Create a Rekognition Stream Processor to work on a Kinesis Video Stream and pass the generated events to Lambda for processing or analytics.
This sample project demonstrates how to use Rekognition Stream Processors to analyse Kinesis Video Streams to search for faces and then pass the generated metadata to AWS Lambda for further processing/analytics. This pattern is leveraging the native integration between Kinesis Video and Rekognition Stream Processors which means we only need CDK to connect these components
For this sample project, we're going to develop a Rekognition Stream Processor that works to find connected home labels such as 'PERSON' or 'PET' or 'PACKAGE' for the demo, we're simply using 'PERSON' and 'PET' with a confidence threshold of 80.
< Back to all patterns
Clone repo
git clone https://github.com/aws-samples/serverless-patterns/cd serverless-patterns/kinesis-video-rekognition-lambdaDeploy
cd src/cdk deployTesting
See the GitHub repo for detailed testing instructions.
Cleanup
Delete the stack:
cd src/ && cdk destroy.Created by:
