AWS Rekognition - PPE Detection

DETECT PERSONAL PROTECTIVE EQUIPMENT ==============================

ACTION DESCRIPTION
--------------------------------
DETECT PERSONAL PROTECTIVE EQUIPMENT detects to help determine if workers on a construction site are wearing head covers, or if medical workers are wearing face covers and hand covers.

STEP-BY-STEP SETUP
--------------------------------
The steps from 0) to 1) can be automatically performed by using this deployment template:
 https://console.aws.amazon.com/cloudformation/home?#/stacks/create/review?stackName=BubbleRekognitionSyncOnly&templateURL=https://bubble-resources.s3.amazonaws.com/deployment-assets/CloudFormation-AWSRekognitionSyncOnly.yaml

 You will find the required parameters values used across the plugin in the "OUTPUT" tab of the created stack.

 0) Sign-up for AWS REKOGNITION by following this link: https://console.aws.amazon.com/rekognition/home?p=rkn&cp=bn&ad=c

 1) Create your AWS REKOGNITION API KEY & SECRET and attach the AWS REKOGNITION READ ONLY or FULL ACCESS POLICY to DETECTPROTECTIVEEQUIPMENT API: https://docs.aws.amazon.com/general/latest/gr/aws-sec-cred-types.html#access-keys-and-secret-access-keys

 If you intend to use AWS S3 URI (s3://) with your own BUCKET, attach the AWS S3 READ ONLY policy to the considered BUCKET.

 2) Enter in the PLUGIN SETTINGS your AWS REKOGNITION API KEY & SECRET & AWS SERVICE ENDPOINT REGION (if not provided, the default endpoint is "us-east-1").

 3) Set up the action "DETECT PERSONAL PROTECTIVE EQUIPMENT" action in the workflow.

   Inputs Fields :
     - IMAGE : JPEG or PNG image from the Bubble.io uploader, or a Protocol-relative URLs (//server/file.ext), a HTTPS file URL (https://server/file.ext) or a AWS S3 URI (s3://bucket/image.jpg). For both Protocol-relative and HTTPS URL, the file must be accessible through HTTPS Protocol.
     - MIN CONFIDENCE : Specifies the minimum confidence level for the required equipment. Amazon Rekognition doesn't return any equipment with confidence lower than this specified value. Minimum value of 0. Maximum value of 100. Default value is 80 if not provided.
     - FACE COVER : Specifies Face Cover as a required equipment.
     - HAND COVER : Specifies Hand Cover as a required equipment.
     - HEAD COVER : Specifies Head Cover as a required equipment.
     - OUTPUT TYPE : Returned type, must always be set to "RESULT (REKOGNITION)".
   Output Fields :
     - RESULTS : Returns the list of 15 people maximum who properly wear the PPE's against the PPE's requirements you set, detected in the image, along with the parts of a body where the PPE is or is not properly worn, and the types of detected PPE's (face cover, hand cover, and head cover).

IMPLEMENTATION EXAMPLE
======================
Feel free to browse the app editor in the Service URL for an implementation example.

ADDITIONAL INFORMATION
======================
> DETECT PROTECTIVE EQUIPMENT details : https://docs.aws.amazon.com/rekognition/latest/dg/ppe-detection.html#ppe-confidence

> AWS REKOGNITION service limits : https://docs.aws.amazon.com/rekognition/latest/dg/limits.html
> AWS services availability per region : https://aws.amazon.com/about-aws/global-infrastructure/regional-product-services/
> AWS Service endpoints list : https://docs.aws.amazon.com/general/latest/gr/rande.html

TROUBLESHOOTING
================
Any plugin related error will be posted to the the Logs tab, "Server logs" section of your App Editor.
 Make sure that "Plugin server side output" and "Plugin server side output" is selected in "Show Advanced".

> Server Logs Details: https://manual.bubble.io/core-resources/bubbles-interface/logs-tab#server-logs

PERFORMANCE CONSIDERATIONS
===========================

GENERAL
-------------
 This implementation posts the file data to AWS for non-AWS Storage URI (e.g: non-s3://).
 Therefore, the maximum allowable file size depends both on the bandwidth between Bubble.io & AWS, the highest limit being capped by Bubble.io's Workflow Action maximum execution time to perform this transfer operation.


QUESTIONS ?
===========
Contact us at bubble@wiseable.io for any additional feature you would require or support question.