Introduced last November, AWS DeepLens is offered as a deep learning-enabled wireless video camera specifically designed to help developers of all skill levels grow their machine learning skills through hands-on computer vision tutorials, example code, and pre-built models. It includes an HD video camera with on-board compute optimized for deep learning, which is fully programmable using the company’s AWS Lambda event-driven, serverless computing platform.
The device’s hardware includes a 4-megapixel camera (1080P video), 2D microphone array, Intel Atom processor, dual-band Wi-Fi, USB and micro HDMI ports, and 8 GB of memory for models and code. Software features include Ubuntu 16.04, AWS Greengrass Core, device-optimized versions of MXNet and Intel clDNN library, and support for other deep learning frameworks.
DeepLens integrates with Amazon SageMaker, a fully-managed platform that enables developers and data scientists to quickly and easily build, train, and deploy machine learning models at any scale. The video stream from the DeepLens camera can be used in conjunction with Amazon Kinesis Video Streams, enabling users to stream the raw camera feed to the cloud and then use Amazon Rekognition Video to extract objects, faces, and content from the video.
DeepLens includes a sample project for head pose detection (powered by TensorFlow). DeepLens is available to order from Amazon.com.