Vision AppKit utilizes the Alif Semiconductor Ensemble® MCU family of industry-leading Edge ML MCUs and Telit Cinterion’s power-efficient LTE-M and low-power Wi-Fi and Bluetooth® wireless technology modules
Ultra-compact camera design can perform on-device AI use cases like face and object detection, image classification, and more at a significantly lower power consumption than previously possible for these use cases
Telit Cinterion, an end-to-end IoT solutions enabler, and Alif Semiconductor, a supplier of the most secure, power-efficient Edge AI-enabled MCUs and fusion processors in the market, today announced the Vision AppKit — the world’s smartest and most efficient connected camera reference design.
The Vision AppKit combines Telit Cinterion’s Wi-Fi and Bluetooth wireless technology or LTE-M communication modules in an ultra-compact camera design together with Alif Semiconductor’s Ensemble E3 series MCU, capable of performing on-device AI use-cases like face and object detection, image classification, and more at significantly lower power consumption than previously possible.
The Vision AppKit is a reference design for ultra-low power, small form factor AI-enabled camera that can capture images and/or video, perform AI-based processing in real-time on captured data, and deliver the results wirelessly to a display or other external system. Alif’s E3 Series MCU — known for its EdgeAI capabilities in battery-operated IoT devices — powers this groundbreaking design. Telit Cinterion supports communication in the Vision AppKit with the ME310 LTE Cat-M and WE310 Wi-Fi and Bluetooth Low Energy 5.0 modules.
The Alif Ensemble E3 series features a distinct High-Efficiency MCU core and a separate High-Performance MCU core, along with microNPUs that can be promptly enabled when a device needs additional AI/ML compute performance, to keep the overall system power footprint as low as possible. Alif Semiconductor’s aiPM™ technology dynamically powers only the logic that is in use at any given time thus achieving the lowest overall system power consumption. This combination delivers a performance uplift of at least two orders of magnitude compared to traditional 32-bit MCUs at a power consumption that is two orders of magnitude lower, drastically reducing inference times for AI camera vision-based tasks like object detection, face recognition, and image classification.
Reza Kazerounian, Co-Founder and President at Alif Semiconductor, said:
“The Vision AppKit AI camera reference design incorporates highly efficient processing capability to deliver small form factor camera solutions for object detection and image classification in a secure way.”
“This technology enables battery-operated cameras to perform computations previously only possible in the cloud.”
The ME310 empowers enterprises to implement novel, compact designs across a diverse range of applications, such as asset tracking, healthcare monitoring, smart metering, portable devices, industrial sensors, home automation, and more. This module facilitates enhanced power efficiency in IoT applications through Power Saving Mode (PSM) and extended Discontinuous Reception (eDRX), catering to devices requiring optimization in cost, size, and power consumption. Additionally, the WE310 is a fully integrated module combining single-band Wi-Fi (802.11 b/g/n) and Bluetooth Low Energy (BLE5). It offers a cost-effective and high-speed wireless connection to an embedded microcontroller via UART, SPI, and SDIO interfaces.
“Integrating Alif’s cutting-edge edge AI technology with Telit Cinterion’s industry-leading secure modules opens the path to a new category of intelligent, compact, ultra-low power, and cost-efficient IoT devices,” said Manish Watwani, Chief Marketing and Product Officer at Telit Cinterion. “This integrated design reduces adoption barriers and guarantees optimal AI and communication performance.”
For more information and to see a demo of the Vision AppKit in action at CES 2024, visit Alif Semiconductor’s suite at The Palazzo and Telit Cinterion’s booth #10662.
