SlideShare a Scribd company logo
1 of 44
Download to read offline
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Bryan Samis
Specialized Solutions Architect, AWS
SRV322
Increase the Value of Video with ML &
Media Services
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Why Machine Learning for Media?
Increase Engagement
and Content
Discovery
Accelerate existing
production processes
Launch new content
or services
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Agenda
• Quick Service Overview
• Content Indexing & Metadata
Generation for image and video
• Clipped Content Retrieval
• Media Analysis Solution
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Machine Learning Stack
Platforms
Application services
A m a z o n
R e k o g n i t i o n
A m a z o n
R e k o g n i t i o n
V i d e o
P o l l y T r a n s c r i b e T r a n s l a t e C o m p r e h e n dL e x
Amazon SageMaker Amazon Mechanical Turk
Frameworks KERAS
NVIDIA
Tesla V100 GPUs
(14x faster than P2)
P3
Machine Learning
AMIs
5,120 Tensor cores
128 GB of memory
1 Petaflop of compute
NVLink 2.0
Infrastructure
&
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Automating Footage Tagging with Amazon Rekognition
• Built in 3 weeks
• Indexed against 99,000 people
• Index created in one day
• Saved ~9,000 hours a year in manual
curation costs
• Live video with frame sampling
Previously, only about half of all footage was indexed due to the immense time
requirements required by manual processes
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Key Services For Today
Processing ML Orchestration
AWS Step Functions
AWS LambdaAmazon
Transcribe
Amazon
Rekognition
AWS Elemental
MediaConvert
AWS Elemental
MediaLive
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AWS Elemental MediaConvert
• Professional grade video features and quality
• No software or hardware infrastructure to manage
• Automatically scales in response to variations in incoming
video volume
• Ability to manage capacity and control order in which jobs
are processed
• Pay for what you use, billed by the second of content
produced
AWS Elemental
MediaConvert
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition
Object & scene
detection
Facial
analysis
Face
comparison
Face
search
Celebrity
detection
Image
moderation
Text
detection
"Amazon Rekognition allows us to scalably
identify and track actors across millions of frames
of content with much higher reliability than any
other solution we've used.”
- Jared Browarnik, Co-Founder & CTO, TheTake
“Amazon Rekognition enables us to quickly and
efficiently add value through various automated
metadata tagging processes, and images and
video segments are much easier to find for our
enterprise and our customers.”
- Shane Murphy, Solutions Engineer, Scrippsnetworks
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition Video
Object, scene &
Activity detection
Face
search
Facial analysis Activity pathing
Unsafe content
detection
Celebrity
detection
Text in images
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Transcribe
A fully managed and continuously trained automatic speech recognition (ASR)
service that takes in audio and automatically generates accurate transcripts
Support for audio in
many formats and
low fidelity
§
Amazon S3
integration
Hello/
Hola
Time stamps and
confidence scores
English and SpanishPunctuation
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Transcribe – Use Cases
Call Center
Subtitles
MeetingsContent indexingCompliance
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AWS Step Functions
VisualizeDefine Monitor
Task A single unit of work
Choice Adds branching logic
Parallel Fork and join the data
Wait Delay for a specified time
Fail Stops an execution
Succeed Stops an execution successfully
Pass Passes its input to its output
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Using Amazon ML Services for Media
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Using Amazon ML Services for Media
• Use services such as Amazon Rekognition &
Amazon Transcribe to generate metadata about
your content
• Store that metadata and make it searchable
• Retrieve only the portion of the content
you want
• Prepare it for timely use
Live and file
Sources
Amazon ML
Services
ML
Amazon
DynamoDB
Database
Live and file
Content
Content Indexing / Metadata Generation Content Retrieval / Action Metadata
AWS Elemental
Media Services
Media processing
AWS Elemental
Media Services
Media processing
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Content Indexing / Metadata Generation
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Content Indexing / Metadata Generation
File-based
content
Live
content
MediaLive
Kinesis
Video
Streams
MediaConvert
Amazon Rekognition
(Image)
• JPEG/PNG
• Up to 15 MB
Amazon Rekognition
(Video)
• H.264 video
• MP4/MOV file
• Up to 8 GB
Transcribe
• FLAC/MP3/WAV/MP
4
• Up to 2 hours
• Up to 1 GB
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Content Indexing / Metadata Generation − ImageTheChallenge
• A broadcaster
wants to add
metadata to
existing archive of
video content
• Index metadata
and video to make
it searchable
• Keep costs low
TheSolution
• Use AWS
Elemental
MediaConvert to
extract frames
from video content
• Use Amazon
Rekognition to
analyze and create
metadata for video
content
TheBenefit
• Video tagged with
objects, scene
and celebrities
detection
• Five-second frame
extraction keeps
cost low while
providing
searching index
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Content Indexing / Metadata Generation − Image
AWS Elemental
MediaConvert job
transcodes file and
extracts JPEG frames to S3
bucket.
AWS Lambda function
triggered by Amazon S3
object-created event tells
Amazon Rekognition to
analyze the JPEG file.
Amazon Rekognition
performs requested
operation on image (i.e.,
object detection, celebrity
recognition, etc.).
Amazon Rekognition returns result
to AWS Lambda, which stores tags
and confidence scores in Amazon
DynamoDB, Amazon Redshift,
Amazon Elasticsearch Service,
Amazon RDS, or whichever service
best suits the use case.
AWS Elemental
MediaConvert
File-based
processing
Amazon S3
Storage
AWS Lambda
Serverless
Amazon
Rekognition
ML / AI
Amazon
DynamoDB
Database
File
Source
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
MediaConvert Configuration
Framerate
determines the
number of images
that will be extracted
from the video per
second. 1/5 indicates
to create one JPEG
