Prophesee claims event-based vision sensor is world’s smallest 

Claimed to be the world’s smallest and most power efficient event-based vison sensor, the GenX320 brings intelligence, privacy and safety to consumer edge AI devices, claimed Prophesee.

The company’s latest event-based Metavision sensor has low power, low latency, high flexibility for efficient integration in AR/VR headsets, security and monitoring/detection systems, touchless displays, eye tracking features and always-on smart IoT devices, said the company. 

It is, said Prophesee, the industry’s first event-based vision sensor developed specifically for integration into low power edge AI vision devices. The fifth generation Metavision sensor is available in a tiny 3.0 x 4.0mm die size.   

The 320 x 320 6.3 micron pixel BSI stacked event-based vision sensor offers a tiny 1/5 inch optical format. It has been developed with a specific focus on the requirements of efficient integration of event sensing in energy-, compute- and size-constrained embedded at-the-edge vision systems. It enables robust, high-speed vision at ultra-low power and in challenging operating and lighting conditions, added the company.

Features of the GenX320 include low latency microsecond resolution timestamping of events with flexible data formatting. There are also on-chip intelligent power management modes reduce power consumption to as low as 36 microW and enable smart wake-on-events. Deep sleep and standby modes are also featured.

Ease of integration/interfacing with standard SoCs with multiple integrated event data pre-processing, filtering, and formatting functions minimises external processing overhead. In addition, MIPI or CPI data output interfaces offer low-latency connectivity to embedded processing platforms, including low power microcontrollers and modern neuromorphic processor architectures.

The GenX320 is AI-ready, with on-chip histogram output that is compatible with multiple AI accelerators. For security, sensor-level privacy is enabled via the event sensor’s inherent sparse frameless event data with inherent static scene removal.

There is also native compatibility with Prophesee Metavision Intelligence event-based vision software suite, which is available free of charge and is used by community of 10,000+ users.

The high speed eye-tracking allows for foveated rendering for seamless interaction in AR/VR/XR headsets. The low latency touch-free human machine interface is suitable for consumer devices (TVs, laptops, game consoles, smart home appliances and devices and smart displays. The event-based sensor is also suitable for smart presence detection and people counting in IoT cameras and other devices as well as for always-on area monitoring systems and fall detection cameras in homes and health facilities.

The GenX320 is available for purchase from Prophesee and its sales partners. It is supported by a complete range of development tools, including a comprehensive evaluation kit housing a chip on board (COB) GenX320 module, or a compact optical flex module. In addition, Prophesee is offering a range of adapter kits that enable seamless connectivity to a large range of embedded platforms, such as a STM32 MCU, enabling faster time-to-market.

Prophesee creates neuromorphic vision systems. It developed an event-based vision approach to machine vision which allows for significant reductions of power, latency and data processing requirements to reveal what was invisible to traditional frame-based sensors until now. Prophesee’s patented Metavision sensors and algorithms mimic how the human eye and brain work to dramatically improve efficiency in areas such as autonomous vehicles, industrial automation, IoT, mobile and AR/VR. Prophesee is based in Paris, with local offices in Grenoble, Shanghai, Tokyo and Silicon Valley.

http://www.prophesee.ai

> Read More

Qualcomm launches next-generation XR and AR platforms

Two spatial computing platforms called Snapdragon XR2 Gen 2 and Snapdragon AR1 Gen 1 have been introduced by Qualcomm to enable the next generation of mixed reality (MR), virtual reality (VR) devices and smart glasses.

Snapdragon XR2 Gen 2 brings premium MR and VR technology into a single chip architecture for immersive experiences in thinner and more comfortable headsets, that do not require an external battery pack.

It is engineered to deliver a lag-free experience with immersive sound blending virtual content with the user’s physical surroundings and transition seamlessly between MR and VR experiences.

Snapdragon AR1 Gen 1 platform is designed with power optimisations for sleek, lightweight smart glasses that enable the user to capture, share or live-stream hands-free, directly from the glasses. On-device AI enables personal assistant experiences such as audio quality enhancement, visual search and real-time translation. There is also support for a visual heads-up display to enable content consumption, including video, that blend seamlessly in the users’ field of view.

The platforms were developed in close collaboration with Meta and will commercially debut on Meta devices in 2023. The Meta Quest 3 will be powered by Snapdragon XR2 Gen 2 Platform, and Ray-Ban Meta smart glasses collection will be powered by Snapdragon AR1 Platform. Other manufacturers are expected to follow next year.

“At Meta, we’re focused on developing the technologies of the future in mixed reality and smart glasses, as well as the foundational innovations that will one day power our vision for AR glasses,” said Andrew “Boz” Bosworth, Meta’s CTO and Head of Reality Labs. 

“The Snapdragon XR2 Gen 2 and Snapdragon AR1 platforms are the latest purpose-built processors that are designed to power the next generation of MR and VR devices and sleek smart glasses for all,” said Hugo Swart, vice president and GM of XR, Qualcomm Technologies. “The commercial debut of these two platforms with Meta is a further step forward in realizing our joint vision – unlocking premium, all-in-one XR devices and smart glasses that are affordable to users around the globe.”

http://www.qualcomm.com

> Read More

Contactless connections simplify and streamline design, says Molex

The MX60 series of contactless connectivity solutions have been developed to ease device pairing, streamline design engineering and boost product reliability, said Molex.

These low power, high speed, solid state devices feature miniaturised mmWave RF transceivers and built-in antennas in a single package. They deliver faster, simpler, device-to-device communications without the use of physical cables or connectors, said the company. The MX60 solutions can offer seamless device pairing and increased communications reliability for video displays, sleek and light consumer electronics, industrial robotics and devices operating in harsh environments, the company continued.

