Unique Architecture Delivers Performance and Flexibility Optimization
RA’ANANA, Israel, September 7, 2017 – Inuitive, a developer of cutting edge 3D computer vision and image processors has introduced the NU4000, a superior multi-core vision processor that supports 3D Imaging, Deep Learning and Computer Vision processing for Augmented and Virtual Reality, Drones, Robots and other applications. This next generation processor enables high quality depth sensing, SLAM on-chip, Computer Vision and Deep Learning (CNN) capabilities in affordable form factor and minimized power consumption, leading the way for smarter user experiences.
Combining high performance and flexibility, the powerful core-processors backed by hardware accelerators reduce latency to less than 1mSec, delivering an enhanced augmented and virtual reality experience. The NU4000’s deep Learning Engine enables object detection, classification and recognition, and scene understanding.
Leading the Vision processors category, NU4000 provides unmatched Imaging and Vision computing power exceeding a total of 8 Terra OPS (Operations per second). It introduces an optimized Embedded Vision architecture that effectively combines a set of computing blocks positioning it as the most powerful vision processor available. These include:
“With the NU4000, we are uniquely positioned to be the cornerstone chip for MR/VR, Robots and Drones, and are defining the Vision Processor Unit category,” said Mr. Shlomo Gadot – Inuitive Co-Founder & CEO. “We are excited to provide innovative products that address the needs of the market and paves the way for the future’s most advanced technologies.”
The NU4000 connects to 6 cameras and 2 displays, and is 7x8mm. It also features an enhanced depth processor engine for active and passive stereo, and Structured Light technologies; Smart sensor hub capabilities that synchronize, time-stamp and process inputs from multiple sensors offloading the host processor; and a fully programmable Deep Learning Processor, all at an advanced and power efficient 12nm process node.
To learn more, visit www.inuitive-tech.com.
Inuitive optimizes consumer experiences and enhances competitive advantages in the areas of Augmented & Virtual Reality, Drones, Robots and Autonomous Cars, among others. Inuitive combines algorithms, ASIC, and System solution to realize the AI practice enabling devices to acquire more human capabilities. With AI at its core, Inuitive’s platform includes a 3D Depth Sensing Computer Vision processor and powerful deep learning capabilities enabling smart devices to become smarter.
Inuitive Ltd. (Inuitive) and SoftBank Corp. (SoftBank), a subsidiary of SoftBank Group Corp. (TOKYO: 9984), today announced that they have agreed to collaborate through the development of artificial intelligence (AI), deep learning (DL) and advanced 3D sensing with computer vision capabilities for future IoT.
This collaboration will draw from the expertise of both companies in AI by leveraging Inuitive’s existing and future vision processors and its AI framework with SoftBank’s IoT platforms, which offer advanced heterogeneous processing capabilities for embedded products. The companies expect the collaboration to drive the popularity and development of smart IoT devices and systems.
Devices such as IoT are becoming more intelligent with the proliferation of AI. Implementing AI on the device provides a number of advantages over current market implementations, enabling edge devices to provide human-like interaction while keeping consumer market price tag. Additional benefits of on-chip AI include real-time performance, privacy protection and longer operation time.
“To develop an AI framework, it takes efforts from players in multiple domains,” said Mr. Shlomo Gadot, founder and chief executive officer, Inuitive. “The strategic collaboration between Inuitive and SoftBank will advance on-device intelligence by leveraging Inuitive’s advanced technologies and SoftBank market proven technologies. Together we’ll push the performance envelope and extend AI to places that are currently beyond reach. Our strategic collaboration will become a turning point for the whole on-chip AI industry”.
“SoftBank has been conducting research in AI over a decade,” said Hironobu Tamba, Vice President, Head of Smart IoT Division, SoftBank. “We look forward to the results of our collaboration with Inuitive to further accelerate new and exciting capabilities of on-chip AI for millions of devices”.
