Japanese electronics company Renesas has introduced microprocessors with vision-optimised artificial intelligence (AI) accelerators for cameras used in retail and other industrial applications.
  
The RZ/V microprocessors (MPUs) use the firm’s DRP-AI dynamically reconfigurable processor.
 
The demand to have real-time, AI-based person and object recognition functionality in applications such as surveillance cameras for industrial and infrastructure as well as product scanners and PoS terminal cameras has been growing rapidly. However, the higher power consumption and heat generation required for AI processing are introducing new problems for embedded developers.
 
The RZ/V2M leverages the DRP-AI’s power efficiency to realise power consumption down to 4W typical. This eliminates the need for heat sinks and cooling fans, simplifying heat dissipation measures. This lets them be used in compact devices or help to reduce equipment sizes, expanding the opportunities to incorporate AI in embedded devices. It also helps reduce costs.
 
“The new RZ/V series delivers both high performance and low power consumption, the two key issues that are keeping vision AI processing from achieving a higher level of real-time performance,” said Hiroto Nitta, senior vice president at Renesas. “The RZ/V series will dramatically expand the range of AI applications in embedded devices through object recognition, for example cameras in smart shopping cart systems that automatically calculate totals based on the cart items, robots in factories that can safely work together with humans, and medical cameras that assist doctors in making diagnoses.”
 
Each MPU has an imaging signal processor (ISP) that can process high-resolution 4K pixels at 30 frames per second. The ISP uses high dynamic range functionality capable of handling images with large differences between brightness and darkness, noise reduction functionality, and distortion correction functionality to boost precision in AI recognition. This ensures the ability to produce clear images regardless of factors such as the weather, time of day and installation location.
 
The accelerator is an intellectual property (IP) evolved from the DRP built into the RZ/A2M, designed for tasks such as reading 2D barcodes and iris recognition. To magnify operation processing capabilities, the DRP functionality is combined with an AI mac (multiply and accumulate) circuit, making it suitable for applications using AI inference.
 
The IP core is capable of AI processing with approximately ten times the power efficiency of the DRP, achieving the 1Tops/W class. In addition, since the DRP can dynamically change the configuration of its operation circuits every clock cycle, the DRP-AI adds the flexibility to support evolving and advancing AI algorithms.
 
Renesas also plans to offer the DRP-AI translator, a tool for DRP-AI based development that simplifies the implementation of user’s learned AI models into embedded devices.
 
The CPU has dual Arm Cortex-A53 cores with an operating frequency of 1GHz. The device comes in a 15 by 15mm FCBGA package. Samples are available now for early adopters, and mass production is scheduled to start before the end of the year.