Skip to main content

AWS Panorama

AWS Panorama FAQs

Page topics

General

Open all

AWS Panorama is a new machine learning (ML) appliance and software development kit (SDK) allowing organizations to bring computer vision (CV) to their on-premises cameras to make automated predictions with high accuracy and low latency. With AWS Panorama, companies can use compute power at the edge (without requiring video streamed to the cloud) to improve their operations. Panorama automates monitoring and visual inspection tasks like evaluating manufacturing quality, finding bottlenecks in industrial processes, and assessing worker safety within their facilities. Panorama terms - https://aws.amazon.com/panorama/terms/ 

The AWS Panorama Appliance is a hardware device you can install on your network. Connect Panorama to existing cameras within your facility to run multiple computer vision models on concurrent video streams. The AWS Panorama Appliance allows you to deploy CV applications to the edge when low latency and data privacy are required and internet bandwidth is limited. The AWS Panorama Appliance gives you the ability to add CV to your existing IP cameras, and automate tasks that traditionally require human inspection and monitoring. The AWS Panorama Appliance, when installed in a network, can connect to and process video from networked cameras and run simultaneous machine learning models per stream. Your cameras do not need any built-in ML or “smart” capabilities as the Appliance provides the CV. The Appliance is dust-proof and water-resistant, so you can install it in different environments without compromising functionality. Learn more »

The AWS Panorama Device SDK is a software development kit (SDK) allowing third-party manufacturers to run sophisticated computer vision models on their cameras. The SDK also allows hardware vendors to build new devices enhanced with computer vision for object detection or activity recognition. Using the Appliance, or cameras running the Device SDK, CV can help companies accomplish tasks like evaluating manufacturing quality, finding bottlenecks in industrial processes, or counting patrons in retail stores, even in environments with limited internet connectivity. The AWS Panorama Device SDK provides you with a device software stack for computer vision, sample code, APIs, and tools to enable and test your AWS Panorama-enabled devices for AWS Panorama service. Device manufacturers including ADLINK Technology, Axis Communications, Basler AG, Lenovo, STANLEY Security, and Vivotek are using the AWS Panorama SDK and APIs to build new AWS Panorama-enabled cameras and devices. AWS Panorama enabled devices work out of the box with AWS ML services and software and can be managed, monitored, and updated in the AWS management console. 

First, identify the process you want to improve with computer vision. For some ideas, see the AWS Panorama Use Cases. Second, you can either connect with an AWS Panorama Partner to take advantage of their deep expertise in building CV solutions, or you can build your CV solution using Amazon SageMaker and AWS Panorama.

The AWS Panorama Appliance is now available for purchase to deploy in production environments.

Device manufacturers can build new AWS Panorama-enabled devices (for example cameras or gateways devices), with the AWS Panorama SDK. Learn more »

The AWS Panorama Appliance gives you the ability to add CV to your existing internet protocol (IP) cameras, so you can automate tasks that traditionally require human inspection and monitoring. The AWS Panorama Appliance, when connected to a network, can connect to and process video from networked cameras. You can bring your own CV models, such as those built with Amazon SageMaker or use pre-built models from AWS or third-party application providers, and create CV applications by combining the CV models and business logic using the AWS Panorama management console. You can then deploy these applications to AWS Panorama devices and run simultaneous CV applications per video stream, turning your existing onsite cameras into powerful edge CV devices and generate highly accurate predictions within milliseconds. 

Many customers face challenges improving their physical systems, be it increasing manufacturing quality, ensuring safety and operating compliance of their facilities, or gaining insight into customer behavior inside retail locations. To do this today, employees monitor live video of the facility or equipment or review recorded footage after a problem or incident has occurred. These methods are manual, error prone, and difficult to scale. Customers are beginning to take advantage of computer vision models running in the cloud to automate these inspection tasks, but there are circumstances when relying exclusively on the cloud isn’t optimal due to latency requirements, intermittent connectivity, or data privacy needs that make a round trip to the cloud infeasible. You can use AWS Panorama to support scenarios that have low latency or local data processing requirements, and in locations that may not have reliable network bandwidth or connectivity. AWS Panorama customers typically need to generate near real-time responses to end-user applications or need to communicate with other on-premises systems or control on-site equipment. These scenarios are applicable for use cases such as for automated operations in manufacturing, crowd density monitoring in airports, worker safety in warehouses, extracting text from vials in labs, and quality assessment is production lines and factory floors.