Currently, SoftBank is focused on optimizing the high-end platforms to accelerate AI products use cases in the areas of computer vision and neural networks and is researching broader executions in the areas of Objects recognition, Scene reconstruction, SLAM and power management. Inuitive is a leading company in vision processing and its applications. It plays an important role in deep learning algorithm innovation. The company’s leading technology in deep learning makes it possible to innovate and develop a variety of algorithms with low cost and fast response time. Inuitive has also made breakthroughs in sensing technologies. Its strategic collaboration with SoftBank is expected to drastically improve the speed and efficiency of combining system with chipset, making Inuitive’s AI technology more pervasive.
INUITIVE (www.inuitive-tech.com) Inuitve is the leading fabless semiconductor company in the area of 3D imaging and with its NU4000 optimizes consumer experiences and enhances competitive advantages in the areas of Robots, Drones, Augmented Reality and Virtual Reality to name just a few. INUITIVE intelligent offering combines, algorithms, ASIC and System solution to realize the AI practice enabling devices to acquire more human capabilities. With AI at its core, The INUITIVE platform also includes a 3D Depth Sensing Computer Vision processor and powerful deep learning capabilities to enable smart devices to become even smarter.
SoftBank Corp., a subsidiary of SoftBank Group Corp. (TOKYO: 9984), provides mobile communication, fixed-line communication and Internet connection services to customers in Japan. Leveraging synergies with other companies in the SoftBank Group, SoftBank Corp. aims to transform lifestyles through ICT and expand into other business areas including IoT, robotics and energy. To learn more, please visit www.softbank.jp/en/corp/group/sbm/
MOUNTAIN VIEW, Calif., Sept. 14, 2017
Synopsys, Inc. (Nasdaq: SNPS) today announced that Inuitive selected Synopsys’ DesignWare® EV62 Embedded Vision Processor IP for its production NU4000 system-on-chip (SoC), Inuitive’s most advanced 3D imaging and vision SoC. Inuitive adopted the EV62 Processor IP to take advantage of the high performance and processing efficiency of the tightly integrated vector DSPs and convolutional neural network (CNN) engine. The CNN engine operates in parallel with the vector DSPs, enabling Inuitive to implement highly accurate object detection, image classification and semantic segmentation capabilities in its SoC at a fraction of the power consumption of competing vision processor IP solutions. The MetaWare EV Development Toolkit, a comprehensive set of tools and software for the EV6x Processors, can distribute the NU4000’s computations between the vision CPU and CNN resources to support new and emerging neural network algorithms as well as customer-specific CNN layers.
“To provide our customers with the most advanced, high-performance vision processing capabilities for their demanding computer vision and machine learning applications, we require vision processing IP with the best mix of performance and power consumption with the flexibility to support current and future CNN graphs,” said NAME, TITLE at Inuitive. “The competitive power, performance and area advantages of the DesignWare EV62 processor with its fast CNN engine were critical to achieving the real-time processing capabilities of our NU4000 3D imaging and vision processor SoC.”
The DesignWare EV6x Processor Family supports Inuitive’s NU4000 SoC requirements for processing multiple camera inputs with high-definition resolutions up to 4K. The EV6x processors have a heterogeneous multicore architecture that includes one to four high-performance vector DSPs designed to be tightly coupled to a CNN engine that delivers up to 4.5 TeraMACs/sec in typical 16-nm FinFET process technologies. To simplify software application development, the DesignWare EV6x Processors are fully programmable and supported by the MetaWare EV Development Toolkit, which includes software development tools based on the OpenVX™, OpenCV and Open CL™ C embedded vision standards. In addition, the Toolkit includes a CNN mapping tool that automatically converts neural networks trained using popular frameworks like Caffe and Tensorflow into an executable for the CNN engine.
“Artificial intelligence is enabling intelligent, real-time identification and recognition at high precision for applications such as ADAS, video surveillance and virtual/augmented reality,” said John Koeter, vice president of marketing for IP at Synopsys. “By using Synopsys’ EV6x Vision Processor IP, companies like Inuitive can create SoC designs that execute deep learning algorithms at TeraMAC-per-second speeds with the lowest power consumption and highest accuracy.”
