 位置情報関連アルゴリズムあれこれ
 
後部座席タブレットにおけるMaaS時代を見据えた半歩先のUX設計」 [MOBILITY:dev]
後部座席タブレットにおけるMaaS時代を見据えた半歩先のUX設計」 [MOBILITY:dev]後部座席タブレットにおけるMaaS時代を見据えた半歩先のUX設計」 [MOBILITY:dev]
後部座席タブレットにおけるMaaS時代を見据えた半歩先のUX設計」 [MOBILITY:dev]
 
ドライブレコーダ映像からの3次元空間認識 [MOBILITY:dev]
ドライブレコーダ映像からの3次元空間認識 [MOBILITY:dev]ドライブレコーダ映像からの3次元空間認識 [MOBILITY:dev]
ドライブレコーダ映像からの3次元空間認識 [MOBILITY:dev]
 
MOVで実践したサーバーAPI実装の超最適化について [MOBILITY:dev]
MOVで実践したサーバーAPI実装の超最適化について [MOBILITY:dev]MOVで実践したサーバーAPI実装の超最適化について [MOBILITY:dev]
MOVで実践したサーバーAPI実装の超最適化について [MOBILITY:dev]
 
MOV お客さま探索ナビの GCP ML開発フローについて
MOV お客さま探索ナビの GCP ML開発フローについてMOV お客さま探索ナビの GCP ML開発フローについて
MOV お客さま探索ナビの GCP ML開発フローについて
 
DeNA の AWS アカウント管理とセキュリティ監査自動化
DeNA の AWS アカウント管理とセキュリティ監査自動化DeNA の AWS アカウント管理とセキュリティ監査自動化
DeNA の AWS アカウント管理とセキュリティ監査自動化
 
DeNAのQCTマネジメント IaaS利用のベストプラクティス [AWS Summit Tokyo 2019]
DeNAのQCTマネジメント IaaS利用のベストプラクティス [AWS Summit Tokyo 2019]DeNAのQCTマネジメント IaaS利用のベストプラクティス [AWS Summit Tokyo 2019]
DeNAのQCTマネジメント IaaS利用のベストプラクティス [AWS Summit Tokyo 2019]
 
知っててもいいかもしれない知財のこと(抜粋版)
知っててもいいかもしれない知財のこと(抜粋版)知っててもいいかもしれない知財のこと(抜粋版)
知っててもいいかもしれない知財のこと(抜粋版)
 

Dernier

Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)wesley chun
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUK Journal
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Drew Madelung
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfsudhanshuwaghmare1
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsMaria Levchenko
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Scriptwesley chun
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘RTylerCroy
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationRadu Cotescu
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonAnna Loughnan Colquhoun
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...apidays
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processorsdebabhi2
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Igalia
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?Antenna Manufacturer Coco
 

Dernier (20)

Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)Powerful Google developer tools for immediate impact! (2023-24 C)
Powerful Google developer tools for immediate impact! (2023-24 C)
 
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdfUnderstanding Discord NSFW Servers A Guide for Responsible Users.pdf
Understanding Discord NSFW Servers A Guide for Responsible Users.pdf
 
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
Strategies for Unlocking Knowledge Management in Microsoft 365 in the Copilot...
 
Boost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdfBoost Fertility New Invention Ups Success Rates.pdf
Boost Fertility New Invention Ups Success Rates.pdf
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
Handwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed textsHandwritten Text Recognition for manuscripts and early printed texts
Handwritten Text Recognition for manuscripts and early printed texts
 
Automating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps ScriptAutomating Google Workspace (GWS) & more with Apps Script
Automating Google Workspace (GWS) & more with Apps Script
 
🐬 The future of MySQL is Postgres 🐘
🐬  The future of MySQL is Postgres   🐘🐬  The future of MySQL is Postgres   🐘
🐬 The future of MySQL is Postgres 🐘
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Scaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organizationScaling API-first – The story of a global engineering organization
Scaling API-first – The story of a global engineering organization
 
Data Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt RobisonData Cloud, More than a CDP by Matt Robison
Data Cloud, More than a CDP by Matt Robison
 
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
Apidays Singapore 2024 - Building Digital Trust in a Digital Economy by Veron...
 
Exploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone ProcessorsExploring the Future Potential of AI-Enabled Smartphone Processors
Exploring the Future Potential of AI-Enabled Smartphone Processors
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
Raspberry Pi 5: Challenges and Solutions in Bringing up an OpenGL/Vulkan Driv...
 
What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?What Are The Drone Anti-jamming Systems Technology?
What Are The Drone Anti-jamming Systems Technology?
 

Can We Make Maps from Videos? ~From AI Algorithm to Engineering for Continuous Improvement~【DeNA TechCon 2020 ライブ配信】

  • 1. Can We Make Maps from Videos? ~From AI Algorithm to Engineering for Continuous Improvement~ Kazuyuki Miyazawa Kosuke Kuzuoka
  • 2. Agenda Background Computer Vision Technologies for Video-Based Map Creation/Maintenance Engineering for Continuous Improvement 1 2 3 Wrap Up4
  • 3. Who am I? Kazuyuki Miyazawa Work Experience • April 2019 - Present AI Research Engineer @DeNA Co., Ltd. • April 2010 - March 2019 Research Scientist @Mitsubishi Electric Corp. Education • PhD in Information Science @Tohoku Univ. @kzykmyzw
  • 4. Background •Maps are an essential ingredient for every mobility service •Higher & higher map quality is in demand to enable advanced services (e.g., autonomous vehicle) -1980s 1980s-20XXs 20XXs-
  • 5. Problems for Current Map Creation/Maintenance •Manual processes are labor-intensive and time-consuming •Using a special measurement system (e.g., mobile mapping system) is costly and difficult to scale to achieve high coverage for various types of mobility services https://www.infradoctor.jp/details/detail20190313.pdf https://www.google.com/streetview/explore/
  • 6. What Can DeNA Do About It? •Dashcams are becoming popular, and can capture a lot of useful information for maps •Current AI shows an amazing performance for image/video analysis •We are developing low-cost and rapid map creation (or maintenance) technology using dashcam videos collected via cloud servers 2014 2015 2016 2017 2018 160 120 80 40 0 Dashcam sales volume (Japan)(million units) GfKジャパン, “2018年ドライブレコーダーの販売動向,” 2019 https://www.gfk.com/fileadmin/user_upload/dyna_content/JP/20190328_drivinngrecorders.pdf
  • 7. What Do We Need to Do? MapImage ©️OpenStreetMap contributors https://en.wikipedia.org/wiki/Geographic_coordinate_system Want to place the newly found object on the map
  • 8. What Do We Need to Do? Map x y z ©️OpenStreetMap contributors https://en.wikipedia.org/wiki/Geographic_coordinate_system Need to know the 3D position of the object! Image (x, y, z)
  • 9. How Do We Know the 3D Position from a 2D Image? ? ? ? From a single 2D image, we cannot decide the 3D position of the object
  • 10. How Do We Know the 3D Position from 2D Images? If we have two (or more) views, we can decide the 3D object position as the intersection of camera rays
  • 11. Dashcam Video = Multi-View Images time: t1 time: t2 time: t3 Dashcam video can be seen as a set of multi-view images because the vehicle moves while capturing
  • 12. Dashcam Video = Multi-View Images time: t1 time: t2 time: t3 Dashcam video can be seen as a set of multi-view images because the vehicle moves while capturing Camera pose for each frame is necessary to calculate the 3D object position
  • 13. Camera Pose Estimation from Video •SfM*1 or Visual SLAM*2 is used as a core technology •Estimate the camera poses by tracking salient points in the video *1 Structure from Motion *2 Simultaneous Localization And Mapping
  • 14. Coordinate Conversion Map x y z ©️OpenStreetMap contributors https://en.wikipedia.org/wiki/Geographic_coordinate_system Convert the estimated object position to the geospatial coordinate system using the GNSS signal received by dashcam (x, y, z) Image (lat, lon, alt) GNSS
