AWS Panorama Appliance allows customers to analyze video feeds in edge environments
Amazon Web Services released AWS Panorama Appliance, a new device that customers can install in their facilities to run applications that analyze multiple video streams from existing on-premises cameras.
The AWS Panorama Appliance enables customers to use computer vision technology to quickly and easily perform visual inspections of production lines (e.g. spot defects in manufactured parts), enhance customer experiences at quick service restaurants (e.g. monitor drive-through queues), or optimize the layout of physical retail stores (e.g. improve product placement, inventory checks, etc.).
The AWS Panorama Appliance is one of four AWS products (along with Amazon Monitron, Amazon Lookout for Equipment, and Amazon Lookout for Vision) that form the most comprehensive suite of cloud-to-edge industrial machine learning services available
Customers in industrial, hospitality, logistics, retail, and other industries want to use computer vision to make decisions faster and optimize their operations. These organizations typically have cameras installed onsite to support their businesses, but they often resort to manual processes like watching video feeds in real time to extract value from their network of cameras, which is tedious, expensive, and difficult to scale.
While some smart cameras can provide real-time visual inspection, replacing existing cameras with new smart cameras can be cost prohibitive. Even then, smart cameras are often ineffective because they are limited to specific use cases and require additional effort to fine-tune. For example, updating a smart camera because of a simple change in the environment (e.g. lighting, camera placement, or production line speed) means that a customer often has to contact their vendor for support, which can be costly and time consuming.
Alternatively, some customers send video feeds from existing on-premises cameras to third-party servers, but often the required internet bandwidth is costly or facilities are in remote locations where internet connectivity can be slow, all of which degrades the usefulness and practicality of the analysis. Consequently, most customers are stuck using slow, expensive, error-prone, or manual processes for visual monitoring and inspection tasks that do not scale and can lead to missed defects or operational inefficiencies.
The AWS Panorama Appliance is a new device that solves these challenges by enabling customers to improve their operations and reduce costs by using existing on-premises cameras and analyzing video streams locally with computer vision. Customers can get started in minutes by connecting the AWS Panorama Appliance to their network and identifying the video feeds for analysis.
Because the computer vision processing happens locally on the AWS Panorama Appliance at the edge, customers can save on bandwidth costs and use it in locations with limited internet bandwidth. Additionally, the AWS Panorama Appliance is integrated with Amazon SageMaker (an AWS service that makes it easy for data scientists and developers to build, train, and deploy machine learning models), so customers can update their computer vision application in Amazon SageMaker and deploy the model to the AWS Panorama Appliance themselves.
For customers that do not want to build their own computer vision applications, AWS Panorama Partners like Deloitte, TaskWatch, Vistry, Sony, and Accenture provide a wide range of solutions that can address unique use cases across manufacturing, construction, hospitality, retail, and other industries. For example, customers in the retail industry have used AWS Panorama Partners to develop computer vision applications that can analyze foot traffic to help optimize store layout and product placement, analyze peak times when additional staffing is needed to assist customers, and quantify inventory levels.
“Organizations across all industries like construction, hospitality, industrial, logistics, retail, transportation, and more are always keen to improve their operations and reduce costs. Computer vision offers a valuable opportunity to achieve these goals, but companies are often inhibited by a range of factors including the complexity of the technology, limited internet connectivity, latency, and inadequacy of existing hardware,” said Swami Sivasubramanian, Vice President of Amazon Machine Learning at AWS.
“We built the AWS Panorama Appliance to help remove these barriers so our customers can take advantage of existing on-premises cameras and accelerate inspection tasks, reduce operational complexity, and improve consumer experiences through computer vision.”
The AWS Panorama Appliance is available for sale through AWS Elemental in the United States, Canada, United Kingdom, and European Union. The AWS Panorama service is available today in US East (N. Virginia), US West (Oregon), Canada (Central), and Europe (Ireland), with availability in additional AWS Regions in the coming months.
The Cincinnati/Northern Kentucky International Airport is a public international airport located in Hebron, Kentucky, that provides world-class service to travelers in the Cincinnati tri-state area. “CVG Airport is committed to providing a world-class traveler experience through continuous innovation and strategic cooperation,” said Brian Cobb, Chief Innovation Officer at Cincinnati/Northern Kentucky International Airport.
“By using TaskWatch’s application on AWS Panorama, we are able to bring machine learning to our existing IP cameras and automatically monitor congestion over 70,000 square feet of airport traffic lanes. Once an issue is detected, such as a disabled vehicle, TaskWatch sends real-time alerts to airport staff so they can provide assistance, keep the traffic flowing, and reduce delays for our passengers.”
The Vancouver Fraser Port Authority is the third-largest port in North America, processing 3.5 million shipping containers a year. “We needed a solution to help optimize ground operations and expedite container inspection for the thousands of containers entering our port every day,” said Greg Rogge, Director of Operations at Vancouver Fraser Port Authority.
“We identified machine learning as an enabler that could address this problem. With the help of Deloitte, we are using AWS Panorama and other advanced technologies to identify and track containers throughout our facilities. Our customers benefit from real-time visibility through data feeds into a blockchain system, and the port is able to identify efficiency-improvement opportunities in the existing process.”
Tyson Foods, Inc. is the largest U.S. food company, focused on tackling some of the biggest sustainability challenges facing the world today. “Our team worked with the Amazon ML Solutions Lab to build computer vision models for counting packaged products on our line for quality assurance,” said Barret Miller, Senior Manager of Emerging Technology at Tyson Foods, Inc. “These efforts have enabled us to develop automated solutions for our packaging lines using AWS Panorama.”