Advertorial:
Meet Ability Enterprise Co., Ltd.

Edge computing capabilities have expanded the deployment of AI-enabled smart cameras into various vertical markets. How have these edge AI cameras redefined what video surveillance is and what it can be?

Traditional video surveillance faces a few different problems today. They use legacy hardware from a highly fragmented ecosystem with little to no common software. In addition, such systems do not provide proactive surveillance or actionable insights, and often, are only referred to after an incident has occurred.

Ability offers edge AI cameras that are designed with the developer and integrator in mind. It is a software-defined camera – essentially taking on the functionality defined by the software and the application that is deployed on it.

Furthermore, as Ability’s camera portfolio is fully NDAA (National Defense Authorization Act) compliant, we are an ideal ODM/OEM partner for our customers in the U.S.

Using Intel® Distribution of OpenVINO™ Toolkit, Ability’s AI cameras are intended to be developer friendly and reduces time-to-market. The data acquired from the AI applications deployed on the edge AI cameras can be easily integrated with back-end management systems to drive smart decision making and policies.

There is now market traction on the notion of AI-as-a-Service where revenue generation for businesses do not need to be fully dependent on the sale of hardware and/or software but can be in the maintenance of AI algorithms. This also reduces the burden on the end-users from the perspective of upkeep and financing.

Ability cameras can integrate multiple AI algorithms to run simultaneously on the edge. Can they be customized for Smart City applications?

Powered by the Intel® Movidius™ Myriad™ X VPU, the programmable Ability edge AI cameras allow developers to port and run image centric neural networks on the edge cameras alone. Using top of the line image sensors from Sony, from 2MP to 8MP with various lens combinations, the cameras can address a range of practical use-cases in Smart Cities, such as traffic monitoring, smart buildings, security and assistance, and crowd monitoring. It also offers the best-in-class IP and IK ratings to withstand the harsh environments expected in these environments.

More importantly, the Intel® Distribution of OpenVINO™ Toolkit enables developers to easily take AI models from its Public Model Zoo repository for quick demonstration, or to port their own proprietary models and achieve the best performance goals. For instance, a traffic monitoring system may require models including vehicle-type detection and license plate recognition to run concurrently. In another example, a crowd monitoring system may require face detection, body detection and object detection.

It is also important to underscore the value of a developer-friendly device. As edge AI cameras are being developed, continuous learning is a natural outcome, and the ability to provide iterative improvements will be essential.

How does Ability’s AI-enabled video solutions impact the retail market?

The Ability camera allows for inference logic to be performed directly on the camera. For retail users, this creates efficiency on multiple fronts:

• Operational: Fewer logistics, as cameras do not need to be complemented by companion computer.
• Economic: An in-store retail camera network can be achieved more economically because the equipment needed to accomplish the task is reduced by about 40%. This is due to the diminished need for CPU/computers because processing of inference logic is done on board the camera. This also creates significant savings on bandwidth. Examples of algorithms/inference logic that can run on the cameras include people counting, demographics analysis, face detection, and dwell time.

In retail, cameras are used for operational visibility and for brand monetization. Cameras can also be used to measure the performance and audience measurement for digital signage – a new source of potential revenue for retailers.

Jay Hutton, CEO of VSBLTY Groupe Technologies Corp. has also commented “Computer vision is uniquely equipped to anonymously measure audiences in physical spaces. Retails is evolving into a powerful and valuable media channel. Computer vision is critical to this as it is only through computer vision that consumer engagement can be measured in real time effectively. Our proven ability to run computer vision directly on the camera changes the unit level economics for this market.”