Weartech-Design Sources / Software Archives - Page 2 of 14

SoM by Variscite brings machine learning to compact, cost-optimised, rugged edge devices

Wed, May 08, 2024

Variscite has announced the newest member of the DART Pin2Pin family for machine learning on edge devices for markets like industrial, IoT, smart devices, and wearables.

At only 55 x 30 millimetres—about half the size of a credit card—the DART-MX93 enables machine learning, even in compact devices. Its energy-flex architecture provides efficient processing; built-in security ensures data and applications are protected.

Similar to the VAR-SOM-MX93 which was already launched by Variscite in 2023, the DART-MX93 is based on the same NXP iMX93 processor with up to 1.7GHz Dual Cortex-A55, and 250MHz Cortex-M33 real-time co-processor, equipped with the Arm neural processing unit Ethos-U65 microNPU. The new SoM includes robust features like 2x CAN bus, 2x GbE, and industrial temperature grade plus a wide range of features and connectivity options: camera inputs, audio in/out, ADC, 2x USB, certified Wi-Fi 6 dual-band 802.11 ax/ac/a/b/g/n with optional 802.15.4, BT/BLE 5.3, and LVDS display outputs.

Variscite offers a broad range of SoMs based on NXP’s i.MX 9 series. The upcoming VAR-SOM-MX91, to be released in parallel with NXP’s iMX91, is ideal for price-sensitive devices. The DART-MX95, powered by NXP i.MX95, was created for powerful edge platforms that demand high performance, high-end graphics, AI/ML capabilities, advanced security and safety functions, and a rich set of high-speed connectivity options.

The DART-MX93 is part of the DART Pin2Pin family that gives Variscite customers a future-proof way to scale their device capabilities with new generations of DART SoMs. This ensures extended longevity for customer products, as well as reduces development time, costs, and risks for future product iterations. From the i.MX8M Mini, through the i.MX8M and iMX8M Plus, to the i.MX 95.

https://www.variscite.com

> Read More

THine introduces camera kit for NVIDIA Jetson Orin NX/Nano

Tue, Apr 23, 2024

THine Solutions have announced the new THEIA-CAM 13MP PDAF camera, THSCJ101, for the NVIDIA Jetson Orin NX and Jetson Orin Nano platforms. Along with its pre-optimised ISP firmware and Linux driver, Jetson users are now able to easily integrate advanced imaging capabilities into their systems.

The THSCJ101 kit is a camera reference design kit for embedded camera applications that are using the NVIDIA Jetson Orin NX or the Jetson Orin Nano platform. The THSCJ101 kit is based on THine’s THP7312-P ISP and Sony’s IMX258 13MP CMOS PDAF image sensor.

THine’s optimised ISP firmware provides ultra-quick autofocus using Phase Detection Autofocus (PDAF) technology and best-in-class image quality. The kit hardware includes all items required to interface with Jetson Orin carrier boards with a 22-pin MIPI CSI-2 input connector, including a camera board in an acrylic case and a flat flexible cable.

The Video4Linux2 (V4L2) driver for the THSCJ101 is also available to control various video functions. The performance of each kit is repeatable for use in high volume production due to our production process to characterise the image parameters of each image sensor and to calibrate the image signal processing to compensate for variation from sensor to sensor.
All technical information including the reference circuit schematics, ISP firmware, and V4L2 Driver are available to customers.

Also, for customers that require unique image performance features, THine can provide a GUI based software development tool that customises the ISP firmware and/or the image sensor selection. As a result, the THSCJ101 can accelerate NVIDIA Jetson Orin NX/Nano platform users’ time-to-market without expensive integration cost or additional effort for developing embedded camera systems.

THEIA-CAM is designed for embedded vision systems. Using and optimising THine’s own ISP, THine offers Best-in-Class image quality and high production quality suitable for any project phase from proof of concept to high volume production. THEIA-CAM supports various operating systems including Windows, macOS, Android, and Linux, and various platforms including Raspberry Pi, Jetson Orin, i.MX 8M families, and MediaTek Genio series. THEIA-CAM addresses wide-ranging camera applications including but not limited to AI + IoT devices, AR glasses, barcode reading devices, biometric devices, bodycams, document scanners, machine vision systems, medical scopes, microscopes, surveillance cameras, vision assistance glasses, and webcams. THSCU101, the first Kit in the family, is a 13MP PDAF USB video class (UVC) Camera

https://www.thinesolutions.com

> Read More

Ceva launches multi-protocol wireless platform IP family to accelerate enhanced connectivity

Thu, Apr 11, 2024

Ceva has launched Ceva-Waves Links, a new family of multi-protocol wireless platform IPs. The integrated offering supports the latest wireless standards to address the surging demand for connectivity-rich chips targeting Smart Edge devices in the consumer IoT, Industrial, automotive, and personal computing markets. These IPs include Wi-Fi, Bluetooth, Ultra-Wideband (UWB), and IEEE 802.15.4 (for Thread / Zigbee / Matter), to offer a range of qualified, easy-to-integrate, multi-protocol wireless communications subsystems, each featuring optimised co-existence schemes and adapted to various radios and configurations.