every 5 seconds.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Lambda Function Code Example – Amazon Rekognition Image
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition Image Results
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Demo
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Content Indexing / Metadata Generation – VideoTheChallenge
• A content producer
wants to log who is
in each scene of
new episode of a
show
• Raw video files are
~200 GB for 60 min
TheSolution
• Use AWS Elemental
MediaConvert to
compress video
content (but retain
quality
• Use Amazon
Rekognition Video to
analyze and create
metadata for video
content
TheBenefit
• Video tagged
celebrities detection
and timing and
position of celebrity
• Video files reduces
to <8 GB for 60 mins
to reduce costs
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Content Indexing / Metadata Generation – Video
AWS Elemental MediaConvert
job transcodes source file to
H.264/MP4 at a bit rate such that
the file size is <8 GB.
AWS Lambda function triggered by
Amazon S3 object-created event
tells Amazon Rekognition to analyze
the video file.
Amazon Rekognition Video
performs requested operation on
video (i.e., person tracking,
celebrity recognition, etc.).
Amazon Rekognition returns result to
AWS Lambda, which stores tags and
confidence scores in Amazon
DynamoDB, Amazon Redshift, Amazon
Elasticsearch Service, Amazon RDS, or
whichever service best suits the use
case.
AWS Elemental
MediaConvert
File-based
processing
Amazon S3
Storage
AWS Lambda
Serverless
Amazon
Rekognition
ML / AI
Amazon
DynamoDB
Database
File
Source
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
MediaConvert Configuration
Use Container MPEG-
4 Container (MP4)
and a file extension of
mp4.
Set Video Codec to
MPEG-4 AVC (H.264).
Select bit rate accordingly
so output file is smaller
than 8 GB. For example, a
60-minute movie at 7 Mbps
will be approximately
3.2 GB.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Lambda Function Code Example – Amazon Rekognition Video
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Lambda Function Code Example – Amazon Rekognition Video
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition Video Results
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Demo
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Content Indexing / Metadata Generation – TranscriptionTheChallenge
• An online training
provider has 1,000s of
hours of video that
need captions
• Video is in a variety of
formats
TheSolution
• Use AWS Elemental
MediaConvert create
audio only version of
content
• Use Amazon
Transcribe to generate
timestamped
transcription
• Convert Amazon
Transcribe output to
captions file
TheBenefit
• All formats of video
content get captions
added to make them
more accessible
• Option to run Amazon
Transcribe output
through Amazon
Translate to get multi-
language captions
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Content Indexing / Metadata Generation – Transcription
AWS Elemental MediaConvert
job transcodes source file,
creating audio-only rendition for
Amazon Transcribe
AWS Elemental
MediaConvert also
creates normal
audio/video output
AWS Lambda function triggered
by Amazon S3 object-created
event creates a new Transcribe
job
Amazon Transcribe outputs
JSON file of detected words
and timing
Lambda function converts Amazon
Transcribe JSON into subtitle format
(such as WebVTT, SRT, or TTML) and
delivers to
Amazon S3 bucket with content
AWS Elemental
MediaConvert
File-based
processing
AWS Lambda
Serverless
Amazon
Transcribe
ML / AI
File
Source
Amazon S3
Storage
Amazon S3
STORAGE
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
MediaConvert Configuration
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Lambda Function Code Example − Amazon Transcribe
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Polling Transcribe with AWS Step Functions
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Transcribe Results
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Transcribe to Captions
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Transcribe to Captions Approaches
Cadence Heuristic – Use larger than
average gaps between words as delimiter
Fixed Duration – Aggregate all words
within a given duration
What about scene changes? Non-dialog sound
elements?
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Content Retrieval
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Content Retrieval with MediaConvert ClippingTheChallenge
• The content
producer would like
to create a promo
clip of all of the
scenes from their
episode that contain
a particular actor.
• Remember, the
source file is 60
minutes long and
200 GB.
TheSolution
• Amazon Rekognition
video facial
recognition identifies
when the star
appears in the source
video.
• AWS Elemental
MediaConvert uses
time references to
selectively transcode
source video.
TheBenefit
• Faster and more
cost-effective clip
generation as only
the video contents
that has been
identified as
featuring the
celebrity is
transcoded.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Content Retrieval with MediaConvert Clipping
AWS Elemental MediaConvert
transcodes clips from the source file,
using only the time range(s) specified
AWS Elemental
MediaConvert
File-based
processing
Amazon S3
Storage
Clipped file
Output
Amazon
DynamoDB
Database
AWS Lambda
Serverless
Lambda function
queries database for
metadata being
searched
Lambda function creates
MediaConvert transcode job
specifying time(s) from
source to clip
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
MediaConvert Input Clipping Configuration
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AWS Media Analysis Solution
https://aws.amazon.com/answers/media-entertainment/media-analysis-solution/
• Generate searchable metadata from
your media assets using Amazon
Rekognition, Amazon Transcribe,
Amazon Comprehend, and Amazon
Elasticsearch Service
• Deploy in minutes with a single click
using AWS CloudFormation
• Interact via API or demo web UI
• Orchestrated with Step Functions,
extensible and easily customizable
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Thanks!
Please complete the session survey
in the mobile app.
samisb@amazon.com
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Submit session feedback
1. Tap the Schedule icon.
2. Select the session you
attended.
3. Tap Session Evaluation to
submit your feedback.

