SlideShare a Scribd company logo
1 of 48
Download to read offline
© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved.
Paul Armstrong
Principal Solutions Architect, Amazon Web Services
Using AWS to Ingest, Store, Archive,
Share and carry out Analysis of Video
Content
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Streaming
Amazon Kinesis
Analytics
KCL
Apps
AWS Lambda
COLLECT STORE CONSUMEPROCESS/ANALYZE
Amazon ES
Apache Kafka
Amazon Kinesis
Streams
Amazon Kinesis
Firehose
Amazon
DynamoDB
Amazon ElastiCache
Amazon RDS
Amazon Aurora
HotHotWarm
Fast
Stream
SQLNoSQLCacheFileStream
Mobile apps
Web apps
Devices
Sensors
IoT platforms
AWS IoT
Data centers AWS Direct
Connect
Migration
Snowball
Logging
Amazon
CloudWatch
AWS
CloudTrail
RECORDS
FILES
STREAMS
Amazon
QuickSight
Analysis&visualizationDataSceince
DataTransport&LoggingIoTApplications
Amazon EMR
Amazon Redshift
& Spectrum
Presto
Amazon
EMR
FastSlow
Amazon Athena
BatchInteractivePredictive
AmazonAI
Amazon S3
Amazon DAX
Import/export
Lex PollyAML Rekognition
AWS DL AMI
AI Apps
Amazon ECS
Apps
Model
Train/
Eval
Models
Deploy
ETL
AWS Greengrass
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Building a video ingestion system is complex
• Cumbersome to rewrite code for various devices and development
environments
• Difficult to elastically scale to millions of devices
• Requires support for cadence, latency, and jitter on streams
• Requires secure, highly scalable, available storage
• Need easy-to-use APIs to retrieve, process, and replay video
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Stream video from millions of devices
Easily build vision-enabled apps
Secure
Durable, searchable storage
Fully managed
Amazon Kinesis Video Streams
S t r e a m v i d e o a n d t i m e - e n c o d e d d a t a f o r a n a l y t i c s
Amazon AI
Services
Apache MxNet
TensorFlow
Custom Video
Processing
3rd Party
Partners
Kinesis
Video
Streams
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Kinesis Video Streams Concept
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
• Flexible SDK for integration with on-
device hardware media pipelines
• Out-of-the-box integration with AWS
auth mechanism: SigV4
• Flexible Put API to stream Frames or
buffered Fragments or after-the-fact
uploads
• Build custom integrations with diverse
camera and device types
• Secure authN and authZ to connect
devices w/ image sensors to AWS
• Stream video data based on the
preferred transmission scenario
Video Streams SDK offers … … that enables developers to
Kinesis Video Streams Producer SDK
Easily connect and stream from camera sources
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Ingestion Options
Camera with sdk directly to Stream e.g. Partner cameras
Camera to stream to proxy e.g. IP Camera
Camera at the edge e.g. Deep Lens
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Kinesis Video Streams
• Kinesis Video Stream:
• Customer-owned entity that transports video-like data such as frames,
samples, and fragments
• Stores durably, and makes it available for both real-time and ad hoc
consumption.
• Kinesis Video Stream only has a single producer publishing data into it.
• Producer:
• Producers put data into Kinesis Video Streams, and include hardware devices
like security cameras, body-worn cams, smartphones, dashcams, etc.
• A single producer can generate one or more Kinesis Video Streams
• Consumer:
• Consumers are applications that get data from Streams to process.
• Consumers get data in real-time/continuous or in batch-oriented path
• Consumers run on the customers own Amazon EC2 instances.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
View Video Archive
• Ingest from existing Camera using Producer to put on stream, for long term
storage and archive retrieval
• User request footage from HTML
• Search for start time in stream and duration
• Store extracted footage on S3 with a pre-signed URL to securely share with 3rd
parties
Producer SDK
Video Stream
userAmazon API
Gateway
GetFrame
Lambda
function
S3
Search for Stream
Footage
Share with 3rd Parties
Amazon
Cognito
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
View Video Archive
List the Streams to
Select Footage from
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
View Video Archive
Pass the Time and
Duration to the
Stream
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
View Video Archive
Store the fragments
in S3 and return pre-
signed URL
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition
Extract rich metadata from visual content
Object and Scene
Detection
Facial
Analysis
Face
Comparison
Facial
Recognition
Celebrity
Recognition
Image
Moderation
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
https://console.aws.amazon.com/rekognition/hom
e
© 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.
Automating Footage Tagging with
Amazon Rekognition
Solution Architecture
EncodersStills
Extraction &
FeedsResults
Cache
Bucket
R3
Amazon
Rekognition
users
Stills
Frames
SQS
Trigger
1
2
3
4
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Rekognition from HTML Client Demo
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Data Ingestion
• Ingest from Mac Camera
• Take a snapshot
• Query Amazon Rekognition – detectfaces
• Query Amazon Rekognition Collection – searchfacesbyImage
Amazon
Rekognition
Image
Collection
Extract meta-data for the image
Validate image matches with
stored image
Amazon
Cognito
HTML
Unauthenticated
identity
<scripttype="text/javascript"src="https://s3.amazonaws.com/.../jpeg_camera_update.js"></script>
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Rekognition APIs – example
Detect labels using
ML model
Rekognition
returns meta-
data about image
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Rekognition APIs – example
Match against image
collection using ML
models
Confidence on
Match?
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Rekognition APIs – Advanced Usage
Decision trees and processing pipelines
Why?
• Many use cases require more than a single operation to arrive
at actionable data
How?
• S3 event notifications, Lambda, Step Functions
• DynamoDB for persistent pipeline storage
• Augmenting results with 3rd Party AI/ML
• OpenCV, MXNet, etc. on EC2 Spot, ECS, AI/ML AMI
Sample Use Cases
• Person of interest near a celebrity
• Multi-pass motion detection enhancement
• Subjects leaving a location without possessions
IndexFaces
DetectLabels
“person”
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
aws rekognition recognize-celebrities –image “S3Object={Bucket=mybucket,Name=cam.jpg}”
aws rekognition search-faces-by-image –image “S3Object={Bucket=mybucket,Name=cam.jpg}” 
