Artificial intelligence (AI) is coming to the fore in more business applications, with image analysis the latest use case to benefit from AI. Using deep learning to understand pixels and sensors, and analyse metadata, businesses can leverage images to drive more effective retail analytics, intelligent traffic control, automated optical inspection, freight and goods tracking, web content filtering and target ad injection, according to Empired.
Building next-generation computer vision applications that run on the edge computing layer lets users analyse those videos in real time, even when multiple streams come from various cameras. These real-time analytics can deliver powerful insights to decision-makers who can act on current situations to make smarter choices.
Dr Steve Leven, head of advanced technologies and transformation, Empired, said, “The application uses Microsoft Azure and NVIDIA alongside Empired’s proprietary approach to deep learning. The Empired solution offers the versatility to deploy from NVIDIA Jetson on edge to NVIDIA Tesla in Azure. Empired’s developers have also integrated the edge to the cloud with standard message brokers like Kafka, an open-source stream-processing software platform, for large-scale, wide deployments.”
The solution includes multiple graphics processing unit clusters or micro-service containers, which provide a highly-flexible system architecture that opens up new application capabilities. Empired can co-develop with clients by making available Docker images of pre-trained and supervised assets on DeepStream and couple this with Azure Cognitive services. By combining this with Kubernetes, an open source container-orchestration system, Empired has created a solution that scales rapidly and supports tens of thousands of video frames that can be ingested from hundreds of cameras.
Dr Steve Leven said, “Empired is an early mover in this space and has seen demand for video intelligence grow rapidly. The faster the video data can be analysed, the sooner organisations can turn insights into action, making smarter decisions, faster, for increased competitiveness.
“Empired intends to stay ahead of the curve and continue providing enterprise-grade solutions and strong returns for its clients. Empired is currently working on building extensible capability and working with open source edge computing layers that will create more seamless and adaptable intelligent assets that leverage Internet of Things (IoT) Platform-as-a-Service running in Azure.”