More Related Content

What's hot

Building Well Architected .NET Apps (WIN304) - AWS re:Invent 2018
Building Well Architected .NET Apps (WIN304) - AWS re:Invent 2018Building Well Architected .NET Apps (WIN304) - AWS re:Invent 2018
Building Well Architected .NET Apps (WIN304) - AWS re:Invent 2018Amazon Web Services
 
Design and Implement a Serverless Media-Processing Workflow
Design and Implement a Serverless Media-Processing Workflow Design and Implement a Serverless Media-Processing Workflow
Design and Implement a Serverless Media-Processing Workflow Amazon Web Services
 
BDA309 Build Your First Big Data Application on AWS
BDA309 Build Your First Big Data Application on AWSBDA309 Build Your First Big Data Application on AWS
BDA309 Build Your First Big Data Application on AWSAmazon Web Services
 
Optimize Amazon EC2 for Fun and Profit
Optimize Amazon EC2 for Fun and Profit Optimize Amazon EC2 for Fun and Profit
Optimize Amazon EC2 for Fun and Profit Amazon Web Services
 
BDA302 Building Intelligent Apps with AWS Machine Learning Language Services
BDA302 Building Intelligent Apps with AWS Machine Learning Language ServicesBDA302 Building Intelligent Apps with AWS Machine Learning Language Services
BDA302 Building Intelligent Apps with AWS Machine Learning Language ServicesAmazon Web Services
 
Increase the Value of Video with ML & Media Services - SRV322 - New York AWS ...
Increase the Value of Video with ML & Media Services - SRV322 - New York AWS ...Increase the Value of Video with ML & Media Services - SRV322 - New York AWS ...
Increase the Value of Video with ML & Media Services - SRV322 - New York AWS ...Amazon Web Services
 
Optimize Your SaaS Offering with Serverless Microservices (GPSTEC405) - AWS r...
Optimize Your SaaS Offering with Serverless Microservices (GPSTEC405) - AWS r...Optimize Your SaaS Offering with Serverless Microservices (GPSTEC405) - AWS r...
Optimize Your SaaS Offering with Serverless Microservices (GPSTEC405) - AWS r...Amazon Web Services
 
Build Intelligent Apps with Amazon ML
Build Intelligent Apps with Amazon ML Build Intelligent Apps with Amazon ML
Build Intelligent Apps with Amazon ML Amazon Web Services
 
Analyze Amazon CloudFront and Lambda@Edge Logs to Improve Customer Experience...
Analyze Amazon CloudFront and Lambda@Edge Logs to Improve Customer Experience...Analyze Amazon CloudFront and Lambda@Edge Logs to Improve Customer Experience...
Analyze Amazon CloudFront and Lambda@Edge Logs to Improve Customer Experience...Amazon Web Services
 
Protecting Your Greatest Asset (Your Data): Security Best Practices on Dynamo...
Protecting Your Greatest Asset (Your Data): Security Best Practices on Dynamo...Protecting Your Greatest Asset (Your Data): Security Best Practices on Dynamo...
Protecting Your Greatest Asset (Your Data): Security Best Practices on Dynamo...Amazon Web Services
 
Architecture Patterns of Serverless Microservices (ARC304-R1) - AWS re:Invent...
Architecture Patterns of Serverless Microservices (ARC304-R1) - AWS re:Invent...Architecture Patterns of Serverless Microservices (ARC304-R1) - AWS re:Invent...
Architecture Patterns of Serverless Microservices (ARC304-R1) - AWS re:Invent...Amazon Web Services
 
Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...
Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...
Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...Amazon Web Services
 
Authentication & Authorization in GraphQL with AWS AppSync (MOB402) - AWS re:...
Authentication & Authorization in GraphQL with AWS AppSync (MOB402) - AWS re:...Authentication & Authorization in GraphQL with AWS AppSync (MOB402) - AWS re:...
Authentication & Authorization in GraphQL with AWS AppSync (MOB402) - AWS re:...Amazon Web Services
 
Protect & Manage Amazon S3 & Amazon Glacier Objects at Scale (STG316-R1) - AW...
Protect & Manage Amazon S3 & Amazon Glacier Objects at Scale (STG316-R1) - AW...Protect & Manage Amazon S3 & Amazon Glacier Objects at Scale (STG316-R1) - AW...
Protect & Manage Amazon S3 & Amazon Glacier Objects at Scale (STG316-R1) - AW...Amazon Web Services
 
Serverless Architectural Patterns I AWS Dev Day 2018
Serverless Architectural Patterns I AWS Dev Day 2018Serverless Architectural Patterns I AWS Dev Day 2018
Serverless Architectural Patterns I AWS Dev Day 2018AWS Germany
 
Best Practices to Secure Data Lake on AWS (ANT327) - AWS re:Invent 2018
Best Practices to Secure Data Lake on AWS (ANT327) - AWS re:Invent 2018Best Practices to Secure Data Lake on AWS (ANT327) - AWS re:Invent 2018
Best Practices to Secure Data Lake on AWS (ANT327) - AWS re:Invent 2018Amazon Web Services
 
SRV327 Replicate, Analyze, and Visualize Data Using Managed Database and Ser...
 SRV327 Replicate, Analyze, and Visualize Data Using Managed Database and Ser... SRV327 Replicate, Analyze, and Visualize Data Using Managed Database and Ser...
SRV327 Replicate, Analyze, and Visualize Data Using Managed Database and Ser...Amazon Web Services
 

What's hot (20)

Building Well Architected .NET Apps (WIN304) - AWS re:Invent 2018
Building Well Architected .NET Apps (WIN304) - AWS re:Invent 2018Building Well Architected .NET Apps (WIN304) - AWS re:Invent 2018
Building Well Architected .NET Apps (WIN304) - AWS re:Invent 2018
 
Design and Implement a Serverless Media-Processing Workflow
Design and Implement a Serverless Media-Processing Workflow Design and Implement a Serverless Media-Processing Workflow
Design and Implement a Serverless Media-Processing Workflow
 
BDA309 Build Your First Big Data Application on AWS
BDA309 Build Your First Big Data Application on AWSBDA309 Build Your First Big Data Application on AWS
BDA309 Build Your First Big Data Application on AWS
 
Optimize Amazon EC2 for Fun and Profit
Optimize Amazon EC2 for Fun and Profit Optimize Amazon EC2 for Fun and Profit
Optimize Amazon EC2 for Fun and Profit
 
BDA302 Building Intelligent Apps with AWS Machine Learning Language Services
BDA302 Building Intelligent Apps with AWS Machine Learning Language ServicesBDA302 Building Intelligent Apps with AWS Machine Learning Language Services
BDA302 Building Intelligent Apps with AWS Machine Learning Language Services
 
Increase the Value of Video with ML & Media Services - SRV322 - New York AWS ...
Increase the Value of Video with ML & Media Services - SRV322 - New York AWS ...Increase the Value of Video with ML & Media Services - SRV322 - New York AWS ...
Increase the Value of Video with ML & Media Services - SRV322 - New York AWS ...
 
