ZF has taken a six percent stake in South Korean software firm StradVision, a vision processing technology company, to enhance its portfolio of automated driving perception software.
Safe autonomous vehicles need to reliably detect and identify other road users, road markings or traffic signs, including in harsh weather conditions or poor lighting. This is where high-performance software for recognizing the vehicle environment comes in – the StradVision SVNet software allows vehicles to detect and identify objects accurately, such as other vehicles, lanes, pedestrians, animals, free space, traffic signs, and lights. The software, which StradVision said is currently used in high volume models of ADAS and autonomous driving vehicles, relies on deep learning-based perception algorithms, which requires a relatively small amount of memory and has low power consumption. The software supports several hardware platforms and can also be customized and optimized for other hardware systems.
For ZF, autonomous driving (AD) and vehicle software are key strategic areas within its product portfolio. Its AD system solutions for automotive and mobility sectors include high-performance computers such as the ZF ProAI, automotive software supporting ADAS and AD functions, sensors like camera, radar and lidar, and smart actuators.
The CEO of StradVision, Junhwan Kim, added, “We are proud to count ZF as one of our strategic investors. Together with the global mobility specialist ZF, we will strive to speed up the market for autonomous driving with leading perception solutions.”
In December 2021 StradVision highlighted its work with LG Electronics, announcing its camera perception software is being in LG Electronics’ latest ADAS front camera system, and also its cooperation on what it said would be the most advanced cockpit instrument platform based on augmented reality solutions for the global automotive industry.
In the front camera system, StradVision supported development of an algorithm implementing various ADAS functions, including full customization of object detection and free space detection.
In addition to this, the work with LG on augmented reality would aim to address a trend in which automakers are increasingly looking at adopting the technology, and in particular augmented reality head-up displays (AR-HUD). This technology projects important road information such as navigation and various ADAS warnings into the line of sight of drivers, allowing them to keep their eyes on the road while also perceiving the surroundings accurately through real-time interaction with the objects in their path. StradVision said its SVNet software is focused on improving visuals for head-up displays or center screens of automobiles.
- Open lidar API aims to accelerate software-defined lidar adoption
- Robotaxi software platforms take shape