While customers can take advantage of AWS services and use them as building blocks to develop a custom edge computer vision deployment solution, AWS Panorama offers an integrated edge-to-cloud workflow making it easy to build, manage, and deploy computer vision solutions. AWS Panorama removes the heavy lifting from each step of the computer vision process by integrating with familiar AWS services such as AWS SageMaker so you can build and train your CV models easily. AWS Panorama devices enable you to run your CV models directly on the device (at the edge), right where the data is created, meaning you can access real-time predictions even in remote and isolated places where network connectivity can be slow, expensive, or intermittent. AWS Panorama application results can be integrated with on-premises line of business applications for automation and can be routed to services such as Amazon Simple Storage Service (S3), Amazon Kinesis Video Streams, or Amazon CloudWatch for deriving actionable insights to drive process improvements.

Ordering and availability

Open all

The AWS Panorama Appliance is now available for purchase through Amazon.com, Amazon Business, and AWS Elemental. Learn more »

The Lenovo ThinkEdge SE70 device is available for purchase through Lenovo. Please visit the Lenovo ThinkEdge SE70 page to learn more.

AWS Panorama is available now in the AWS management console, and is supported in the following regions:

US East (N. Virginia), US West (Oregon), Republic of Ireland (Dublin), Canada (Central), Asia Pacific (Sydney), and Asia Pacific (Singapore).

Check out this GitHub repository with AWS Panorama computer vision examples. Learn how you can develop AWS Panorama applications for popular use cases such as object detection, semantic segmentation, and image classification. These examples are available as Jupyter notebooks that come with fully functioning Python code and include detailed commentary showing how you can use the AWS Panorama Application SDK APIs across multiple use cases.

For device manufacturers interested in building new AWS Panorama-enabled devices (for example cameras or gateways devices to meet customer needs), with the AWS Panorama SDK (Software Development Kit), reach out to your AWS sales representative. Learn more about the AWS Panorama SDK here »
 

Getting started & installation

Open all

AWS Panorama is a managed service and relies on connectivity to the parent AWS Region to manage applications, manage the device, and to receive over-the-air (OTA) updates. Once your CV applications are deployed on the device, you can access real-time predictions even in places where network connectivity can be slow or limited such as remote factory locations. Panorama service will not work in locations that are permanently disconnected from internet. It is also not recommended to deploy Panorama in locations that lose internet connectivity for several hours or days at a time.

Security, privacy, & compliance

Open all

AWS Panorama may help you to address your data privacy and sovereignty requirements. With AWS Panorama, you have control to ensure that sensitive data stays on premises. For real-time predictions with the AWS Panorama Appliance, the video streams do not leave the device on your premises. Control plane data (e.g. instance IDs, monitoring metrics, metering records, tags, etc.) will flow back to the AWS Region. You can also use AWS CloudTrail, where you can log, continuously monitor, and retain your account activity related to your actions with AWS Panorama. Together, these features help address many of the data privacy and sovereignty requirements we hear from our customers. You should confirm with your own compliance team or advisors to address whether these features help you to meet any requirements you may have.

No, the existing certifications for AWS Services are applicable to services running entirely in an AWS Region. AWS Panorama Appliance and AWS Panorama Appliance Developer Kit go through a separate evaluation for certifications. The AWS Panorama Appliance Developer Kit can be used in a manner consistent with the General Data Protection Regulation (GDPR). We expect to add more compliance certifications for the AWS Panorama Appliance. Compared to the certification for other AWS services, with AWS Panorama, the customer owns the responsibility for physical security and access controls around the AWS Panorama Appliance and the AWS Panorama Appliance Developer Kit with respect to compliance certifications.