Optimize Your SaaS Offering with Serverless Microservices (GPSTEC405) - AWS r...
Optimize Your SaaS Offering with Serverless Microservices (GPSTEC405) - AWS r...Optimize Your SaaS Offering with Serverless Microservices (GPSTEC405) - AWS r...
Optimize Your SaaS Offering with Serverless Microservices (GPSTEC405) - AWS r...
 
Build Intelligent Apps with Amazon ML
Build Intelligent Apps with Amazon ML Build Intelligent Apps with Amazon ML
Build Intelligent Apps with Amazon ML
 
Analyze Amazon CloudFront and Lambda@Edge Logs to Improve Customer Experience...
Analyze Amazon CloudFront and Lambda@Edge Logs to Improve Customer Experience...Analyze Amazon CloudFront and Lambda@Edge Logs to Improve Customer Experience...
Analyze Amazon CloudFront and Lambda@Edge Logs to Improve Customer Experience...
 
Taking Serverless to the Edge
Taking Serverless to the Edge Taking Serverless to the Edge
Taking Serverless to the Edge
 
Protecting Your Greatest Asset (Your Data): Security Best Practices on Dynamo...
Protecting Your Greatest Asset (Your Data): Security Best Practices on Dynamo...Protecting Your Greatest Asset (Your Data): Security Best Practices on Dynamo...
Protecting Your Greatest Asset (Your Data): Security Best Practices on Dynamo...
 
Architecture Patterns of Serverless Microservices (ARC304-R1) - AWS re:Invent...
Architecture Patterns of Serverless Microservices (ARC304-R1) - AWS re:Invent...Architecture Patterns of Serverless Microservices (ARC304-R1) - AWS re:Invent...
Architecture Patterns of Serverless Microservices (ARC304-R1) - AWS re:Invent...
 
Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...
Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...
Policy Verification and Enforcement at Scale with AWS (SEC320) - AWS re:Inven...
 
Authentication & Authorization in GraphQL with AWS AppSync (MOB402) - AWS re:...
Authentication & Authorization in GraphQL with AWS AppSync (MOB402) - AWS re:...Authentication & Authorization in GraphQL with AWS AppSync (MOB402) - AWS re:...
Authentication & Authorization in GraphQL with AWS AppSync (MOB402) - AWS re:...
 
Managed NoSQL databases
Managed NoSQL databasesManaged NoSQL databases
Managed NoSQL databases
 
Protect & Manage Amazon S3 & Amazon Glacier Objects at Scale (STG316-R1) - AW...
Protect & Manage Amazon S3 & Amazon Glacier Objects at Scale (STG316-R1) - AW...Protect & Manage Amazon S3 & Amazon Glacier Objects at Scale (STG316-R1) - AW...
Protect & Manage Amazon S3 & Amazon Glacier Objects at Scale (STG316-R1) - AW...
 
Bring Alexa to Work
Bring Alexa to Work Bring Alexa to Work
Bring Alexa to Work
 
Serverless Architectural Patterns I AWS Dev Day 2018
Serverless Architectural Patterns I AWS Dev Day 2018Serverless Architectural Patterns I AWS Dev Day 2018
Serverless Architectural Patterns I AWS Dev Day 2018
 
Best Practices to Secure Data Lake on AWS (ANT327) - AWS re:Invent 2018
Best Practices to Secure Data Lake on AWS (ANT327) - AWS re:Invent 2018Best Practices to Secure Data Lake on AWS (ANT327) - AWS re:Invent 2018
Best Practices to Secure Data Lake on AWS (ANT327) - AWS re:Invent 2018
 
SRV327 Replicate, Analyze, and Visualize Data Using Managed Database and Ser...
 SRV327 Replicate, Analyze, and Visualize Data Using Managed Database and Ser... SRV327 Replicate, Analyze, and Visualize Data Using Managed Database and Ser...
SRV327 Replicate, Analyze, and Visualize Data Using Managed Database and Ser...
 

Similar to Increase the Value of Video with ML & Media Services - SRV322 - Toronto AWS Summit

AWS Immersion Day - Image Data Insights & Analytics Specialist Session - June...
AWS Immersion Day - Image Data Insights & Analytics Specialist Session - June...AWS Immersion Day - Image Data Insights & Analytics Specialist Session - June...
AWS Immersion Day - Image Data Insights & Analytics Specialist Session - June...Amazon Web Services
 
SRV322 Increase the Value of Video with ML & Media Services
 SRV322 Increase the Value of Video with ML & Media Services SRV322 Increase the Value of Video with ML & Media Services
SRV322 Increase the Value of Video with ML & Media ServicesAmazon Web Services
 
Building Data Lakes That Cost Less and Deliver Results Faster - AWS Online Te...
Building Data Lakes That Cost Less and Deliver Results Faster - AWS Online Te...Building Data Lakes That Cost Less and Deliver Results Faster - AWS Online Te...
Building Data Lakes That Cost Less and Deliver Results Faster - AWS Online Te...Amazon Web Services
 
Customizing Data Lakes to Work for Your Enterprise with Sysco (STG340) - AWS ...
Customizing Data Lakes to Work for Your Enterprise with Sysco (STG340) - AWS ...Customizing Data Lakes to Work for Your Enterprise with Sysco (STG340) - AWS ...
Customizing Data Lakes to Work for Your Enterprise with Sysco (STG340) - AWS ...Amazon Web Services
 
