Amazon Web Services Inc. today announced the general availability of AWS Panorama, an appliance that companies can deploy at locations such as factories to run computer vision software on-premises.

Organizations are applying artificial intelligence to more and more parts of their operations in a bid to increase efficiency. In many cases, the AI models a company uses run on public cloud infrastructure. But there are certain scenarios where it’s more practical to run AI on-premises instead, close to where the data being processed is generated. That’s the use case AWS is addressing with Panorama.

Panorama is a compact appliance that ships in a dust-proof and water-resistant case. Organizations can use the system to run computer vision applications that analyze footage from cameras at locations such as factories, retail stores and warehouses.

A manufacturer could use Panorama to monitor a production line for flawed components. A logistics company, meanwhile, can harness the appliance to ensure that trucks arriving at its warehouse park at the correct spots. Improving employee safety is another use case that the appliance supports. At locations such as factories where employees work in proximity to industrial robots and other heavy equipment, AI software running on Panorama can automatically identify potential safety issues.

“You can use AWS Panorama Appliance to evaluate manufacturing quality, identify bottlenecks in industrial processes, and monitor workplace security even in environments with limited or no internet connectivity,” AWS Principal Developer Advocate Sébastien Stormacq wrote in a blog post today.

There are several reasons why running AI models on-premises is sometimes more practical than using public cloud infrastructure. Moving data to the cloud for analysis requires reliable internet connectivity, which isn’t always available in locations such as factories.

Another factor is that, even when reliable network access is accessible, sending information to a remote data center and then waiting on the results to return leads to latency. Processing information on-premises speeds up applications by avoiding a round-trip to the cloud. 

A third factor that can make Panorama compelling for companies such as manufacturers is that moving large amounts of data to the cloud has the potential to incur significant bandwidth costs. By processing data on-premises, companies can reduce bandwidth requirements. 

The launch of Panorama comes a few months after AWS announced the general availability of AWS IoT SiteWise Edge, another solution aimed at edge computing use cases. It’s an on-premises version of the Amazon.com Inc. unit’s cloud-based IoT SiteWise service. The solution helps companies collect diagnostics data from industrial equipment to identity and troubleshoot technical issues. 

Image: AWS