--collection-id “persons-of-interest"
aws rekognition create-collection --collection-id “persons-of-interest”
aws rekognition index-faces --image “S3Object={Bucket=mybucket,Name=subject.jpg}” 
--collection-id “persons-of-interest”
Rekognition APIs – Advanced Usage
{
"FaceMatches": [
{"Face": {"BoundingB
"Height":
0.2683333456516266,
"Left":
0.5099999904632568,
"Top":
0.1783333271741867,
"Width":
0.17888888716697693},
"
CompareFaces
DetectFaces
DetectLabels
DetectModerationLabels
GetCelebrityInfo
RecognizeCelebrities
2
{
"FaceMatches": [
{"Face": {"BoundingB
"Height":
0.2683333456516266,
"Left":
0.5099999904632568,
"Top":
0.1783333271741867,
"Width":
0.17888888716697693},
"
CreateCollection
DeleteCollection
DeleteFaces
IndexFaces
ListCollections
SearchFaces
SearchFacesByImage
ListFaces
3
1
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition Video
Features
Detects objects,
activities, scenes.
Label name,
timestamp,
confidence
Detects and analyzes
faces. Timestamp,
face bounding box,
age range, emotion,
gender, pose …
Search video for
matches in a face
collection.
Timestamp, person &
face bounding boxes,
matched face IDs,
similarity % …
Detects and tracks
unique people,
including occlusions
and shot changes,
Persona and Face
bounding box,
person ID
Recognizes
celebrities
throughout video.
Celebrity name,
bounding box,
confidence %
Detects nudity and
explicit nudity.
Timestamp,
confidence, label
name.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition Video Streams
• CCTV for building entry
• Ensure workers on a building
site are registered and known.
• Foreign object detection on a
runway
• Trespassing on railway track
• Customer personalization
• Looking for celebrities in your
street
• Working out who’s at the
front door
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Amazon Rekognition Video
Who’s at the front door?
Producer
Application
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Requirements for your application code
• Producer Application
• Any video data generating device
• Streaming media data in real time
• Streaming media data after buffering it for a few seconds
• Streaming after-the-fact media uploads
• Kinesis Video Streams Producer Libraries and SDK
• Java
• Android
• C++
• Consumer Application
• Lambda function - python
• Triggered by the data arriving on the Kinesis Data Stream
• Remember data flow is Camera > Kinesis Video Stream > Rekognition Data Processor > Kinesis Data
Stream
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Detecting Faces at the Edge Demo
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
AWS DeepLens
• A deep-learning enabled HD video camera
• Compute capable of running sophisticated deep
learning computer vision models in real time on the
device.
• Perform inference at the edge
• Trigger a lambda function when an action takes place
• Apply more advanced analytics on the cloud
• Amazon Kinesis Video Streams
• Amazon Rekognition video
CPU
Intel Atom® Processor
MEMORY
8GB RAM
OS
Ubuntu OS-16.04 LTS
BUILT-IN STORAGE
16GB Memory (expandable)
GRAPHICS
Intel Gen9 Graphics Engine
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Face Detection
user
Amazon API
Gateway
S3
Kinesis Data
Stream
deeplens-
processor
deeplens_viewer
Search_faces
_by_image
detect_faces
Cropped
faces
DeepLens
Viewer
Matched Faces
In Collection
Amazon ES
Amazon Kinesis
Firehose
DeepLensDetected
Faces
Amazon
Rekognition
Get
Sentiment of
all detected
faces
DeepLensDetected
FacesData
Presented
Image Store
Deeplens_upload.py
Upload Images to
Rekognition Collection, meta
store and image store using
json template
AWS
Greengrass
Face
detection
DeepLens
SSD
+ResNet
Model
Display
Detected
Images and
Meta data
Display Time
Series of
Emotions
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
What happens on the device?
Load Model to GPU
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
What happens on the device?
Resize captured
frame, doinference
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
What happens on the device?
Resize captured
frame with a border
Crop just the face,
send to Kinesis data
stream
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
What happens on the device?
Add the framing box
to the detected face
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Storing meta data and the Image Collection
json file, with meta
data and location of
image to display
Process json, resize
images
Add image to
rekognition
collection
Deeplens_upload.py
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Storing meta data and the Image Collection
Store meta data in
DynamoDB table
Deeplens_upload.py
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Processing Detected Faces
Process Images
from Kinesis stream
and match with
collection
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Processing Detected Faces
Get Sentiment from
detected faces and
send by Firehose to
ElasticSearch
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Processing Detected Faces
Stored detected
image ids in the
collection in
DynamoDB
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Detected Faces Viewer
Query DynamoDB table
for detected faces in the
last 1 minute
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Detected Faces Viewer
For unique records
determine the
associated meta data
and image
Determine unique
images detected
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Detected Faces Viewer
Get smile url and return
json to html page
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Sentiment Analysis
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
What have we seen
Simple HTML
• Build a web page to process video content as snapshots
• Use Amazon Rekognition to analyze those images
Process live video
• Stream video through Amazon Kinesis Video Stream
• StreamProcessor interacts with Amazon Rekognition Video
• Support for Archive and Sharing of Video
Custom image processing at the edge
• Amazon DeepLens and your own machine learning model
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Further Links
Single Shot Multi Object Detection Inference Service
https://github.com/zhreshold/mxnet-ssd
Sagemaker
https://aws.amazon.com/sagemaker/
Image Classification Algorithm
https://docs.aws.amazon.com/sagemaker/latest/dg/image-classification.html
Kinesis Video Streams
https://aws.amazon.com/kinesis/video-streams/
DeepLens
https://aws.amazon.com/deeplens/
Amazon Elasticsearch service
https://aws.amazon.com/elasticsearch-service/
© 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
Please complete the session survey in the
summit mobile app.
Thank You
armpaul@amazon.co.uk
aws.amazon.com/blogs/machine-learning/