Build Enterprise-Grade Serverless Apps - SRV315 - Atlanta AWS Summit
Build Enterprise-Grade Serverless Apps - SRV315 - Atlanta AWS SummitBuild Enterprise-Grade Serverless Apps - SRV315 - Atlanta AWS Summit
Build Enterprise-Grade Serverless Apps - SRV315 - Atlanta AWS SummitAmazon Web Services
 
Build Your Own Log Analytics Solutions on AWS (ANT323-R) - AWS re:Invent 2018
Build Your Own Log Analytics Solutions on AWS (ANT323-R) - AWS re:Invent 2018Build Your Own Log Analytics Solutions on AWS (ANT323-R) - AWS re:Invent 2018
Build Your Own Log Analytics Solutions on AWS (ANT323-R) - AWS re:Invent 2018Amazon Web Services
 
Building+your+Data+Project+on+AWS+-+Luke+Anderson.pdf
Building+your+Data+Project+on+AWS+-+Luke+Anderson.pdfBuilding+your+Data+Project+on+AWS+-+Luke+Anderson.pdf
Building+your+Data+Project+on+AWS+-+Luke+Anderson.pdfSasikumarPalanivel3
 
Building+your+Data+Project+on+AWS+-+Luke+Anderson.pdf
Building+your+Data+Project+on+AWS+-+Luke+Anderson.pdfBuilding+your+Data+Project+on+AWS+-+Luke+Anderson.pdf
Building+your+Data+Project+on+AWS+-+Luke+Anderson.pdfsaidbilgen
 
Big Data - EBC on the road Brazil Edition [Portuguese]
Big Data - EBC on the road Brazil Edition [Portuguese]Big Data - EBC on the road Brazil Edition [Portuguese]
Big Data - EBC on the road Brazil Edition [Portuguese]Amazon Web Services
 
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...Amazon Web Services
 
Building Serverless Applications with Amazon DynamoDB & AWS Lambda - Workshop...
Building Serverless Applications with Amazon DynamoDB & AWS Lambda - Workshop...Building Serverless Applications with Amazon DynamoDB & AWS Lambda - Workshop...
Building Serverless Applications with Amazon DynamoDB & AWS Lambda - Workshop...Amazon Web Services
 
Evolution of media workflows aided by Machine Learning- AWS Summit Cape Town ...
Evolution of media workflows aided by Machine Learning- AWS Summit Cape Town ...Evolution of media workflows aided by Machine Learning- AWS Summit Cape Town ...
Evolution of media workflows aided by Machine Learning- AWS Summit Cape Town ...Amazon Web Services
 
Big Data Meets AI - Driving Insights and Adding Intelligence to Your Solutions
 Big Data Meets AI - Driving Insights and Adding Intelligence to Your Solutions Big Data Meets AI - Driving Insights and Adding Intelligence to Your Solutions
Big Data Meets AI - Driving Insights and Adding Intelligence to Your SolutionsAmazon Web Services
 
Building an end to end image recognition service - Tel Aviv Summit 2018
Building an end to end image recognition service - Tel Aviv Summit 2018Building an end to end image recognition service - Tel Aviv Summit 2018
Building an end to end image recognition service - Tel Aviv Summit 2018Amazon Web Services
 
Visualise and Voice-Enable Your Security
Visualise and Voice-Enable Your SecurityVisualise and Voice-Enable Your Security
Visualise and Voice-Enable Your SecurityAmazon Web Services
 
Scaling from zero to millions of users
Scaling from zero to millions of usersScaling from zero to millions of users
Scaling from zero to millions of usersAmazon Web Services
 
Aws Tools for Alexa Skills
Aws Tools for Alexa SkillsAws Tools for Alexa Skills
Aws Tools for Alexa SkillsBoaz Ziniman
 
Build Enterprise-Grade Serverless Apps - SRV315 - Chicago AWS Summit
Build Enterprise-Grade Serverless Apps - SRV315 - Chicago AWS SummitBuild Enterprise-Grade Serverless Apps - SRV315 - Chicago AWS Summit
Build Enterprise-Grade Serverless Apps - SRV315 - Chicago AWS SummitAmazon Web Services
 
Building serverless enterprise applications - SRV315 - Toronto AWS Summit
Building serverless enterprise applications - SRV315 - Toronto AWS SummitBuilding serverless enterprise applications - SRV315 - Toronto AWS Summit
Building serverless enterprise applications - SRV315 - Toronto AWS SummitAmazon Web Services
 

Similar to Increase the Value of Video with ML & Media Services - SRV322 - Toronto AWS Summit (20)

AWS Immersion Day - Image Data Insights & Analytics Specialist Session - June...
AWS Immersion Day - Image Data Insights & Analytics Specialist Session - June...AWS Immersion Day - Image Data Insights & Analytics Specialist Session - June...
AWS Immersion Day - Image Data Insights & Analytics Specialist Session - June...
 
SRV322 Increase the Value of Video with ML & Media Services
 SRV322 Increase the Value of Video with ML & Media Services SRV322 Increase the Value of Video with ML & Media Services
SRV322 Increase the Value of Video with ML & Media Services
 
Building Data Lakes That Cost Less and Deliver Results Faster - AWS Online Te...
Building Data Lakes That Cost Less and Deliver Results Faster - AWS Online Te...Building Data Lakes That Cost Less and Deliver Results Faster - AWS Online Te...
Building Data Lakes That Cost Less and Deliver Results Faster - AWS Online Te...
 
Customizing Data Lakes to Work for Your Enterprise with Sysco (STG340) - AWS ...
Customizing Data Lakes to Work for Your Enterprise with Sysco (STG340) - AWS ...Customizing Data Lakes to Work for Your Enterprise with Sysco (STG340) - AWS ...
Customizing Data Lakes to Work for Your Enterprise with Sysco (STG340) - AWS ...
 