  • 15. Dataset Creation for Accuracy Evaluation •Built our own dataset of dashcam videos and corresponding highly accurate 3D data as ground truth for evaluation purposes •Manually annotated various objects (e.g., traffic signs, lanes, etc.) Videos from Dashcams 3D Point Clouds from LiDAR
  • 16. Sample Results Dashcam Video Estimated Position Estimated camera positions Estimated object position Ground-truth object position Error: 0.20m
  • 17. Sample Results Dashcam Video Estimated Position Estimated camera positions Estimated object position Ground-truth object position Error: 1.2m
  • 18. Results Summary 0 0.5 1.0 1.5 2.0 2.5 Error [m] Frequency Average Error: 0.74m Average error of object position estimation is below 1m!
  • 19. Wait, How Do You Find Objects in Images? MapImage ©️OpenStreetMap contributors https://en.wikipedia.org/wiki/Geographic_coordinate_system Want to place the newly found object on the map
  • 20. Of Course, Deep Learning! R-FCN: Object Detection via Region-based Fully ConvolutionalNetworks https://arxiv.org/pdf/1605.06409v2.pdf OpenPose: RealtimeMulti-Person 2D Pose Estimation using Part AffinityFields https://arxiv.org/pdf/1812.08008.pdf Panoptic Segmentation https://arxiv.org/pdf/1801.00868.pdf
  • 21. Traffic Light/Sign Detection using CNN • Use Faster R-CNN to detect traffic lights/signs in each frame of dashcam videos • Faster R-CNN is one of the most successful object detection methods proposed in 2016 • Main drawback is speed, but acceptable for off-line applications Classification Regression Traffic light Stop Speed limit No right turn Position … CNN Region Proposals
  • 23. Q. Is It Easy to Achieve This?
  • 24. Q. Is It Easy to Achieve This? A. NO! Data Preparation Model Training Parameter Tuning Model Verification Deploy Monitoring Data Analysis Model Development Need to iterate again and again
  • 25. Q. Is It Easy to Achieve This? A. NO! Data Preparation Model Training Parameter Tuning Model Verification Deploy Monitoring Data Analysis Model Development Rapid iteration is the key
  • 26. Who am I? Profile • Kosuke Kuzuoka (23) • Love Tesla, Elon Musk and cats Experience • February 2020 - Present Software Engineer, ML @Mercari, Inc. • June 2018 – February 2020 AI Research Engineer @DeNA Co., Ltd. • March 2017 – June 2018 R&D Manager @Photoruction, inc.
  • 27. Brief Intro to Object Detection • An active research area among computer vision community • Task is detecting objects (like cats) in an image • Modern algorithms heavily rely on deep learning • Takes hours to train a model Photo by Paul Hanaoka on Unsplash
  • 28. Photo by Paul Hanaoka on Unsplash A cat is detected as a cat, hence it’s a true positive. Wrongly detected as cats, hence they are false positives
  • 29. Problems in Development Processes 1. Train, validate and test models (computationally expensive) 2. Evaluate, visualize and analyze models (time consuming) 3. Adjust hyper-param, then go back to 1
  • 30. Problems in Development Processes 1. Train, validate and test models (computationally expensive) 2. Evaluate, visualize and analyze models (time consuming) 3. Adjust hyper-param, then go back to 1
  • 31. Problems in Development Processes 1. Train, validate and test models (computationally expensive) 2. Evaluate, visualize and analyze models (time consuming) 3. Adjust hyper-param, then go back to 1
  • 32. Problems in Development Processes 1. Train, validate and test models (computationally expensive) 2. Evaluate, visualize and analyze models (time consuming) 3. Adjust hyper-param, then go back to 1
  • 33. Problems in Development Processes 1. Train, validate and test models (computationally expensive) 2. Evaluate, visualize and analyze models (time consuming) 3. Adjust hyper-param, then go back to 1 Not essential, yet very important...
  • 34. Some of Problems are: • Error-prone process (misspelling commands, etc.) • Going back and forth between EC2 instances… • Inefficient process, like drawing boxes, uploading to third party app for visualization etc. • Researchers not being able to focus on essential work (developing models etc.)
