From the course: Debiasing AI Using Amazon SageMaker

Unlock the full course today

Join today to access over 22,600 courses taught by industry experts or purchase this course individually.

Architecture diagram

Architecture diagram

From the course: Debiasing AI Using Amazon SageMaker

Start my 1-month free trial

Architecture diagram

- [Narrator] Let's look at the components that make up the architecture of our crime-fighting case study. First, AWS DeepLens is the video camera that is placed in a location to observe a given scene. DeepLens is not a normal camera, though. It is smart because it is running a face detection machine learning model that I've deployed to it. Thanks to AWS Greengass, a service that extends AWS functionality to IoT devices, I'm able to run lambda code on the video camera. All of this activity happens at the edge directly on the device itself. As soon as a face is detected in the scene, a picture is taken and uploaded to an S3 bucket in the cloud for analysis. S3 is an object storage mechanism and can store objects of many different types. The photo upload to the bucket triggers lambda code that retrieves the photo and sends it to AWS Rekognition. Rekognition is a computer vision service that gives computers a visual understanding of the world around it. Rekognition analyzes the photo and…

Contents