Build Enterprise-Grade Serverless Apps - SRV315 - Atlanta AWS Summit
Build Enterprise-Grade Serverless Apps - SRV315 - Atlanta AWS SummitBuild Enterprise-Grade Serverless Apps - SRV315 - Atlanta AWS Summit
Build Enterprise-Grade Serverless Apps - SRV315 - Atlanta AWS Summit
 
Build Your Own Log Analytics Solutions on AWS (ANT323-R) - AWS re:Invent 2018
Build Your Own Log Analytics Solutions on AWS (ANT323-R) - AWS re:Invent 2018Build Your Own Log Analytics Solutions on AWS (ANT323-R) - AWS re:Invent 2018
Build Your Own Log Analytics Solutions on AWS (ANT323-R) - AWS re:Invent 2018
 
Building+your+Data+Project+on+AWS+-+Luke+Anderson.pdf
Building+your+Data+Project+on+AWS+-+Luke+Anderson.pdfBuilding+your+Data+Project+on+AWS+-+Luke+Anderson.pdf
Building+your+Data+Project+on+AWS+-+Luke+Anderson.pdf
 
Building+your+Data+Project+on+AWS+-+Luke+Anderson.pdf
Building+your+Data+Project+on+AWS+-+Luke+Anderson.pdfBuilding+your+Data+Project+on+AWS+-+Luke+Anderson.pdf
Building+your+Data+Project+on+AWS+-+Luke+Anderson.pdf
 
Big Data - EBC on the road Brazil Edition [Portuguese]
Big Data - EBC on the road Brazil Edition [Portuguese]Big Data - EBC on the road Brazil Edition [Portuguese]
Big Data - EBC on the road Brazil Edition [Portuguese]
 
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
Dissecting Media Asset Management Architecture and Media Archive TCO (MAE301)...
 
Building Serverless Applications with Amazon DynamoDB & AWS Lambda - Workshop...
Building Serverless Applications with Amazon DynamoDB & AWS Lambda - Workshop...Building Serverless Applications with Amazon DynamoDB & AWS Lambda - Workshop...
Building Serverless Applications with Amazon DynamoDB & AWS Lambda - Workshop...
 
Evolution of media workflows aided by Machine Learning- AWS Summit Cape Town ...
Evolution of media workflows aided by Machine Learning- AWS Summit Cape Town ...Evolution of media workflows aided by Machine Learning- AWS Summit Cape Town ...
Evolution of media workflows aided by Machine Learning- AWS Summit Cape Town ...
 
Big Data Meets AI - Driving Insights and Adding Intelligence to Your Solutions
 Big Data Meets AI - Driving Insights and Adding Intelligence to Your Solutions Big Data Meets AI - Driving Insights and Adding Intelligence to Your Solutions
Big Data Meets AI - Driving Insights and Adding Intelligence to Your Solutions
 
Building an end to end image recognition service - Tel Aviv Summit 2018
Building an end to end image recognition service - Tel Aviv Summit 2018Building an end to end image recognition service - Tel Aviv Summit 2018
Building an end to end image recognition service - Tel Aviv Summit 2018
 
Intro to AI & ML at Amazon
Intro to AI & ML at AmazonIntro to AI & ML at Amazon
Intro to AI & ML at Amazon
 
Visualise and Voice-Enable Your Security
Visualise and Voice-Enable Your SecurityVisualise and Voice-Enable Your Security
Visualise and Voice-Enable Your Security
 
Scaling from zero to millions of users
Scaling from zero to millions of usersScaling from zero to millions of users
Scaling from zero to millions of users
 
Aws Tools for Alexa Skills
Aws Tools for Alexa SkillsAws Tools for Alexa Skills
Aws Tools for Alexa Skills
 
Build Enterprise-Grade Serverless Apps - SRV315 - Chicago AWS Summit
Build Enterprise-Grade Serverless Apps - SRV315 - Chicago AWS SummitBuild Enterprise-Grade Serverless Apps - SRV315 - Chicago AWS Summit
Build Enterprise-Grade Serverless Apps - SRV315 - Chicago AWS Summit
 
Building serverless enterprise applications - SRV315 - Toronto AWS Summit
Building serverless enterprise applications - SRV315 - Toronto AWS SummitBuilding serverless enterprise applications - SRV315 - Toronto AWS Summit
Building serverless enterprise applications - SRV315 - Toronto AWS Summit
 

More from Amazon Web Services

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Amazon Web Services
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Amazon Web Services
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateAmazon Web Services
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSAmazon Web Services
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Amazon Web Services
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Amazon Web Services
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...Amazon Web Services
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsAmazon Web Services
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareAmazon Web Services
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSAmazon Web Services
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAmazon Web Services
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareAmazon Web Services
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWSAmazon Web Services
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckAmazon Web Services
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without serversAmazon Web Services
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...Amazon Web Services
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceAmazon Web Services
 

More from Amazon Web Services (20)

Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
Come costruire servizi di Forecasting sfruttando algoritmi di ML e deep learn...
 
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
Big Data per le Startup: come creare applicazioni Big Data in modalità Server...
 
Esegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS FargateEsegui pod serverless con Amazon EKS e AWS Fargate
Esegui pod serverless con Amazon EKS e AWS Fargate
 
Costruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWSCostruire Applicazioni Moderne con AWS
Costruire Applicazioni Moderne con AWS
 
Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot Come spendere fino al 90% in meno con i container e le istanze spot
Come spendere fino al 90% in meno con i container e le istanze spot
 
Open banking as a service
Open banking as a serviceOpen banking as a service
Open banking as a service
 
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
Rendi unica l’offerta della tua startup sul mercato con i servizi Machine Lea...
 
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...OpsWorks Configuration Management: automatizza la gestione e i deployment del...
OpsWorks Configuration Management: automatizza la gestione e i deployment del...
 