More Related Content

What's hot

Building a well-engaged and secure AWS account access management - FND207-R ...
 Building a well-engaged and secure AWS account access management - FND207-R ... Building a well-engaged and secure AWS account access management - FND207-R ...
Building a well-engaged and secure AWS account access management - FND207-R ...Amazon Web Services
 
AWS Tutorial | AWS Certified Solutions Architect | Amazon AWS | AWS Training ...
AWS Tutorial | AWS Certified Solutions Architect | Amazon AWS | AWS Training ...AWS Tutorial | AWS Certified Solutions Architect | Amazon AWS | AWS Training ...
AWS Tutorial | AWS Certified Solutions Architect | Amazon AWS | AWS Training ...Edureka!
 
Containers on AWS: An Introduction
Containers on AWS: An IntroductionContainers on AWS: An Introduction
Containers on AWS: An IntroductionAmazon Web Services
 
AWS 상의 컨테이너 서비스 소개 ECS, EKS - 이종립 / Principle Enterprise Evangelist @베스핀글로벌
AWS 상의 컨테이너 서비스 소개 ECS, EKS - 이종립 / Principle Enterprise Evangelist @베스핀글로벌AWS 상의 컨테이너 서비스 소개 ECS, EKS - 이종립 / Principle Enterprise Evangelist @베스핀글로벌
AWS 상의 컨테이너 서비스 소개 ECS, EKS - 이종립 / Principle Enterprise Evangelist @베스핀글로벌BESPIN GLOBAL
 
Cloud computing by Google Cloud Platform - Presentation
Cloud computing by Google Cloud Platform - PresentationCloud computing by Google Cloud Platform - Presentation
Cloud computing by Google Cloud Platform - PresentationTinarivosoaAbaniaina
 
Introduction to AWS Organizations
Introduction to AWS OrganizationsIntroduction to AWS Organizations
Introduction to AWS OrganizationsAmazon Web Services
 
Introduction To Amazon Web Services | AWS Tutorial for Beginners | AWS Traini...
Introduction To Amazon Web Services | AWS Tutorial for Beginners | AWS Traini...Introduction To Amazon Web Services | AWS Tutorial for Beginners | AWS Traini...
Introduction To Amazon Web Services | AWS Tutorial for Beginners | AWS Traini...Edureka!
 
Serverless Architecture
Serverless ArchitectureServerless Architecture
Serverless ArchitectureElana Krasner
 
AWS Security Week: AWS Secrets Manager
AWS Security Week: AWS Secrets ManagerAWS Security Week: AWS Secrets Manager
AWS Security Week: AWS Secrets ManagerAmazon Web Services
 
Introduction to the Well-Architected Framework and Tool - SVC208 - Anaheim AW...
Introduction to the Well-Architected Framework and Tool - SVC208 - Anaheim AW...Introduction to the Well-Architected Framework and Tool - SVC208 - Anaheim AW...
Introduction to the Well-Architected Framework and Tool - SVC208 - Anaheim AW...Amazon Web Services
 
AWS Landing Zone Deep Dive (ENT350-R2) - AWS re:Invent 2018
AWS Landing Zone Deep Dive (ENT350-R2) - AWS re:Invent 2018AWS Landing Zone Deep Dive (ENT350-R2) - AWS re:Invent 2018
AWS Landing Zone Deep Dive (ENT350-R2) - AWS re:Invent 2018Amazon Web Services
 
Overview of AWS by Andy Jassy - SVP, AWS
Overview of AWS by Andy Jassy - SVP, AWSOverview of AWS by Andy Jassy - SVP, AWS
Overview of AWS by Andy Jassy - SVP, AWSAmazon Web Services
 
