Tuesday, June 25, 2024

Edge AI And Vision Processing Within An Energy Efficient Framework

- Advertisement -

A Computer-on-Module designed for AI edge functions, these power-saving units enhance industrial automation and vision-focused applications.

Computer on module

Congatec, an embedded and edge computing technology vendor, has launched SMARC Module 2.1 Computer-on-Module based on Texas Instruments Jacinto 7 TDA4x or DRA8x processors. The state-of-the-art industrial-grade modules are suitable for top-tier Artificial Intelligence (AI) edge tasks, boasting an ultra-low power (ULP) footprint, dual Arm Cortex-A72 cores, advanced AI accelerators, and enhanced 3D graphics capabilities. Consuming a mere 5 to 10 watts, the modules are designed for industrial mobile machinery necessitating 2D/3D camera, radar, and lidar analytics. This makes them suitable for automated guided vehicles (AGVs), autonomous mobile robots (AMRs), construction, and farming equipment. Furthermore, they shine in vision-centric industrial automation or medical applications that demand potent yet energy-efficient AI processing on the edge.

The SMARC modules are equipped with two Mobile Industry Processor Interface (MIPI) Camera Serial Interface (CSI) camera interfaces. The conga-STDA4, powered by the TDA4x processor, incorporates an Image Signal Processor (ISP), vision accelerators, and readily accessible pre-trained AI models from the TI Model Zoo. This facilitates a smooth transition into the realm of AI-driven application design. Moreover, it features a Robotic SDK, amplifying its capabilities. On the other hand, the DRA8x versions present a budget-friendly alternative, lacking the vision processing accelerators. Engineered for rugged industrial conditions, both module versions can operate in extended temperature ranges from -40 °C to +85°C. They also support Time Sensitive Networking (TSN) and incorporate cybersecurity protections.

- Advertisement -

“By integrating the powerful Texas Instruments JacintoTM 7 TDA4x and TI DRA8x processors in our high-performance SMARC Module 2.1 ecosystem, congatec simplifies the design-in process for this advanced Arm Cortex-A72 based SoC technology. This allows vision-based situational awareness designers in various embedded industries to focus on their core competencies, saving upfront costs and reducing time to market, especially for industrial quantity production”, explains Martin Danzer, Director of Product Management at Congatec.

Industrial OEMs, especially those with limited time and budget for bespoke designs, stand to gain from the SMARC high-performance ecosystem. This system simplifies the design journey, guarantees robust design security, and minimizes one-time engineering (NRE) expenses.

Nidhi Agarwal
Nidhi Agarwal
Nidhi Agarwal is a journalist at EFY. She is an Electronics and Communication Engineer with over five years of academic experience. Her expertise lies in working with development boards and IoT cloud. She enjoys writing as it enables her to share her knowledge and insights related to electronics, with like-minded techies.


Unique DIY Projects

Electronics News

Truly Innovative Tech

MOst Popular Videos

Electronics Components