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows WorkloadsMicrosoft Active Directory su AWS per supportare i tuoi Windows Workloads
Microsoft Active Directory su AWS per supportare i tuoi Windows Workloads
 
Computer Vision con AWS
Computer Vision con AWSComputer Vision con AWS
Computer Vision con AWS
 
Database Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatareDatabase Oracle e VMware Cloud on AWS i miti da sfatare
Database Oracle e VMware Cloud on AWS i miti da sfatare
 
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJSCrea la tua prima serverless ledger-based app con QLDB e NodeJS
Crea la tua prima serverless ledger-based app con QLDB e NodeJS
 
API moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e webAPI moderne real-time per applicazioni mobili e web
API moderne real-time per applicazioni mobili e web
 
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatareDatabase Oracle e VMware Cloud™ on AWS: i miti da sfatare
Database Oracle e VMware Cloud™ on AWS: i miti da sfatare
 
Tools for building your MVP on AWS
Tools for building your MVP on AWSTools for building your MVP on AWS
Tools for building your MVP on AWS
 
How to Build a Winning Pitch Deck
How to Build a Winning Pitch DeckHow to Build a Winning Pitch Deck
How to Build a Winning Pitch Deck
 
Building a web application without servers
Building a web application without serversBuilding a web application without servers
Building a web application without servers
 
Fundraising Essentials
Fundraising EssentialsFundraising Essentials
Fundraising Essentials
 
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
AWS_HK_StartupDay_Building Interactive websites while automating for efficien...
 
Introduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container ServiceIntroduzione a Amazon Elastic Container Service
Introduzione a Amazon Elastic Container Service
 

Increase the Value of Video with ML & Media Services - SRV322 - Toronto AWS Summit