 Introduction google cloud platform
 Introduction google cloud platform Introduction google cloud platform
 Introduction google cloud platformmarwa Ayad Mohamed
 
AWS Control Tower
AWS Control TowerAWS Control Tower
AWS Control TowerCloudHesive
 
Day 5 - AWS Autoscaling Master Class - The New Capacity Plan
Day 5 - AWS Autoscaling Master Class - The New Capacity PlanDay 5 - AWS Autoscaling Master Class - The New Capacity Plan
Day 5 - AWS Autoscaling Master Class - The New Capacity PlanAmazon Web Services
 
AWS Global Infrastructure Foundations
AWS Global Infrastructure Foundations AWS Global Infrastructure Foundations
AWS Global Infrastructure Foundations Amazon Web Services
 

What's hot (20)

Building a well-engaged and secure AWS account access management - FND207-R ...
 Building a well-engaged and secure AWS account access management - FND207-R ... Building a well-engaged and secure AWS account access management - FND207-R ...
Building a well-engaged and secure AWS account access management - FND207-R ...
 
AWS Security Best Practices
AWS Security Best PracticesAWS Security Best Practices
AWS Security Best Practices
 
AWS Tutorial | AWS Certified Solutions Architect | Amazon AWS | AWS Training ...
AWS Tutorial | AWS Certified Solutions Architect | Amazon AWS | AWS Training ...AWS Tutorial | AWS Certified Solutions Architect | Amazon AWS | AWS Training ...
AWS Tutorial | AWS Certified Solutions Architect | Amazon AWS | AWS Training ...
 
Containers on AWS: An Introduction
Containers on AWS: An IntroductionContainers on AWS: An Introduction
Containers on AWS: An Introduction
 
Cost Optimisation on AWS
Cost Optimisation on AWSCost Optimisation on AWS
Cost Optimisation on AWS
 
AWS 상의 컨테이너 서비스 소개 ECS, EKS - 이종립 / Principle Enterprise Evangelist @베스핀글로벌
AWS 상의 컨테이너 서비스 소개 ECS, EKS - 이종립 / Principle Enterprise Evangelist @베스핀글로벌AWS 상의 컨테이너 서비스 소개 ECS, EKS - 이종립 / Principle Enterprise Evangelist @베스핀글로벌
AWS 상의 컨테이너 서비스 소개 ECS, EKS - 이종립 / Principle Enterprise Evangelist @베스핀글로벌
 
Cloud computing by Google Cloud Platform - Presentation
Cloud computing by Google Cloud Platform - PresentationCloud computing by Google Cloud Platform - Presentation
Cloud computing by Google Cloud Platform - Presentation
 
Introduction to AWS Organizations
Introduction to AWS OrganizationsIntroduction to AWS Organizations
Introduction to AWS Organizations
 
AWS IAM Introduction
AWS IAM IntroductionAWS IAM Introduction
AWS IAM Introduction
 
Introduction To Amazon Web Services | AWS Tutorial for Beginners | AWS Traini...
Introduction To Amazon Web Services | AWS Tutorial for Beginners | AWS Traini...Introduction To Amazon Web Services | AWS Tutorial for Beginners | AWS Traini...
Introduction To Amazon Web Services | AWS Tutorial for Beginners | AWS Traini...
 
Serverless Architecture
Serverless ArchitectureServerless Architecture
Serverless Architecture
 
AWS Security Week: AWS Secrets Manager
AWS Security Week: AWS Secrets ManagerAWS Security Week: AWS Secrets Manager
AWS Security Week: AWS Secrets Manager
 
Introduction to the Well-Architected Framework and Tool - SVC208 - Anaheim AW...
Introduction to the Well-Architected Framework and Tool - SVC208 - Anaheim AW...Introduction to the Well-Architected Framework and Tool - SVC208 - Anaheim AW...
Introduction to the Well-Architected Framework and Tool - SVC208 - Anaheim AW...
 
AWS Landing Zone Deep Dive (ENT350-R2) - AWS re:Invent 2018
AWS Landing Zone Deep Dive (ENT350-R2) - AWS re:Invent 2018AWS Landing Zone Deep Dive (ENT350-R2) - AWS re:Invent 2018
AWS Landing Zone Deep Dive (ENT350-R2) - AWS re:Invent 2018
 
Overview of AWS by Andy Jassy - SVP, AWS
Overview of AWS by Andy Jassy - SVP, AWSOverview of AWS by Andy Jassy - SVP, AWS
Overview of AWS by Andy Jassy - SVP, AWS
 
 Introduction google cloud platform
 Introduction google cloud platform Introduction google cloud platform
 Introduction google cloud platform
 
AWS Control Tower
AWS Control TowerAWS Control Tower
AWS Control Tower
 
AWS Simple Storage Service (s3)
AWS Simple Storage Service (s3) AWS Simple Storage Service (s3)
AWS Simple Storage Service (s3)
 
Day 5 - AWS Autoscaling Master Class - The New Capacity Plan
Day 5 - AWS Autoscaling Master Class - The New Capacity PlanDay 5 - AWS Autoscaling Master Class - The New Capacity Plan
Day 5 - AWS Autoscaling Master Class - The New Capacity Plan
 
