Texas Instruments Launches a New Series of Visual Processors to Achieve Scalable Edge AI Performance in Intelligent Camera Applications
Time:2023-08-14
Views:747
In architectural, industrial, and retail automation applications, designers can easily and cost-effectively add visual and AI processing functions to up to 12 cameras
In order to promote the development of edge intelligence based on innovation, Texas Instruments (TI) (NASDAQ stock code: TXN) has launched six ARM based ® Cortex ® The new series of visual processors enables designers to add more visual and artificial intelligence (AI) processing capabilities at lower costs and higher energy efficiency in applications such as visual doorbells, machine vision, and autonomous mobile robots.
This new series includes AM62A, AM68A, and AM69A processors, supported by open source evaluation and model development tools, as well as general software that can be programmed through industry wide application programming interfaces (APIs), frameworks, and models. By utilizing this platform composed of visual processors, software, and tools, designers can easily develop and extend edge AI designs across multiple systems, while reducing product time to market. For more information, please refer to www.ti.com edgeai.
Sameer Wasson, Vice President of Texas Instruments‘ Processor Division, said, "In order to achieve real-time response in the field of electronic devices that are closely related to global development, it is necessary to make decisions locally and improve power efficiency. This new affordable and highly integrated SoC processor family supports the use of more cameras and visual processing capabilities in edge applications, thus realizing the future of embedded AI
Implementing Scalable AI Camera Performance at Edges Using Visual Processors
When implementing visual processing and deep learning functions in low-power edge AI applications, Texas Instruments‘ new visual processor brings intelligence from the cloud to the real world by eliminating cost and design complexity barriers.
These processors adopt a System on Chip (SoC) architecture that supports extensive integration. The integrated components include ARM Cortex-A53 or Cortex-A72 central processing units, third-generation Texas Instruments image signal processors, internal memory, interfaces, and hardware accelerators, which can provide AI processing capabilities ranging from 1 trillion to 32 trillion operations per second (TOPS) for deep learning algorithms.
The visual processors in this series include:
AM62A3, AM62A3 Q1, AM62A7, and AM62A7-Q1, which can support one to two cameras less than 2W in applications such as doorbell cameras and smart retail systems. This series includes the industry‘s low-cost 1 TOPS visual processor AM62A3.
AM68A can support 1 to 8 cameras in applications such as machine vision, as well as AI processing capabilities up to 8 TOPS for advanced video analysis.
AM69A can achieve 32 TOPS AI processing functions 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 using open source free tools
Starting from the second quarter of 2023, designers can shorten the time to market of their edge AI applications through the public beta version of Texas Instruments‘ free open source tool Edge AI Studio. This web-based and feature rich tool allows users to quickly and easily develop and test AI models using self created and optimized models from Texas Instruments, and these models can also be retrained using custom data. For more information about Edge AI Studio, please refer to dev.ti.com/edgeaistudio.
Texas Instruments promises to make the future of embedded systems possible by launching a scalable range of processing products, and these new processors, software, and tools for edge AI applications are built on this promise.
|
Disclaimer: This article is transferred from other platforms and does not represent the views and positions of this site. If there is any infringement or objection, please contact us to delete it. thank you! |
Business consulting
13823761625
Mail me