StradVision’s SVNet software allows vehicles to detect and recognize objects on the roads. It is said to perform well even in harsh weather conditions and is able to prevent traffic accidents by processing collected road data with high speed and accuracy. Compared with competitors, SVNet claims to be compact to require dramatically less memory capacity to run, and to consume less energy. Thanks to the company’s patented Deep Neural Network enabled software, it can also be customised for any hardware system.
SVNet is currently used in mass production models of ADAS and autonomous driving vehicles that support safety function Levels 2 to 4, and will be deployed in more than 9 million vehicles worldwide. It can also be customised for any hardware system It can also be customised for any hardware system.
“It is now possible to provide object detection with high recognition accuracy that is optimized for vehicle-mounted camera systems”, said Koichi Yamashita, Head of the Automotive Business Unit, Automotive & Industrial Business Group at Socionext. “Software like SVNet can detect vehicles, pedestrians, lanes, and free space. In the automotive market, where significant growth is expected in the future, we will actively utilize StradVision's software with the aim of providing custom SoCs that are a source of customer differentiation and competitiveness.”
Related articles:
Hyundai Mobis to develop deep learning cameras with AI startup StradVision
Fujitsu Semiconductor Europe repositions itself as a distributor
Socionext brings automotive and Edge AI technology to Embedded World