AWS Global Infrastructure Foundations
AWS Global Infrastructure Foundations AWS Global Infrastructure Foundations
AWS Global Infrastructure Foundations
 

Similar to Using AWS to Ingest, Store, Archive, Share and carry out Analysis of Video Content.pdf

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
 
Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...
Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...
Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...Amazon Web Services
 
Deep Dive on Amazon Elastic Container Service (ECS) I AWS Dev Day 2018
Deep Dive on Amazon Elastic Container Service (ECS) I AWS Dev Day 2018Deep Dive on Amazon Elastic Container Service (ECS) I AWS Dev Day 2018
Deep Dive on Amazon Elastic Container Service (ECS) I AWS Dev Day 2018AWS Germany
 
Identity Round Robin Workshop - Serverless Round: Security Week at the SF Loft
Identity Round Robin Workshop - Serverless Round: Security Week at the SF LoftIdentity Round Robin Workshop - Serverless Round: Security Week at the SF Loft
Identity Round Robin Workshop - Serverless Round: Security Week at the SF LoftAmazon Web Services
 
Serverless Development Deep Dive
Serverless Development Deep DiveServerless Development Deep Dive
Serverless Development Deep DiveAmazon 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
 
Build a Social News App with Android and AWS (MOB307) - AWS re:Invent 2018
Build a Social News App with Android and AWS (MOB307) - AWS re:Invent 2018Build a Social News App with Android and AWS (MOB307) - AWS re:Invent 2018
Build a Social News App with Android and AWS (MOB307) - AWS re:Invent 2018Amazon Web Services
 
Control for Your Cloud Environment Using AWS Management Tools (ENT226-R1) - A...
Control for Your Cloud Environment Using AWS Management Tools (ENT226-R1) - A...Control for Your Cloud Environment Using AWS Management Tools (ENT226-R1) - A...
Control for Your Cloud Environment Using AWS Management Tools (ENT226-R1) - A...Amazon Web Services
 
Serverless Architectural Patterns
Serverless Architectural PatternsServerless Architectural Patterns
Serverless Architectural PatternsAmazon 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
 
Increase the Value of Video with ML & Media Services - SRV322 - Toronto AWS S...
Increase the Value of Video with ML & Media Services - SRV322 - Toronto AWS S...Increase the Value of Video with ML & Media Services - SRV322 - Toronto AWS S...
Increase the Value of Video with ML & Media Services - SRV322 - Toronto AWS S...Amazon Web Services
 
Increase the Value of Video with ML & Media Services - SRV322 - Chicago AWS S...
Increase the Value of Video with ML & Media Services - SRV322 - Chicago AWS S...Increase the Value of Video with ML & Media Services - SRV322 - Chicago AWS S...
Increase the Value of Video with ML & Media Services - SRV322 - Chicago AWS S...Amazon Web Services
 
Deep Dive - AWS Security by Design
Deep Dive - AWS Security by DesignDeep Dive - AWS Security by Design
Deep Dive - AWS Security by DesignAmazon Web Services
 
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...Amazon Web Services
 
Data Lake Patterns for Voice, Vision, Advanced Analytics, & ML Using Serverle...
Data Lake Patterns for Voice, Vision, Advanced Analytics, & ML Using Serverle...Data Lake Patterns for Voice, Vision, Advanced Analytics, & ML Using Serverle...
Data Lake Patterns for Voice, Vision, Advanced Analytics, & ML Using Serverle...Amazon Web Services
 
AWS18_StartupDayToronto_SecuringYourCustomersDataFromDayOne
AWS18_StartupDayToronto_SecuringYourCustomersDataFromDayOneAWS18_StartupDayToronto_SecuringYourCustomersDataFromDayOne
AWS18_StartupDayToronto_SecuringYourCustomersDataFromDayOneAmazon Web Services
 
SecuringYourCustomersDataFromDayOne_SFStartupDay
SecuringYourCustomersDataFromDayOne_SFStartupDaySecuringYourCustomersDataFromDayOne_SFStartupDay
SecuringYourCustomersDataFromDayOne_SFStartupDayAmazon Web Services
 
WildRydes Serverless Data Processing Workshop
WildRydes Serverless Data Processing WorkshopWildRydes Serverless Data Processing Workshop
WildRydes Serverless Data Processing WorkshopAmazon Web Services
 
Getting Started with Serverless Architectures
Getting Started with Serverless ArchitecturesGetting Started with Serverless Architectures
Getting Started with Serverless ArchitecturesAmazon Web Services
 
Increase the Value of Video with ML & Media Services - SRV322 - Anaheim AWS S...
Increase the Value of Video with ML & Media Services - SRV322 - Anaheim AWS S...Increase the Value of Video with ML & Media Services - SRV322 - Anaheim AWS S...
Increase the Value of Video with ML & Media Services - SRV322 - Anaheim AWS S...Amazon Web Services
 

Similar to Using AWS to Ingest, Store, Archive, Share and carry out Analysis of Video Content.pdf (20)

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
 
Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...
Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...
Serverless Architectural Patterns and Best Practices (ARC305-R2) - AWS re:Inv...
 