  • 1. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Bryan Samis Specialized Solutions Architect, AWS SRV322 Increase the Value of Video with ML & Media Services
  • 2. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Why Machine Learning for Media? Increase Engagement and Content Discovery Accelerate existing production processes Launch new content or services
  • 3. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Agenda • Quick Service Overview • Content Indexing & Metadata Generation for image and video • Clipped Content Retrieval • Media Analysis Solution
  • 4. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Machine Learning Stack Platforms Application services A m a z o n R e k o g n i t i o n A m a z o n R e k o g n i t i o n V i d e o P o l l y T r a n s c r i b e T r a n s l a t e C o m p r e h e n dL e x Amazon SageMaker Amazon Mechanical Turk Frameworks KERAS NVIDIA Tesla V100 GPUs (14x faster than P2) P3 Machine Learning AMIs 5,120 Tensor cores 128 GB of memory 1 Petaflop of compute NVLink 2.0 Infrastructure &
  • 5. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Automating Footage Tagging with Amazon Rekognition • Built in 3 weeks • Indexed against 99,000 people • Index created in one day • Saved ~9,000 hours a year in manual curation costs • Live video with frame sampling Previously, only about half of all footage was indexed due to the immense time requirements required by manual processes
  • 6. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Key Services For Today Processing ML Orchestration AWS Step Functions AWS LambdaAmazon Transcribe Amazon Rekognition AWS Elemental MediaConvert AWS Elemental MediaLive
  • 7. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. AWS Elemental MediaConvert • Professional grade video features and quality • No software or hardware infrastructure to manage • Automatically scales in response to variations in incoming video volume • Ability to manage capacity and control order in which jobs are processed • Pay for what you use, billed by the second of content produced AWS Elemental MediaConvert
  • 8. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition Object & scene detection Facial analysis Face comparison Face search Celebrity detection Image moderation Text detection "Amazon Rekognition allows us to scalably identify and track actors across millions of frames of content with much higher reliability than any other solution we've used.” - Jared Browarnik, Co-Founder & CTO, TheTake “Amazon Rekognition enables us to quickly and efficiently add value through various automated metadata tagging processes, and images and video segments are much easier to find for our enterprise and our customers.” - Shane Murphy, Solutions Engineer, Scrippsnetworks
  • 9. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition Video Object, scene & Activity detection Face search Facial analysis Activity pathing Unsafe content detection Celebrity detection Text in images
  • 10. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Transcribe A fully managed and continuously trained automatic speech recognition (ASR) service that takes in audio and automatically generates accurate transcripts Support for audio in many formats and low fidelity § Amazon S3 integration Hello/ Hola Time stamps and confidence scores English and SpanishPunctuation
  • 11. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Transcribe – Use Cases Call Center Subtitles MeetingsContent indexingCompliance
  • 12. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. AWS Step Functions VisualizeDefine Monitor Task A single unit of work Choice Adds branching logic Parallel Fork and join the data Wait Delay for a specified time Fail Stops an execution Succeed Stops an execution successfully Pass Passes its input to its output
  • 13. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Using Amazon ML Services for Media
  • 14. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Using Amazon ML Services for Media • Use services such as Amazon Rekognition & Amazon Transcribe to generate metadata about your content • Store that metadata and make it searchable • Retrieve only the portion of the content you want • Prepare it for timely use Live and file Sources Amazon ML Services ML Amazon DynamoDB Database Live and file Content Content Indexing / Metadata Generation Content Retrieval / Action Metadata AWS Elemental Media Services Media processing AWS Elemental Media Services Media processing
  • 15. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Content Indexing / Metadata Generation
  • 16. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Content Indexing / Metadata Generation File-based content Live content MediaLive Kinesis Video Streams MediaConvert Amazon Rekognition (Image) • JPEG/PNG • Up to 15 MB Amazon Rekognition (Video) • H.264 video • MP4/MOV file • Up to 8 GB Transcribe • FLAC/MP3/WAV/MP 4 • Up to 2 hours • Up to 1 GB
  • 17. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Content Indexing / Metadata Generation − ImageTheChallenge • A broadcaster wants to add metadata to existing archive of video content • Index metadata and video to make it searchable • Keep costs low TheSolution • Use AWS Elemental MediaConvert to extract frames from video content • Use Amazon Rekognition to analyze and create metadata for video content TheBenefit • Video tagged with objects, scene and celebrities detection • Five-second frame extraction keeps cost low while providing searching index
  • 18. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Content Indexing / Metadata Generation − Image AWS Elemental MediaConvert job transcodes file and extracts JPEG frames to S3 bucket. AWS Lambda function triggered by Amazon S3 object-created event tells Amazon Rekognition to analyze the JPEG file. Amazon Rekognition performs requested operation on image (i.e., object detection, celebrity recognition, etc.). Amazon Rekognition returns result to AWS Lambda, which stores tags and confidence scores in Amazon DynamoDB, Amazon Redshift, Amazon Elasticsearch Service, Amazon RDS, or whichever service best suits the use case. AWS Elemental MediaConvert File-based processing Amazon S3 Storage AWS Lambda Serverless Amazon Rekognition ML / AI Amazon DynamoDB Database File Source
  • 19. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. MediaConvert Configuration Framerate determines the number of images that will be extracted from the video per second. 1/5 indicates to create one JPEG every 5 seconds.
  • 20. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Lambda Function Code Example – Amazon Rekognition Image
  • 21. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition Image Results
  • 22. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Demo
  • 23. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Content Indexing / Metadata Generation – VideoTheChallenge • A content producer wants to log who is in each scene of new episode of a show • Raw video files are ~200 GB for 60 min TheSolution • Use AWS Elemental MediaConvert to compress video content (but retain quality • Use Amazon Rekognition Video to analyze and create metadata for video content TheBenefit • Video tagged celebrities detection and timing and position of celebrity • Video files reduces to <8 GB for 60 mins to reduce costs
  • 24. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Content Indexing / Metadata Generation – Video AWS Elemental MediaConvert job transcodes source file to H.264/MP4 at a bit rate such that the file size is <8 GB. AWS Lambda function triggered by Amazon S3 object-created event tells Amazon Rekognition to analyze the video file. Amazon Rekognition Video performs requested operation on video (i.e., person tracking, celebrity recognition, etc.). Amazon Rekognition returns result to AWS Lambda, which stores tags and confidence scores in Amazon DynamoDB, Amazon Redshift, Amazon Elasticsearch Service, Amazon RDS, or whichever service best suits the use case. AWS Elemental MediaConvert File-based processing Amazon S3 Storage AWS Lambda Serverless Amazon Rekognition ML / AI Amazon DynamoDB Database File Source
  • 25. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. MediaConvert Configuration Use Container MPEG- 4 Container (MP4) and a file extension of mp4. Set Video Codec to MPEG-4 AVC (H.264). Select bit rate accordingly so output file is smaller than 8 GB. For example, a 60-minute movie at 7 Mbps will be approximately 3.2 GB.
  • 26. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Lambda Function Code Example – Amazon Rekognition Video
  • 27. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Lambda Function Code Example – Amazon Rekognition Video
  • 28. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition Video Results
  • 29. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Demo
  • 30. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Content Indexing / Metadata Generation – TranscriptionTheChallenge • An online training provider has 1,000s of hours of video that need captions • Video is in a variety of formats TheSolution • Use AWS Elemental MediaConvert create audio only version of content • Use Amazon Transcribe to generate timestamped transcription • Convert Amazon Transcribe output to captions file TheBenefit • All formats of video content get captions added to make them more accessible • Option to run Amazon Transcribe output through Amazon Translate to get multi- language captions
  • 31. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Content Indexing / Metadata Generation – Transcription AWS Elemental MediaConvert job transcodes source file, creating audio-only rendition for Amazon Transcribe AWS Elemental MediaConvert also creates normal audio/video output AWS Lambda function triggered by Amazon S3 object-created event creates a new Transcribe job Amazon Transcribe outputs JSON file of detected words and timing Lambda function converts Amazon Transcribe JSON into subtitle format (such as WebVTT, SRT, or TTML) and delivers to Amazon S3 bucket with content AWS Elemental MediaConvert File-based processing AWS Lambda Serverless Amazon Transcribe ML / AI File Source Amazon S3 Storage Amazon S3 STORAGE
  • 32. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. MediaConvert Configuration
  • 33. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Lambda Function Code Example − Amazon Transcribe
  • 34. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Polling Transcribe with AWS Step Functions
  • 35. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Transcribe Results
  • 36. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Transcribe to Captions
  • 37. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Transcribe to Captions Approaches Cadence Heuristic – Use larger than average gaps between words as delimiter Fixed Duration – Aggregate all words within a given duration What about scene changes? Non-dialog sound elements?
  • 38. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Content Retrieval
  • 39. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Content Retrieval with MediaConvert ClippingTheChallenge • The content producer would like to create a promo clip of all of the scenes from their episode that contain a particular actor. • Remember, the source file is 60 minutes long and 200 GB. TheSolution • Amazon Rekognition video facial recognition identifies when the star appears in the source video. • AWS Elemental MediaConvert uses time references to selectively transcode source video. TheBenefit • Faster and more cost-effective clip generation as only the video contents that has been identified as featuring the celebrity is transcoded.
  • 40. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Content Retrieval with MediaConvert Clipping AWS Elemental MediaConvert transcodes clips from the source file, using only the time range(s) specified AWS Elemental MediaConvert File-based processing Amazon S3 Storage Clipped file Output Amazon DynamoDB Database AWS Lambda Serverless Lambda function queries database for metadata being searched Lambda function creates MediaConvert transcode job specifying time(s) from source to clip
  • 41. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. MediaConvert Input Clipping Configuration
  • 42. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. AWS Media Analysis Solution https://aws.amazon.com/answers/media-entertainment/media-analysis-solution/ • Generate searchable metadata from your media assets using Amazon Rekognition, Amazon Transcribe, Amazon Comprehend, and Amazon Elasticsearch Service • Deploy in minutes with a single click using AWS CloudFormation • Interact via API or demo web UI • Orchestrated with Step Functions, extensible and easily customizable
  • 43. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Thanks! Please complete the session survey in the mobile app. samisb@amazon.com
  • 44. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Submit session feedback 1. Tap the Schedule icon. 2. Select the session you attended. 3. Tap Session Evaluation to submit your feedback.