Description

AWS Amazon Rekognition Video – Deep Learning Video Recognition Service

 

Description:

Amazon Rekognition Video is a machine learning powered video analysis service that detects objects, scenes, celebrities, text, activities, and any inappropriate content from your videos stored in Amazon S3. Rekognition Video also provides highly accurate facial analysis and facial search capabilities to detect, analyze, and compare faces.

Each result or detection is paired with a timestamp so that you can easily create an index for detailed video search, or navigate quickly to an interesting part of the video for further analysis. For objects, faces, text, and people, Rekognition Video also returns bounding box coordinates, which is the specific location of the detection in the frame.

NOTE: For Webcam Analysis demo, remove Envato frame

Benefits of Amazon Rekognition Video:

1. Deep Learning Technology
2. No Machine Learning expertise required
3. Provides highly accurate facial search capabilities
4. Identify thousands of objects and scenes
5. Identify potentially unsafe or inappropriate content
6. Read text in the video
7. Quickly identify well known people in the image
8. Identify products, landmarks and brands
9. Detect up to 100 faces in a frame
10. Analyze videos up to 6 hours
11. Analyze videos up to 10GB in size
12. Supports MPEG-4 and MOV formats
13. Up to 20 concurrent Jobs supported
14. “Pay as you go” payment model
15. Easy to customize

 

Cost of Running Amazon Rekognition – video Recognition Service:

• You can use any hosting platform as you prefer for the application itself
• AWS Account (Free to Open – You will be on Free Tier for the 1st year)
• Amazon S3 Storage Cost (For Data Storage and Data Traffic Out)

As part of the AWS Free Tier, you can get started with Amazon Rekognition Video at no cost. The Free Tier lasts 12 months and includes 1,000 free minutes of video analysis per month. Amazon Rekognition Video free tier covers Label Detection, Content Moderation, Face Detection, Face Search, Celebrity Recognition, Text Detection and Person Pathing.

Amazon Rekognition Video charges you for video analysis performed using AWS APIs. When running multiple API calls against the same section of video, you will get charged separately for each API. Amazon Rekognition can analyze videos stored in Amazon S3.

 

Installation Instructions:

Setup Requirements:

• AWS PHP SDK v3 is Required (Already comes with the App) – Setup Link
• AWS IAM User Amazon Rekognition and Amazon S3 Access Policies attached – Setup Link
• Amazon S3 Bucket with Public Access – Setup Link
• Also Listed and Explained in the Documentation

 

Set Up:

• Create IAM User with Amazon Rekognition and Amazon S3 policies attached.
• Include into the configurations your AWS IAM User Access and Secret Access Key and your AWS S3 Bucket Name
• Webcam usage will require HTTPS connection, it is a browser requirement.

 

Credits:

• FileSaver by Eli Grey
• JSZip by Stuart Knightley
• Video.js by Brightcove