Skip to content

ggiallo28/raspberry-rekognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

2 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Raspberry Rekognition

Prerequisiti:

  • account aws
  • python pip
  • ansible
  • boto

Questo lavoro si ispira al blog post https://amzn.to/2RiUmwo .

Esecuzione

  1. Installare: https://github.com/awslabs/amazon-kinesis-video-streams-producer-sdk-cpp

  2. Creare le Access Key per la tua utenza e settarle usando aws_configure --profile <profile_name>

  3. Create un bucket S3.

  4. Esecuzione dei comandi:

    • aws cloudformation package --template-file raspberry-workshop.yml --output-template-file raspberry-workshop.out.yml --s3-bucket <bucket_name> --region --profile <profile_name>*
    • aws cloudformation deploy --template-file <path_to_raspberry-workshop.out.yml> --stack-name rekognition-workshop --capabilities CAPABILITY_NAMED_IAM --profile <profile_name>*
  5. Andare su Cloud Formation e copiare Kinesis Data Stream ARN.

  6. Creare un Kinesis Video Stream, e copiate ARN.

  7. Creare una Collection in Rekognition:

    • aws rekognition create-collection --collection-id <collection_id> --profile <profile_name>*
  8. Modificare streaming/main.yaml e settare le variabili

    • video_stream_arn: # vedi step precedenti
    • data_stream_arn: # vedi step precedenti
    • collection_id: # nome della collection in rekognition
    • profile: # nome del profilo aws <profile_name>
  9. Modificare IP in streaming/inventory e settarlo pari all'ip della vostra raspberry

  10. Lanciare Playbook Ansible

    • ansible-playbook streaming/main.yaml --ask-pass *
  11. Lanciare python ./polly/main.py

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages