- Collaboration leverages Quadric Chimera™ GPNPU processors alongside the Mira CMOS image sensors from ams OSRAM to deliver high-performance, low-power machine vision
- Solution enables new capabilities of low power and small form factor smart sensing for various applications, for example, face detect and identification, human pose detect, motion and occupancy detect, and many others
- Demonstrator will be first showcased at CES, Las Vegas, January 5-8 2023
BURLINGAME, Calif. & PREMSTAETTEN, Austria–(BUSINESS WIRE)–#CES—Quadric, an innovator in machine learning processor IP for on-device AI, and ams OSRAM (SIX: AMS), a global leader in optical solutions, today announced a strategic collaboration to develop integrated sensing modules combining ams OSRAM’s leading edge Mira Family of CMOS sensors for visible and infrared with Quadric’s novel Chimera™ GPNPU processors. The combined ultra-low power modules will enable new methods of smart sensing for wearable devices, robotics, industrial and security markets. A demonstration of the product will be on display at CES, Las Vegas, January 5-8, 2023.
Quadric’s Chimera™ general purpose neural processors (GPNPUs) offer the ability to handle both machine learning graph processing and classical data-parallel C++ algorithms in a unified architecture, bringing advanced on-device AI capabilities to edge-based applications. Quadric’s architecture delivers efficient machine learning (ML) inference performance, but unlike other neural network accelerators which support a limited number of machine learning graph operators, the Quadric solution also has general-purpose control and signal processing capability – blending the best attributes of NPU accelerators with DSPs. Quadric GPNPUs can run both neural net graphs and C++ code for signal pre-processing and post-processing and at dramatically lower levels of power dissipation than other edge silicon solutions.
The Mira lineup of CMOS image sensors from ams OSRAM are focused on low sensor and system power, and small form factors that maximize resolution efficiency in minimal footprint. The growing portfolio of the Mira family sensors offer a range of resolutions for different applications requiring high performance global shutter image sensors, multiple released products and more in development at higher and lower resolutions.
“The combination of ams OSRAM’s sensors and Quadric’s processing into a single low-power module opens up vast new possibilities for deployment of smart vision sensing,” said Joost Seijnaeve, Vice President and General Manager of CMOS Image Sensors for ams OSRAM. “OEMs no longer need 5W edge silicon chips or 15W board-level compute solutions to perform smart sensing functions like human pose, face identification, object detection, object recognition, and scene analysis” continued Mr. Seijnaeve. “Those leading-edge smart vision functions can be embedded in a single combined sensor and processing module in a host of innovative product form factors in automotive, consumer, industrial and applications.”
A Mira image sensor combined with a Quadric GPNPU integrates image capture and machine learning into a single low-power module – accomplishing in a few hundred milliwatts what today requires a 5W or 10W GPU card according to simulations run by Quadric. The Mira220 and future derivative resolutions offer multiple combinations for different applications combined with Quadric’s scalable Chimera™ processor lineup that spans a range of compute from 1 TOP to 16 TOPs.
“Quadric is excited to be joining forces with ams OSRAM,” said Veer Kheterpal, Quadric CEO. “Empowering device makers with the capability for a fully-programmable smart sensing device at incredibly low power levels will open a vast new tranche of deployments of machine learning in edge devices.”
Demonstrations Available Now
A demonstration kit showcasing the combined Quadric plus Mira Sensors technologies is available from ams OSRAM.
Quadric.io Inc. is the leading licensor of general-purpose neural processor semiconductor IP (GPNPU) that runs both machine learning inference workloads and classic DSP and control algorithms. Quadric’s unified hardware and software architecture is optimized for on-device ML inference. Learn more at www.quadric.io.
About ams OSRAM
The ams OSRAM Group (SIX: AMS) is a global leader in optical solutions. By adding intelligence to light and passion to innovation, we enrich people’s lives. This is what we mean by Sensing is Life.
With over 110 years of combined history, our core is defined by imagination, deep engineering expertise and the ability to provide global industrial capacity in sensor and light technologies. We create exciting innovations that enable our customers in the automotive, consumer, industrial and healthcare sectors maintain their competitive edge and drive innovation that meaningfully improves the quality of life in terms of health, safety and convenience, while reducing impact on the environment.
Our around 22,000 employees worldwide focus on innovation across sensing, illumination and visualization to make journeys safer, medical diagnosis more accurate and daily moments in communication a richer experience. Our work creates technology for breakthrough applications, which is reflected in over 15,000 patents granted and applied. Headquartered in Premstaetten/Graz (Austria) with a co-headquarters in Munich (Germany), the group achieved over EUR 5 billion revenues in 2021 and is listed as ams-OSRAM AG on the SIX Swiss Exchange (ISIN: AT0000A18XM4).
Find out more about us on https://ams-osram.com
ams is a registered trademark of ams-OSRAM AG. In addition many of our products and services are registered or filed trademarks of ams OSRAM Group. All other company or product names mentioned herein may be trademarks or registered trademarks of their respective owners.