Availability & Resources
The DesignWare EV61, EV62 and EV64 processors with optional CNN engine, and the MetaWare EV Development Toolkit, are available now. Support for the TensorFlow framework in the Toolkit’s CNN mapping tool is scheduled to be available in Q4 2017.
About DesignWare IP
Synopsys is a leading provider of high-quality, silicon-proven IP solutions for SoC designs. The broad DesignWare® IP portfolio includes logic libraries, embedded memories, embedded test, analog IP, wired and wireless interface IP, security IP, embedded processors and subsystems. To accelerate prototyping, software development and integration of IP into SoCs, Synopsys’ IP Accelerated initiative offers IP prototyping kits, IP software development kits and IP subsystems. Synopsys’ extensive investment in IP quality, comprehensive technical support and robust IP development methodology enable designers to reduce integration risk and accelerate time-to-market. For more information on DesignWare IP, visit www.synopsys.com/designware.
Synopsys, Inc. (Nasdaq: SNPS) is the Silicon to Software™ partner for innovative companies developing the electronic products and software applications we rely on every day. As the world’s 15th largest software company, Synopsys has a long history of being a global leader in electronic design automation (EDA) and semiconductor IP and is also growing its leadership in software security and quality solutions. Whether you’re a system-on-chip (SoC) designer creating advanced semiconductors, or a software developer writing applications that require the highest security and quality, Synopsys has the solutions needed to deliver innovative, high-quality, secure products. Learn more at www.synopsys.com.
INUITIVE (www.inuitive-tech.com) optimizes consumer experiences and enhances competitive advantages in the areas of Augmented Reality and Virtual Reality, Drones, Robots and Autonomous Cars, to name just a few. INUITIVE intelligent offering combines, algorithms, ASIC and System solution to realize the AI practice enabling devices to acquire more human capabilities. With AI at its core, The INUITIVE platform also includes a 3D Depth Sensing Computer Vision processor and powerful deep learning capabilities to enable smart devices to become even smarter.
Tel Aviv, May, 30, 2017. Inuitive, a developer of cutting edge 3D computer vision and image processing devices, today released its latest reference design, the Veronica. Designed to fit into Virtual Reality Head Mounted Displays, Smart Glasses, Robots and Drones, the Veronica features a 120×90 degree field of view depth sensing, surpassing the industry standard of 60 degrees. The Veronica hosts Inuitive’s NU3000 3D Imaging and Vision processor on a single platform delivering advanced user experience capabilities for consumers.
The Veronica offers complete sensing capabilities enabling accurate inside/out tracking, SLAM based navigation and resolution served at a frame rate of 120 fps. Additionally, the sensors data is managed, calibrated, synchronized, accurately time stamped and sent to the host. The Veronica is designed to enable shorter time to production when dealing with manufacturing calibration and alignment procedures.
“The Veronica addresses the need to both “see” the surroundings and “understand” it with advanced 3D depth sensing capabilities,” said Shlomo Gadot, CEO and Co-Founder of Inuitive. “As the demand for high quality, high performing VR/AR technology grows, Inuitive’s products will continue to meet that demand and deliver an optimum user experience for its customers.”
Inuitive’s NU3000 is a multi-core processor, optimized for depth sensing, 3D image processing and computer vision in mobile environments. It can interface with multiple cameras: two as a stereo depth source and others for RGB and/or for tracking purposes. Moreover, it can process multiple video streams in real time to generate a high quality depth image, assign color to the depth images, extract feature points and execute high-level processing on all available video streams. NU3000’s architecture combines dedicated hardware accelerators with vector DSPs enabling power efficient execution of depth sensing as well as higher-level algorithms and applications. The next generation processor, the NU4000, will be released in the coming months.
Inuitive develops processors with 3D depth sensing, computer vision and powerful deep learning capabilities enabling smart devices to become even smarter. Inuitive optimizes consumer experiences and enhances competitive advantages in the areas of Augmented and Virtual Reality, Drones, Robots and Autonomous Cars. The company’s team of R&D professionals in the fields of Imaging, Computer Vision Algorithms, Optics, Embedded Systems Software and System-on- Chip design has enabled Inuitive to develop its unique processor architecture that addresses both flexibility and performance optimization.