Featured re:Invent 2017 Sessions
NEW LAUNCH! Introducing Amazon Kinesis Video Streams (ABD216)
Amazon Kinesis Video Streams makes it easy to securely stream video from connected devices to AWS for analytics, machine learning (ML), and other processing. In this session, we introduce Kinesis Video Streams and its key features, and review common use cases including smart home, smart city, industrial automation, and computer vision. We also discuss how you can use the Kinesis Video Streams parser library to work with the output of video streams to power popular deep learning frameworks. Lastly, Abeja, a leading Japanese artificial intelligence (AI) solutions provider, talks about how they built a deep-learning system for the retail industry using Kinesis Video Streams to deliver better shopping experience.
Workshop: Stream Video from Edge Devices to AWS for Playback, Storage and Processing
Amazon Kinesis Video Streams is a video ingestion and storage service for analytics, machine learning, and video processing use cases. In this workshop, you will learn how to stream video from devices to Kinesis Video Streams for playback, storage and subsequent processing. For the workshop, we will provide you a Raspberry Pi 3 with camera module and pre-loaded with the Kinesis Video Streams producer SDK. First, you will create and configure a Kinesis video stream in the AWS management console. Next, you will stream videos from the Raspberry Pis to Kinesis Video Streams, view the live video feed in the console, and retrieve stored videos. Lastly, you will pull key operating metrics to understand the performance characteristics of your video stream. For this workshop, you need to create an AWS account.
Kinesis Video Streams Raspberry Pi Tutorial
To help you get started quickly with video ingestion, this tutorial provides step-by-step instructions on how to stream video from a Raspberry Pi (with camera module) to AWS using Kinesis Video Streams. You can then playback the video streams in the Kinesis management console, build machine learning models using the video as an input to popular ML frameworks like Apache MxNet and TensorFlow, recognize faces in the video streams using Amazon Rekognition Video, or process it for live streaming.