BrainChip, Prophesee to deliver “neuromorphic” event-based vision systems for OEMs

Paris-based Prophesee has developed advanced neuromorphic vision systems through their patented sensor design and AI algorithms. Event-based vision systems are expected to take over the traditional frame-based approach to make machine vision more accessible and practical for developers.

“We have successfully ported the data from Prophesee’s neuromorphic-based camera sensor to process inference on Akida with high performance,” said Anil Mankar, co-founder and CDO of BrainChip. “This combination of machine vision sensors with Akida’s ability to process data with improved efficiency, precision and energy-efficient at the point of acquisition advances state-of-the-art AI enablement and offers manufacturers ready-to-implement solutions.”

What is an event-based vision?

The research to evaluate human vision capabilities have taken a big leap over the last couple of years. Existing research shows that humans can gather data from a scene that is changing at a rate of up to 1000 times a second. However, this information is encoded, which is likely impossible for fixed frame-rate cameras to observe using the typical 60 frames per second that high-quality cameras record.

To change this paradigm, event-based sensing has garnered attention. Event-based vision systems rely on each pixel to sense significant change and reduce the recording of redundant data to save processing power, memory and other associated resources.

Basically, event-based vision systems are inspired by the way the human eye works; this miniature vision system enables efficient streaming of visual data for real-time analytics. This vision system has enabled enterprises and manufacturers to track high-speed moving objects, which is far from the capabilities of standard fixed frame-rate cameras. Neuromorphic vision system vendors are developing efficient and advanced machine learning algorithms to achieve higher temporal resolution and lower latency.

Prophesee is known for developing an event-based vision solutions ecosystem that comes with software and hardware integration to enable developers to build advanced used cases for a wide range of markets. Prophesee built 4-sensor generations, with the latest coming from the collaboration between Sony and Prophesee. The Metavision evaluation kit is designed for field testing conditions supported by an IMX636ES sensor inside a 30x30x36 mm box weighing 40 grams.

On the software side of the event-based vision ecosystem, Prophesee’s Metavision Intelligence Suite covers the whole development process from discovery to prototyping and end-application. The software suite provides 95 AI algorithms, 67 code samples and 11 ready-to-use applications. The open-source architecture gives the flexibility to “unlocking full interoperability between software and hardware devices.”

The partnership between BrainChip and Prophesee will give the market more commercially available neuromorphic vision systems for potential applications in autonomous vehicular systems, industrial automation, IoT, security, surveillance, retail automation, and AR/VR.

“By combining Prophesee’s Metavision solution with Akida-based IP, we are better able to deliver a complete high-performance and low-power solution to OEMs looking to leverage edge-based visual technologies as part of their product offerings,” said Luca Verre, CEO and co-founder of Prophesee.”

BrainChip recently announced a collaboration with Edge Impulse to address the growing demands for training AI workloads and inference deployments for large-scale edge AI applications. BrainChip also partnered with RISC-V founding member SiFive to work on deploying edge AI chips for optimized AI/ML compute at the edge.

Article Topics

Brainchip  |  chip  |  computer vision  |  neuromorphic computing  |  Prophesee