  • 35. Solutions! • Work harder and harder... • Automating tasks via workflow engine • Flexible internal tool to evaluate, visualize and analyze models
  • 36. Solutions! • Work harder and harder... • Automating tasks via workflow engine • Flexible internal tool to evaluate, visualize and analyze models But I’m busy with AI dev...
  • 37. What We Wanted... • A system that automatically evaluates, visualizes and analyzes models and datasets. • A tool that lets researchers focus on essential work (parameter tuning etc.) • User-friendly web app
  • 38. • Easy to develop • Easy to collaborate • Good performance • AI engineer friendly (Python… ) Yet, We Want It to Be:
  • 40. • Easy to deploy and maintain • Collaborations made easy • Cost effective, yet performant • You can use Python Image source: https://serverless.com/
  • 41. Serverless Computing • No need to manage servers, cloud providers do it for you! • Consists of small deployable unit of functions • Scales as your app grows • No idle fee, pay as you go
  • 42. • No need to manage servers, cloud providers do it for you! • Consists of small deployable unit of functions • Scales as your app grows • No idle fee, pay as you go Serverless Computing Image source: https://aws.amazon.com/
  • 43. • No need to manage servers, cloud providers do it for you! • Consists of small deployable unit of functions • Scales as your app grows • No idle fee, pay as you go Serverless Computing
  • 44. • No need to manage servers, cloud providers do it for you! • Consists of small deployable unit of functions • Scales as your app grows • No idle fee, pay as you go Serverless Computing
  • 45. Serverless Computing • No need to manage servers, cloud providers do it for you! • Consists of small deployable unit of functions • Scales as your app grows • No idle fee, pay as you go
  • 47. Kaiseki-Kun Architecture 1. Prediction JSON from GPU instance 2. Evaluation begins, store results 3. Users can see results & run evaluations
  • 48. Kaiseki-Kun Architecture 1. Prediction JSON from GPU instance 2. Evaluation begins, store results 3. Users can see results & run evaluations
  • 49. 1. Prediction JSON from GPU instance 2. Evaluation begins, store results 3. Users can see results & run evaluations Kaiseki-Kun Architecture
  • 50. 1. Prediction JSON from GPU instance 2. Evaluation begins, store results 3. Users can see results & run evaluations Kaiseki-Kun Architecture
  • 51. Kaiseki-Kun Tech Stack • Backend app made of 100% serverless • Front app made of React app
  • 52. Kaiseki-Kun Tech Stack • Backend app made of 100% serverless app • Front app made of React app
  • 53. 53
  • 54. 54 Hmm, there is a FN in Red Box. What if we adjust the threshold?
  • 55. 55 Ta-da! Perhaps, the model wasn’t confident enough?
  • 56. Model is missing lots of small objects. We need more data!
  • 57. Evaluation with different config is as easy as pushing a button
  • 58. More Functionalities On Its Way... • Model version control • Dataset analysis and version control • Automating training and testing
  • 59. Summing It Up • Speed is important. You don’t want to spend too much time on an internal tool • Collaboration should be easy. Every engineer should be able to contribute • With little effort, researchers can focus on more essential work
  • 60. Wrap Up AI Technologies for Map Creation/Maintenance • Dashcam videos contain a lot of useful information for maps • Develop computer vision technology to estimate objects’ positions • Experimental evaluation shows the estimation error is less than 1m Engineering for Continuous Improvement • Rapid development cycle is important • Serverless architecture is a cost-effective choice to develop and maintain support tools for continuous improvement of AI