StradVision, an industry pioneer in vision processing technology for autonomous vehicles, has announced a partnership with a leading global Tier 1 supplier to develop custom camera technology for autonomous buses.
Work on the project began in fall 2019, and the technology developed will be implemented by multiple OEMs once completed. A date when these vehicles will see real-world road use has not yet been determined.
StradVision CEO Junhwan Kim said that with mass transit being so popular around the world, autonomous buses are high on the list of mobility projects that StradVision’s software can help to advance. “As we determine our priorities for StradVision’s deep learning-based SVNet software, it’s important to recognise the significant role that mass transit plays in the lives of so many people worldwide. With the precise abilities of our software to detect objects and read traffic signs and traffic lights, we can push forward the arrival of autonomous mass transit vehicles as the wave of the future.”
The project will partner StradVision’s SVNet software with the NVIDIA Xavier chipset platform, and will focus on three key areas: Object Detection (OD), Traffic Sign Recognition (TSR) and Traffic Light Recognition (TLR). These three elements will play a key role in allowing the vehicles using the technology developed from this partnership to accurately navigate the roadways when in self-driving mode. StradVision’s SVNet software is designed to function properly, even in poor lighting or weather conditions. It features three key components: SVNet External, SVNet Internal and SVNet Tools. For this project, SVNet External will be the focus.
With a focus on deep learning, StradVision’s lightweight and highly compatible software is leading the industry in terms of vision processing gains. Other projects currently being developed using StradVision’s vision processing software include a Level 4 automated bus in Germany; a sedan in Germany; and SUV, sedan and bus projects in China.
By 2021, StradVision will have nearly 7 million vehicles on the world’s roadways using SVNet software, which is compliant with standards such as Euro NCAP and Guobiao (GB) in China. StradVision is already deploying ADAS vehicles on Chinese roads.