Deep Dive on Amazon Elastic Container Service (ECS) I AWS Dev Day 2018
Deep Dive on Amazon Elastic Container Service (ECS) I AWS Dev Day 2018Deep Dive on Amazon Elastic Container Service (ECS) I AWS Dev Day 2018
Deep Dive on Amazon Elastic Container Service (ECS) I AWS Dev Day 2018
 
Identity Round Robin Workshop - Serverless Round: Security Week at the SF Loft
Identity Round Robin Workshop - Serverless Round: Security Week at the SF LoftIdentity Round Robin Workshop - Serverless Round: Security Week at the SF Loft
Identity Round Robin Workshop - Serverless Round: Security Week at the SF Loft
 
Serverless Development Deep Dive
Serverless Development Deep DiveServerless Development Deep Dive
Serverless Development Deep Dive
 
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...
 
Build a Social News App with Android and AWS (MOB307) - AWS re:Invent 2018
Build a Social News App with Android and AWS (MOB307) - AWS re:Invent 2018Build a Social News App with Android and AWS (MOB307) - AWS re:Invent 2018
Build a Social News App with Android and AWS (MOB307) - AWS re:Invent 2018
 
Control for Your Cloud Environment Using AWS Management Tools (ENT226-R1) - A...
Control for Your Cloud Environment Using AWS Management Tools (ENT226-R1) - A...Control for Your Cloud Environment Using AWS Management Tools (ENT226-R1) - A...
Control for Your Cloud Environment Using AWS Management Tools (ENT226-R1) - A...
 
Serverless Architectural Patterns
Serverless Architectural PatternsServerless Architectural Patterns
Serverless Architectural Patterns
 
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
 
Increase the Value of Video with ML & Media Services - SRV322 - Toronto AWS S...
Increase the Value of Video with ML & Media Services - SRV322 - Toronto AWS S...Increase the Value of Video with ML & Media Services - SRV322 - Toronto AWS S...
Increase the Value of Video with ML & Media Services - SRV322 - Toronto AWS S...
 
Increase the Value of Video with ML & Media Services - SRV322 - Chicago AWS S...
Increase the Value of Video with ML & Media Services - SRV322 - Chicago AWS S...Increase the Value of Video with ML & Media Services - SRV322 - Chicago AWS S...
Increase the Value of Video with ML & Media Services - SRV322 - Chicago AWS S...
 
Deep Dive - AWS Security by Design
Deep Dive - AWS Security by DesignDeep Dive - AWS Security by Design
Deep Dive - AWS Security by Design
 
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
Get Started with Deep Learning and Computer Vision Using AWS DeepLens (AIM316...
 
Data Lake Patterns for Voice, Vision, Advanced Analytics, & ML Using Serverle...
Data Lake Patterns for Voice, Vision, Advanced Analytics, & ML Using Serverle...Data Lake Patterns for Voice, Vision, Advanced Analytics, & ML Using Serverle...
Data Lake Patterns for Voice, Vision, Advanced Analytics, & ML Using Serverle...
 
AWS18_StartupDayToronto_SecuringYourCustomersDataFromDayOne
AWS18_StartupDayToronto_SecuringYourCustomersDataFromDayOneAWS18_StartupDayToronto_SecuringYourCustomersDataFromDayOne
AWS18_StartupDayToronto_SecuringYourCustomersDataFromDayOne
 
SecuringYourCustomersDataFromDayOne_SFStartupDay
SecuringYourCustomersDataFromDayOne_SFStartupDaySecuringYourCustomersDataFromDayOne_SFStartupDay
SecuringYourCustomersDataFromDayOne_SFStartupDay
 
WildRydes Serverless Data Processing Workshop
WildRydes Serverless Data Processing WorkshopWildRydes Serverless Data Processing Workshop
WildRydes Serverless Data Processing Workshop
 
Getting Started with Serverless Architectures
Getting Started with Serverless ArchitecturesGetting Started with Serverless Architectures
Getting Started with Serverless Architectures
 
Increase the Value of Video with ML & Media Services - SRV322 - Anaheim AWS S...
Increase the Value of Video with ML & Media Services - SRV322 - Anaheim AWS S...Increase the Value of Video with ML & Media Services - SRV322 - Anaheim AWS S...
Increase the Value of Video with ML & Media Services - SRV322 - Anaheim AWS S...
 

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
 

Using AWS to Ingest, Store, Archive, Share and carry out Analysis of Video Content.pdf

