AnyVision’s Recognition AI Software Running on Ambarella’s CVflow® SoCs

AnyVision has announced the availability of new AI software designed to run on Ambarella’s CV2x family of edge AI vision SoCs, and helps make cameras smarter by extracting valuable data from high-resolution video streams in real-time.

The new AnyVision Recognition AI software is available now and optimized for Ambarella’s open and mature software development kit (SDK), enabling low-power, high-resolution IP security cameras with features such as facial recognition, person detection, analytics and more. This software, in combination with Ambarella’s highly efficient CVflow® AI vision SoC architecture, allows cameras to perform complex data analysis and deliver breathtaking imagery, while preserving vital system resources such as power and network bandwidth.

Historically, organizations that wanted to add video analytics and intelligence to their IP security cameras or turnstiles relied on expensive on-premises servers, which were required to handle the compute loads. Ambarella’s edge AI vision SoCs push more of this processing to the actual cameras and dramatically reduce the need for on-premise servers, fundamentally changing the historical paradigm for large-scale video security and biometric-based access control.

“Because of their high data volumes, compute demands and latency requirements, cameras are the most challenging ‘things’ in the Internet of Things,” said Avi Golan, CEO at AnyVision. “By running our video analytics and Recognition AI on Ambarella’s CVflow SoCs, we’re pioneering new frontiers in edge AIoT computing, which opens up whole new use cases and markets.”

The open SDK for Ambarella’s CVflow SoCs allows easy integration of third-party applications, while enabling OEMs to address several emerging use cases, including:

Touchless access control. In order to minimize physical contact between users and surfaces, new touchless access control solutions are evolving that capitalize on facial recognition. Running on Ambarella’s CV2x series SoCs, AnyVision’s Recognition AI software uses deep neural networks to extract and compare the faces of those entering a facility with those registered in the system, providing a recognition accuracy rate of approximately 99%.

Video surveillance. Instead of relying on expensive on-premise servers to process and interpret the video streams from low-power, high-resolution security cameras, the cameras themselves can become powerful edge computing devices with embedded facial recognition and watchlist-alert functionality. AnyVision’s AI software can overcome the most challenging conditions — from large crowds to low light environments, extreme angles, and obscured faces.

Liveness detection. This edge AIoT technology helps organizations take advantage of 2D and high-resolution 3D liveness detection, which is becoming increasingly important as criminals use spoofs (e.g., a 2D picture held up to the camera by an unauthorized person) in order to bypass the access control or video surveillance system.

“The ability to perform real-time video analytics directly on cameras is a growing trend in the convergence of AI and IoT,” said Fermi Wang, president and CEO of Ambarella. “The combination of AnyVision’s Recognition AI software and our CVflow edge AI vision SoCs will enable smarter AIoT devices for the next generation of security and access control systems.”

This partnership empowers organizations of all stripes to harness the power of edge computing to analyze traffic, security, crime and liveness in real-time — and in a much more efficient and cost-effective manner.

Featured

  • Progressing in Capabilities

    Progressing in Capabilities

    Hazardous areas within industries like oil and gas, manufacturing, agriculture and the like, have long-sought reliable video surveillance cameras and equipment that can operate safely in these harsh and unpredictable environments. Read Now

  • A Comprehensive Nationwide Solution

    A Comprehensive Nationwide Solution

    Across the United States, manufacturing facilities, distribution centers, truck yards, parking lots and car dealerships all have a common concern. They are targets for catalytic converters. In nearly every region, cases of catalytic converter thefts have skyrocketed. Read Now

  • Planning for Your Perimeter

    Planning for Your Perimeter

    The perimeter is an organization’s first line of defense and a critical element of any security and surveillance program. Even if a building’s interior or exterior security is strong, without a solid perimeter surveillance approach any company or business is vulnerable. Read Now

  • The Key Issue

    The Key Issue

    It is February 2014. A woman is getting ready in her room on a cruise ship when she hears a knock on the door; it is a crewmember delivering breakfast. She is not presentable so she tells him to leave it by the door. Read Now

Featured Cybersecurity

New Products

  • XS4 Original+

    XS4 Original+

    The SALTO XS4 Original+ design is based on the same proven housing and mechanical mechanisms of the XS4 Original. The XS4 Original+, however, is embedded with SALTO’s BLUEnet real-time functionality and SVN-Flex capability that enables SALTO stand-alone smart XS4 Original+ locks to update user credentials directly at the door. Compatible with the array of SALTO platform solutions including SALTO Space data-on-card, SALTO KS Keys as a Service cloud-based access solution, and SALTO’s JustIn Mobile technology for digital keys. The XS4 Original+ also includes RFID Mifare DESFire, Bluetooth LE and NFC technology functionality. 3

  • SecureAuth

    SecureAuth

    The acceleration of digital transformation initiatives as a result of COVID-19 has created a lasting impact on how businesses empower their workforce and engage customers. 3

  • PDK IO Access Control Software

    PDK.IO Access Control Software

    ProdataKey now allows for "custom fields" within the interface of its pdk.io software. Custom fields increase PDK's solutions' overall functionality by allowing administrators to include a wide range of pertinent data associated with each user. 3