BrainChip partners with Prophesee to optimize computer vision AI performance and efficiency

On June 19, BrainChip, a commercial producer of neuromorphic AI IP, and Prophesee, a developer of neuromorphic vision systems, announced a technical collaboration to bring together event-based vision systems with high-level AI performance and ultra-low-power technology. Integrated OEMs provide next-generation platforms.

Image credit: BrainChip

Inspired by human vision, Prophesee's technology uses a patented sensor design and artificial intelligence algorithms that mimic the eye and brain and use standard frame-based techniques to reveal objects that are currently invisible.Prophesee's computer vision systems open up new potential in areas such as autonomous vehicles, industrial automation, IoT, security and surveillance, and AR/VR.

BrainChip's first neuromorphic processor, Akida, mimics the human brain, analyzing only basic sensor input at the point of acquisition, processing data with extreme efficiency, precision and energy economy.Keeping AI/ML local to the chip, independent of the cloud, also significantly reduces latency.

Anil Mankar, co-founder and chief digital officer of BrainChip, said: "We have successfully ported data from Prophesee's neuromorphic-based camera sensor to Akida for processing inference and achieved superior performance. Combining this smart vision sensor with Akida in acquisition The combination of the point's ability to process data with ultra-high efficiency, precision and energy economy is truly advancing advanced AI applications and providing manufacturers with an off-the-shelf solution."

"By combining our Metavision solution with Akida-based IP, we are better able to offer OEMs a complete high-performance and ultra-low-power solution," said Luca Verre, CEO and co-founder of Prophesee. These OEMs want edge-based vision technology as part of their products."