
Continental, videantis join forces for AI-based cameras
Videantis’ SoCs sourced from a leading global semiconductor supplier for a smart camera program are based on the Hanover, Germany based sartup’s proprietary processing architecture and are accompanied by programming tools originating from this company. For making optimal use of this high-performance, ultra-low-power processors platform and accelerating projects time to completion, Continental relied on the software IP, tools and unique expertise of videantis as the inventors of this technology.
“Videantis processor IP was the key ingredient for us to decide on this hardware platform. During the cooperation, videantis already proved to be a vital technology partner”, said Sascha Semmler from the Advanced Driver Assistance Systems business unit at Continental. Semmler expressed his belief that the deal will Continental to deliver a range of best-in-class features while meeting stringent quality and functional safety requirements to enhance the user experience and driving safety.
The versatility of the videantis processor architecture is said to allow a wide variety of vision and imaging algorithms to run on the same architecture. The architecture is fully software programmable, allowing feature upgrades and algorithm improvements over time. This enabled the development of very small cameras and to address a wide range of active safety use cases such as automatic braking for pedestrians, warning for crossing traffic, and assist in driving with a trailer.
Continental licensed both computer vision and image processing software libraries from videantis, as well as development tools that aid in software development and production sign-off for the cameras. For a successful project completion, automotive quality requirements and processes that include adhering to Automotive SPICE and ISO26262 had to be fulfilled.
Continental: https://www.continental.com/en
videantis GmbH: https://www.videantis.com/
Related articles:
AI processor platform integrates into autonomous driving chip
AI platform for autonomous cars reconfigures on the fly
European research centers unite on neuromorphic memory
videantis claims 1000x performance boost on deep learning applications