  • 1. © 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Paul Armstrong Principal Solutions Architect, Amazon Web Services Using AWS to Ingest, Store, Archive, Share and carry out Analysis of Video Content
  • 2. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Streaming Amazon Kinesis Analytics KCL Apps AWS Lambda COLLECT STORE CONSUMEPROCESS/ANALYZE Amazon ES Apache Kafka Amazon Kinesis Streams Amazon Kinesis Firehose Amazon DynamoDB Amazon ElastiCache Amazon RDS Amazon Aurora HotHotWarm Fast Stream SQLNoSQLCacheFileStream Mobile apps Web apps Devices Sensors IoT platforms AWS IoT Data centers AWS Direct Connect Migration Snowball Logging Amazon CloudWatch AWS CloudTrail RECORDS FILES STREAMS Amazon QuickSight Analysis&visualizationDataSceince DataTransport&LoggingIoTApplications Amazon EMR Amazon Redshift & Spectrum Presto Amazon EMR FastSlow Amazon Athena BatchInteractivePredictive AmazonAI Amazon S3 Amazon DAX Import/export Lex PollyAML Rekognition AWS DL AMI AI Apps Amazon ECS Apps Model Train/ Eval Models Deploy ETL AWS Greengrass
  • 3. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Building a video ingestion system is complex • Cumbersome to rewrite code for various devices and development environments • Difficult to elastically scale to millions of devices • Requires support for cadence, latency, and jitter on streams • Requires secure, highly scalable, available storage • Need easy-to-use APIs to retrieve, process, and replay video
  • 4. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Stream video from millions of devices Easily build vision-enabled apps Secure Durable, searchable storage Fully managed Amazon Kinesis Video Streams S t r e a m v i d e o a n d t i m e - e n c o d e d d a t a f o r a n a l y t i c s Amazon AI Services Apache MxNet TensorFlow Custom Video Processing 3rd Party Partners Kinesis Video Streams
  • 5. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Kinesis Video Streams Concept
  • 6. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. • Flexible SDK for integration with on- device hardware media pipelines • Out-of-the-box integration with AWS auth mechanism: SigV4 • Flexible Put API to stream Frames or buffered Fragments or after-the-fact uploads • Build custom integrations with diverse camera and device types • Secure authN and authZ to connect devices w/ image sensors to AWS • Stream video data based on the preferred transmission scenario Video Streams SDK offers … … that enables developers to Kinesis Video Streams Producer SDK Easily connect and stream from camera sources
  • 7. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Ingestion Options Camera with sdk directly to Stream e.g. Partner cameras Camera to stream to proxy e.g. IP Camera Camera at the edge e.g. Deep Lens
  • 8. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Kinesis Video Streams • Kinesis Video Stream: • Customer-owned entity that transports video-like data such as frames, samples, and fragments • Stores durably, and makes it available for both real-time and ad hoc consumption. • Kinesis Video Stream only has a single producer publishing data into it. • Producer: • Producers put data into Kinesis Video Streams, and include hardware devices like security cameras, body-worn cams, smartphones, dashcams, etc. • A single producer can generate one or more Kinesis Video Streams • Consumer: • Consumers are applications that get data from Streams to process. • Consumers get data in real-time/continuous or in batch-oriented path • Consumers run on the customers own Amazon EC2 instances.
  • 9. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. View Video Archive • Ingest from existing Camera using Producer to put on stream, for long term storage and archive retrieval • User request footage from HTML • Search for start time in stream and duration • Store extracted footage on S3 with a pre-signed URL to securely share with 3rd parties Producer SDK Video Stream userAmazon API Gateway GetFrame Lambda function S3 Search for Stream Footage Share with 3rd Parties Amazon Cognito
  • 10. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. View Video Archive List the Streams to Select Footage from
  • 11. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. View Video Archive Pass the Time and Duration to the Stream
  • 12. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. View Video Archive Store the fragments in S3 and return pre- signed URL
  • 13. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition Extract rich metadata from visual content Object and Scene Detection Facial Analysis Face Comparison Facial Recognition Celebrity Recognition Image Moderation
  • 14. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. https://console.aws.amazon.com/rekognition/hom e
  • 15. © 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
  • 16. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Automating Footage Tagging with Amazon Rekognition Solution Architecture EncodersStills Extraction & FeedsResults Cache Bucket R3 Amazon Rekognition users Stills Frames SQS Trigger 1 2 3 4
  • 17. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Rekognition from HTML Client Demo
  • 18. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Data Ingestion • Ingest from Mac Camera • Take a snapshot • Query Amazon Rekognition – detectfaces • Query Amazon Rekognition Collection – searchfacesbyImage Amazon Rekognition Image Collection Extract meta-data for the image Validate image matches with stored image Amazon Cognito HTML Unauthenticated identity <scripttype="text/javascript"src="https://s3.amazonaws.com/.../jpeg_camera_update.js"></script>
  • 19. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Rekognition APIs – example Detect labels using ML model Rekognition returns meta- data about image
  • 20. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Rekognition APIs – example Match against image collection using ML models Confidence on Match?
  • 21. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Rekognition APIs – Advanced Usage Decision trees and processing pipelines Why? • Many use cases require more than a single operation to arrive at actionable data How? • S3 event notifications, Lambda, Step Functions • DynamoDB for persistent pipeline storage • Augmenting results with 3rd Party AI/ML • OpenCV, MXNet, etc. on EC2 Spot, ECS, AI/ML AMI Sample Use Cases • Person of interest near a celebrity • Multi-pass motion detection enhancement • Subjects leaving a location without possessions IndexFaces DetectLabels “person”
