Arm Introduces New Automotive Image Signal Processor to Accelerate Driver Assistance and Automation

News Highlights.

– Mali-C78AE Image Signal Processor (ISP) is a new member of Arm’s “AE” product family with functional safety, processor IP for Advanced Driver Assistance Systems (ADAS) and human vision applications

– Mali-C78AE with Cortex-A78AE CPU and Mali-G78AE GPU provides superior ADAS image data processing pipeline

– Mobileye First to License Mali-C78AE with Mali-G78AE for Next Generation EyeQ Technology

Arm announced the launch of the Arm Mali-C78AE ISP, adding to its portfolio of IP designed for performance and safety in automotive applications. Paired with the Cortex-A78AE and Mali-G78AE, the Mali-C78AE delivers a complete ADAS image data processing pipeline that optimizes performance, minimizes power consumption, and provides a consistent approach to functional safety to drive the next phase of ADAS volume production introduction.

Arm Mali-C78AE

According to a recent report by research firm Strategy Analytics, the automotive camera market is expected to grow by more than 19% in value from 2020 to 2025, making it the most important sensor for providing vehicles with the data they need to make decisions about their surroundings. The market is expected to grow by more than 19 percent from 2020 to 2025, making it the most important type of sensor for providing vehicles with the data they need to make decisions about their environment.

As the number and sophistication of in-vehicle cameras increase, the arithmetic power to efficiently and securely convert high-throughput image data into outputs that meet the varying requirements of machine and human vision needs to increase accordingly,” said Chet Babla, vice president of Arm’s Automotive and IoT Business Unit. C78AE meets the industry’s need for a new approach to image processing that will help enable new capabilities for ADAS and autonomous driving.”

Human and machine vision requires safety first

The Mali-C78AE is designed for the human and machine vision safety applications required by various ADAS functions and is capable of processing data from up to four live cameras or 16 virtual cameras.

The Mali-C78AE was developed from the ground up with hardware safety mechanisms and software diagnostics to enable system designers to meet the requirements of ISO 26262 ASIL B functional safety. The Mali-C78AE is designed to prevent or detect faults in a single camera frame that could lead to frame data processing errors. To do this, the ISP has more than 380 fault detection circuits, continuous built-in self-test, and detection of sensor and hardware faults in connected cameras.

Vision processing requires large amounts of data and high workload requirements

Processing speed is a key element of the Mali-C78AE, no less important than security and user experience. For example, the process of acquiring an image from a sensor, processing it successively through the ISP and GPU, and then displaying it on the screen for the driver to view should be completed within 150 milliseconds; if the process takes longer than 150 milliseconds, the driver will notice a delay in the image when using features such as parking assistance. In machine vision applications, the vehicle should not move more than 250 mm from the time the camera image is acquired to the time the decision is made; if this distance is exceeded, the machine vision system is too slow to respond to the accurate and timely decisions required by the driving environment.

The Mali-C78AE uses advanced noise reduction technology and dynamic range management to ensure that each frame is clear and properly exposed by adjusting for areas that are too dark or too bright. The Mali-C78AE is capable of processing up to four high-resolution, high-frame rate cameras in real time, significantly reducing memory, communication and processing requirements, thereby increasing system efficiency.

By adjusting areas of the frame that are too dark or too bright, Mali-C78AE ensures that every frame is sharp and properly exposed (Figure 2).

Currently, a separate camera setup is required to implement multiple ADAS functions because cameras used for machine vision applications (e.g., lane departure warning) do not produce images suitable for human vision, such as surround view. To reduce the cost of implementing multiple ADAS functions, the Mali-C78AE enables dual use of camera sensors by scaling down and color converting sensor outputs suitable for machine vision to create images suitable for the human eye. By avoiding duplicate deployments of cameras and their associated electronics and wiring harnesses, OEMs can save costs and reduce complexity, leading to wider deployment of camera-based ADAS capabilities across a wide range of vehicles, providing drivers with a safer, better user experience.

Industry Pioneers Adopt Powerful ADAS Image Data Processing Pipeline

As a pioneer in automotive vision safety technology, Mobileye has pioneered the adoption of the new Mali-C78AE ISP in its next-generation EyeQ technology. mobileye chose the Mali-C78AE for the development of Mobileye EyeQ Ultra and EyeQ6H at the outset for efficient image data processing, and by pairing it with the Mali-G78AE GPU, it enables secure, smooth, real-time and intuitive graphics rendering to meet demanding automotive needs.

By combining Arm ISP and GPU technology to enable panoramic visualization capabilities, we can provide a centralized computing solution with a single SoC to enable the most advanced ADAS and parking assistance systems with a single SoC.”

Intel Core i7 12700K

[Reseller] Mall

[Product Price] $3199

Intel Core i7 11700KF Eight Cores, Sixteen Threads, RWD up to 5.0GHz

[Distributor] Store

[Product Price] $2299

Seven Rainbow iGame GeForce RTX 3070 Ti Ultra W OC 8G

[Distributor] Store

[Product Price] $6299