Texas Instruments (TI) announced a new family of six Arm Cortex-based vision processors that enable designers to add more vision and artificial intelligence (AI) processing capabilities at lower cost and higher power efficiency in applications such as visual doorbells, machine vision and autonomous mobile robots.

The new family includes the AM62A, AM68A and AM69A processors, supported by open source evaluation and model development tools and common software that can be programmed through industry-common application programming interfaces (APIs), frameworks and models. With this platform of vision processors, software and tools, designers can easily develop and scale edge AI designs across multiple systems while reducing time-to-market.

Enabling Scalable AI Camera Performance at the Edge with Vision Processors

When it comes to implementing vision processing and deep learning capabilities in low-power edge AI applications, Texas Instruments' new vision processors bring intelligence from the cloud to the real world by removing cost and design complexity barriers.

These processors feature a system-on-a-chip (SoC) architecture that supports extensive integration. Integrated components include Arm Cortex-A53 or Cortex-A72 central processing units, third-generation Texas Instruments image signal processors, internal memory, interfaces and hardware gas pedals to provide deep learning algorithms with 1 trillion to 32 trillion operations per second TOPS (IT House Note: Tera Operations Per Second is a processor The AI processing capabilities of the processor.

The vision processors in this family include:

AM62A3, AM62A3-Q1, AM62A7 and AM62A7-Q1, which can support one or two cameras smaller than 2W in applications such as doorbell cameras and smart retail systems. The family includes the industry's lower cost 1 TOPS vision processor, the AM62A3.

The AM68A can support one to eight cameras in applications such as machine vision, as well as up to 8 TOPS of AI processing for advanced video analysis.

The AM69A enables 32 TOPS of AI processing for 1 to 12 cameras in high-performance applications such as edge AI boxes, autonomous mobile robots, and traffic monitoring systems.

Simplify AI evaluation and development with open source, free tools

Beginning in the second quarter of 2023, designers can shorten their time to market for edge AI applications with the public beta version of Edge AI Studio, a free open source tool from Texas Instruments. This web-based, feature-rich tool allows users to quickly and easily develop and test AI models using self-created models and Texas Instruments-optimized models that can also be retrained using custom data.

These new processors, software and tools for edge AI applications build on Texas Instruments' commitment to making the embedded future possible with a scalable processing product family.