  • 22. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. aws rekognition recognize-celebrities –image “S3Object={Bucket=mybucket,Name=cam.jpg}” aws rekognition search-faces-by-image –image “S3Object={Bucket=mybucket,Name=cam.jpg}” --collection-id “persons-of-interest" aws rekognition create-collection --collection-id “persons-of-interest” aws rekognition index-faces --image “S3Object={Bucket=mybucket,Name=subject.jpg}” --collection-id “persons-of-interest” Rekognition APIs – Advanced Usage { "FaceMatches": [ {"Face": {"BoundingB "Height": 0.2683333456516266, "Left": 0.5099999904632568, "Top": 0.1783333271741867, "Width": 0.17888888716697693}, " CompareFaces DetectFaces DetectLabels DetectModerationLabels GetCelebrityInfo RecognizeCelebrities 2 { "FaceMatches": [ {"Face": {"BoundingB "Height": 0.2683333456516266, "Left": 0.5099999904632568, "Top": 0.1783333271741867, "Width": 0.17888888716697693}, " CreateCollection DeleteCollection DeleteFaces IndexFaces ListCollections SearchFaces SearchFacesByImage ListFaces 3 1
  • 23. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition Video Features Detects objects, activities, scenes. Label name, timestamp, confidence Detects and analyzes faces. Timestamp, face bounding box, age range, emotion, gender, pose … Search video for matches in a face collection. Timestamp, person & face bounding boxes, matched face IDs, similarity % … Detects and tracks unique people, including occlusions and shot changes, Persona and Face bounding box, person ID Recognizes celebrities throughout video. Celebrity name, bounding box, confidence % Detects nudity and explicit nudity. Timestamp, confidence, label name.
  • 24. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 25. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition Video Streams • CCTV for building entry • Ensure workers on a building site are registered and known. • Foreign object detection on a runway • Trespassing on railway track • Customer personalization • Looking for celebrities in your street • Working out who’s at the front door
  • 26. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Amazon Rekognition Video Who’s at the front door? Producer Application
  • 27. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved.
  • 28. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Requirements for your application code • Producer Application • Any video data generating device • Streaming media data in real time • Streaming media data after buffering it for a few seconds • Streaming after-the-fact media uploads • Kinesis Video Streams Producer Libraries and SDK • Java • Android • C++ • Consumer Application • Lambda function - python • Triggered by the data arriving on the Kinesis Data Stream • Remember data flow is Camera > Kinesis Video Stream > Rekognition Data Processor > Kinesis Data Stream
  • 29. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Detecting Faces at the Edge Demo
  • 30. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. AWS DeepLens • A deep-learning enabled HD video camera • Compute capable of running sophisticated deep learning computer vision models in real time on the device. • Perform inference at the edge • Trigger a lambda function when an action takes place • Apply more advanced analytics on the cloud • Amazon Kinesis Video Streams • Amazon Rekognition video CPU Intel Atom® Processor MEMORY 8GB RAM OS Ubuntu OS-16.04 LTS BUILT-IN STORAGE 16GB Memory (expandable) GRAPHICS Intel Gen9 Graphics Engine
  • 31. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Face Detection user Amazon API Gateway S3 Kinesis Data Stream deeplens- processor deeplens_viewer Search_faces _by_image detect_faces Cropped faces DeepLens Viewer Matched Faces In Collection Amazon ES Amazon Kinesis Firehose DeepLensDetected Faces Amazon Rekognition Get Sentiment of all detected faces DeepLensDetected FacesData Presented Image Store Deeplens_upload.py Upload Images to Rekognition Collection, meta store and image store using json template AWS Greengrass Face detection DeepLens SSD +ResNet Model Display Detected Images and Meta data Display Time Series of Emotions
  • 32. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. What happens on the device? Load Model to GPU
  • 33. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. What happens on the device? Resize captured frame, doinference
  • 34. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. What happens on the device? Resize captured frame with a border Crop just the face, send to Kinesis data stream
  • 35. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. What happens on the device? Add the framing box to the detected face
  • 36. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Storing meta data and the Image Collection json file, with meta data and location of image to display Process json, resize images Add image to rekognition collection Deeplens_upload.py
  • 37. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Storing meta data and the Image Collection Store meta data in DynamoDB table Deeplens_upload.py
  • 38. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Processing Detected Faces Process Images from Kinesis stream and match with collection
  • 39. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Processing Detected Faces Get Sentiment from detected faces and send by Firehose to ElasticSearch
  • 40. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Processing Detected Faces Stored detected image ids in the collection in DynamoDB
  • 41. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Detected Faces Viewer Query DynamoDB table for detected faces in the last 1 minute
  • 42. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Detected Faces Viewer For unique records determine the associated meta data and image Determine unique images detected
  • 43. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Detected Faces Viewer Get smile url and return json to html page
  • 44. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Sentiment Analysis
  • 45. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. What have we seen Simple HTML • Build a web page to process video content as snapshots • Use Amazon Rekognition to analyze those images Process live video • Stream video through Amazon Kinesis Video Stream • StreamProcessor interacts with Amazon Rekognition Video • Support for Archive and Sharing of Video Custom image processing at the edge • Amazon DeepLens and your own machine learning model
  • 46. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Further Links Single Shot Multi Object Detection Inference Service https://github.com/zhreshold/mxnet-ssd Sagemaker https://aws.amazon.com/sagemaker/ Image Classification Algorithm https://docs.aws.amazon.com/sagemaker/latest/dg/image-classification.html Kinesis Video Streams https://aws.amazon.com/kinesis/video-streams/ DeepLens https://aws.amazon.com/deeplens/ Amazon Elasticsearch service https://aws.amazon.com/elasticsearch-service/
  • 47. © 2018, Amazon Web Services, Inc. or its affiliates. All rights reserved. Please complete the session survey in the summit mobile app.