The Links family leverages the newly rebranded Ceva-Waves portfolio of wireless connectivity IPs, formerly known as RivieraWaves. Ceva-Waves Links100, an integrated, low power, Wi-Fi 6 / Bluetooth 5.4 / 802.15.4 communications subsystem IP for IoT applications is the first IP available in this family and is currently being deployed by a leading OEM customer.

The demand for smaller, low-cost, high-performing, innovative devices with versatile connectivity is driving the need to consolidate multiple connectivity protocols in a single chip. ABI Research reflects on the move from module-level integration to on-die chip integration and forecasts that Wi-Fi plus Bluetooth combo chipset shipments will approach 1.6 billion chips annually by 2028.

The first member of the Ceva-Waves Links family, the Links100, is an integrated, low power, Wi-Fi / Bluetooth / 15.4 communications subsystem IP for IoT applications, with the following key features:
• Wi-Fi 6 optimised for cost-sensitive IoT applications,
• Bluetooth 5.4 Dual Mode, supporting advanced Bluetooth Audio with Auracast, and with a comprehensive suite of Bluetooth profiles
• IEEE 802.15.4 (for Thread, ZigBee, Matter) for smart home applications
• Optimised co-existence scheme for efficient concurrent communications
• Pre-integrated with a low power multi-protocol radio at TSMC 22nm process

With its modular architecture, the Ceva-Waves Links family is highly versatile to meet customers’ needs, leveraging the latest Ceva-Waves wireless IPs. Upcoming Links platforms may include:
• Advanced Wi-Fi 6/6E/7 with MLO, for a variety of use-cases, from power-efficient IoT to high-speed data streaming
• Next generation Bluetooth for Channel Sounding and High Data Throughout
• UWB, supporting FiRa 2.0, CCC Digital Key 3.0, and Radar, for innovative micro-location and sensing features
• Optimised co-existence schemes for each specific configuration
• Pre-integrated radio solutions, including partner and customer’s own technology, to address a wide range of configurations and foundry process nodes

For more information, visit https://www.ceva-ip.com

> Read More

ST boosts sensing creativity with new all-in-one MEMS Studio desktop software solution

Thu, Mar 28, 2024

ST’ MEMS Studio is a new all-in-one tool for MEMS sensor evaluation and development, connected closely with the STM32 microcontroller ecosystem and available for Windows, MacOS, and Linux operating systems.

By unifying the sensor-development workflow, from evaluation to configuration and programming, MEMS Studio accelerates development and simplifies bringing rich contextual awareness to users’ projects. Enhanced features help easily acquire and clearly visualise sensor data to explore the operating modes and optimise performance and accuracy. There are also tools for pre-built library testing, as well as convenient drag-and-drop algorithm creation for intuitive, no-code development of STM32 MCU firmware.

MEMS Studio supports the wide portfolio of ST MEMS sensors, including motion sensors, environmental sensors, and infrared sensors. It provides tools to explore and use all the sensors’ features including the finite state machine (FSM) and embedded edge AI in inertial modules for power-efficient inferencing directly in the sensor. These include creating and managing decision trees in sensors equipped with ST’s machine-learning core (MLC), monitoring interrupts status, and testing advanced features like FIFO, pedometer, and freefall detection embedded in the sensor.

MEMS Studio also offers a new experience for analysing sensor data in runtime and offline, where users can visualise, label, and edit the data for the best algorithm implementation. Spectrogram analysis and fast Fourier transform (FFT) are also available and help understand the sensor signal for the best detection of the sensing application target.

Users can choose from a wide variety of compatible development boards, including STM32 Nucleo expansion boards, sensor adapters, and ST’s multi-sensor evaluation kits. These comprise the SensorTile.box PRO, STWIN.box, and STEVAL-MKI109V3 professional MEMS adapter motherboard with adjustable power settings and a STM32F401VE MCU on-board.

As creative use of MEMS sensors continues to drive innovation in cutting-edge applications, MEMS Studio empowers designers to add new and more advanced functions in next-generation high-tech products. Its release promotes the development of smart appliances, medical wearables, and technology for digital healthcare, smart buildings and factories, robotics, asset tracking, and smart driving.

Consolidating and extending the features of established sensor-development tools including AlgoBuilder, Unico-GUI, and Unicleo-GUI, MEMS Studio is available now to download, free of charge, from https://www.st.com/mems-studio.

> Read More

SoM by Variscite brings machine learning to compact, cost-optimised, rugged edge devices

THine introduces camera kit for NVIDIA Jetson Orin NX/Nano

Ceva launches multi-protocol wireless platform IP family to accelerate enhanced connectivity

ST boosts sensing creativity with new all-in-one MEMS Studio desktop software solution

About Smart Cities