The MX60 series is based on wireless chip-to-chip technology and more than 350 filed patent applications acquired in 2021 with the purchase of core technology and IP from high-speed, contactless connectivity company, Keyssa. The acquired technology operates at data rates from 1,0 to 5.4Gbits per second on the 60GHz band with no Wi‑Fi or Bluetooth interference.

The first models in the MX60 series replace traditional DisplayPort, Gigabit Ethernet and USB SuperSpeed connectors to reduce development time, cost and risk, explained Molex. An integrated retimer optimises signal integrity at higher data rates.

A space-saving, contactless solution that provides USB2 and other low-speed interfaces is currently in development.

“Every piece of real estate counts when designing smartphones, AR/VR glasses, smartwatches and other consumer devices,” said Walter Rivera, senior manager, wireless connectivity product manager for the Micro Solutions business unit at Molex. “By combining USB2 and other low-speed interfaces in one contactless solution, we will offer product developers a critical head-start as they won’t have to worry about fitting extra components into ever-shrinking form factors,” he added.

The MX60 series also improves the durability of products exposed to harsh environmental conditions, such as dust, moisture and corrosion. The series addresses a variety of applications and devices, including smartphones, AR/VR glasses, tablets, self-driving vehicles, video walls, industrial robotics, medical wearables and wireless docking stations.

The sealed, contact-free solutions provide significant benefits over physical metal-to-metal contacts which can degrade over time and impact product performance and reliability, claimed the company. The contactless connectivity solutions are less prone to risks associated with ingress and repeated motion, including high-vibration and rotational products. The ability to remove diagnostic ports on wirelessly charged devices also can reduce development and production costs while boosting overall product reliability.

Production samples are available for MX60 USB SuperSpeed products, for high vibration and harsh environments, including mobile devices and networking applications, MX60 Gigabit Ethernet, for wireless infrastructure, industrial automation, medtech and networking applications and MX60 DisplayPort main and auxiliary, the high speed replacements for conventional DisplayPort connectors.

Plans are underway to expand the MX60 series further by leveraging Molex’s mmWave antenna, high-speed signal integrity and volume manufacturing expertise.

http://www.molex.com

> Read More

IP and SDK accelerate on-device and edge AI design, says Cadence

AI IP and software tools to address the escalating demand for on-device and edge AI processing have been unveiled by Cadence. The scalable Cadence Neo neural processing units (NPUs) deliver a range of AI performance in a low-energy footprint, said the company and this is claimed to bring new levels of performance and efficiency to AI SoCs.
The Neo NPUs deliver up to 80TOPS performance in a single core, in order to support both classic and new generative AI models. They can also offload AI/ML execution from any host processor, including application processors, general-purpose microcontrollers and DSPs. This is achieved with a simple and scalable AMBA AXI interconnect.
Cadence has also introduced the NeuroWeave software development kit (SDK) which it said provides developers with a “one-tool” AI software solution across Cadence AI and Tensilica IP products for no-code AI development.
“While most of the recent attention on AI has been cloud-focused, there are an incredible range of new possibilities that both classic and generative AI can enable on the edge and within devices,” pointed out Bob O’Donnell, president and chief analyst at TECHnalysis Research. For these intuitive, intelligent devices to be realised will need a flexible, scalable combination of hardware and software solutions with a range of power requirements and compute performance, “all while leveraging familiar tools” he believed. “New chip architectures that are optimised to accelerate ML models and software tools with seamless links to popular AI development frameworks are going to be incredibly important parts of this process,” he added.
The Neo NPUs are suitable for power-sensitive devices as well as high-performance systems with a configurable architecture. SoC architects will be able to integrate an optimal AI inferencing solution in a range of products, including intelligent sensors, IoT and mobile devices, cameras, hearables/wearables, PCs, AR/VR headsets and advanced driver-assistance systems (ADAS). New hardware and performance enhancements and key features/capabilities include:
The single core NPUs are scalable from 8GOPS to 80TOPS, with further extension to hundreds of TOPS with multi-core devices, said Cadence. They support 256 to 32K MACs per cycle, allowing SoC architects to optimise embedded AI to meet power, performance and area (PPA) tradeoffs.
Offloading of inferencing tasks from any host processor (e.g., DSPs, general-purpose microcontrollers or application processors) significantly improves system performance and power, said Cadence.
Support for Int4, Int8, Int16 and FP16 data types across a wide set of operations that form the basis of CNN, RNN and transformer-based networks allows flexibility in neural network performance and accuracy tradeoffs while the NPUs offer up to 20 times higher performance than the first-generation Cadence AI IP, with two to five time the inferences per second per area (IPS/mm2) and five to 10 times the inferences per second per Watt (IPS/W)

Upgrades to the common software toolchain include the NeuroWeave software development kit (SDK). Providing customers with a uniform, scalable and configurable software stack across Tensilica DSPs, controllers and Neo NPUs to address all target applications, the NeuroWeave SDK streamlines product development and enables an easy migration as design requirements evolve. It supports many industry-standard domain-specific ML frameworks, including TensorFlow, ONNX, PyTorch, Caffe2, TensorFlow Lite, MXNet and JAX for automated end-to-end code generation, together with Android Neural Network Compiler; TF Lite Delegates for real-time execution and TensorFlow Lite Micro for microcontroller-class devices.
The Neo NPUs and the NeuroWeave SDK are expected to be in general availability beginning in December 2023.

http://www.cadence.com

> Read More

About Smart Cities

This news story is brought to you by smartcitieselectronics.com, the specialist site dedicated to delivering information about what’s new in the Smart City Electronics industry, with daily news updates, new products and industry news. To stay up-to-date, register to receive our weekly newsletters and keep yourself informed on the latest technology news and new products from around the globe. Simply click this link to register here: Smart Cities Registration