StradVision and LG Electronics Develop an Augmented Reality Automotive Cockpit

author: Eric Walz   

Augmented reality (AR) instrument clusters can improve safety with a more visually enhanced view of the road ahead.

StradVision, developer of AI-based vision processing technology for autonomous vehicles and advanced driver assist systems (ADAS), announced that it has teamed up with LG Electronics to develop an advanced vehicle instrument platform, based on augmented reality (AR).

The two companies are working closely together on the development of LG Electronics' next-generation augmented reality solutions that offer drivers a higher level of safety.  

The augmented reality head-up (AR HUD) instrument cluster projects information such as navigation and various ADAS (Advanced Driver Assistance System) warnings to the windshield based on data collected in real-time through sensors installed on the vehicle. 

StradVision was founded in 2014 and was an automotive industry pioneer in AI-based vision processing technology. The company says its accelerating the deployment of fully autonomous vehicles by making powerful ADAS features available to automakers at a fraction of the cost compared with competitors. 

These new types of advanced AR displays help drivers keep their eyes on the road by projecting important road information in their line of sight. It also helps drivers perceive their surroundings more accurately through real-time interaction with the objects on the road. 

The AR instrument cluster technology is expected to become a requirement for enhanced vehicle safety within a few years, according to StradVision. 

"LG Electronics is a strategic partner of StradVision, and we have long been cooperating in the development of the most advanced ADAS technology including the advanced development of LG Electronics' DNN-based next-generation augmented reality solution. We look forward to further expanding our collaboration with LG Electronics to develop cutting-edge technologies for a safer road environment and discover new business opportunities," said Junhwan Kim, StradVision CEO.

Digital instrument clusters have already replaced mechanical gauges in most new vehicles and the advances in electronics and display technology allows automakers to offer more visually dynamic instrument clusters for their vehicles, which includes augmented reality displays. 

StradVision's technology for augmented reality is delivered by its camera perception software called "SVNet", which can help improve visuals for head-up displays or center-mounted screens of vehicles with its robust perception capabilities to identify objects around a vehicle. 

SVNet is deep learning-based perception software that supports advanced driver assist systems (ADAS) features, such as automated highway driving.

SVNet supports semantic segmentation, which is a computer vision technology that classifies objects in an image on a pixel-by-pixel basis using deep learning algorithms to identify cars, pedestrians and road signs. The technology which helps improve how a vehicle perceives its surroundings. 

The technology even works in harsh weather conditions such as rain, snow or in darkness for an added layer of safety for automated driving systems.

StradVison's SVNet software provides the most enhanced vision perception features, including depth-map solution which uses innovative "pseudo LiDAR" technology that replaces traditional laser-based LiDAR sensors, which are costly for automakers due to their high performance requirements The pseudo lidar technology offers high precision distance measurements of 3D objects using only a mono-channel camera. It essentially treats camera output as if it were lidar data.

The technology mimics how traditional lidar scans an environment and has the potential to significantly reduce the use of expensive lidar for building self-driving capable vehicles at scale. 

When StradVision's SVNet is paired with LG's world leading high definition display technology as part of a vehicle's instrument cluster, it can offer drivers a more visually enhanced, AR view of the road ahead.

SVNet can also be used for lane Detection, Lane Departure Warning, Lane Keeping Assistance System and Lane Centering Assist. The highly efficient SVNet software relies on deep learning-based perception algorithms and requires dramatically less memory and low power requirements. 

StradVision's SVNet is currently used in mass production models of ADAS and autonomous driving vehicles that supports SAE Levels 2 to 4 autonomous driving systems.

StradVision's SVNet is currently being deployed on various vehicle models in partnership with OEMs, including Mercedes-Benz.

In November, LG Electronics and Mercedes-Benz were named joint winners at the annual AutoSens Awards, which recognizes cutting edge autonomous driving ADAS technology. The Hardware Development of the Year award was given to LG for successfully commercializing its vehicle front camera technology, which is available in the new 2021 Mercedes-Benz C-Class.

StradVision is based in Seoul, South Korea, with additional offices in Silicon Valley, Tokyo, and Munich. 

Eric Walz

Originally hailing from New Jersey, Eric is a automotive & technology reporter covering the high-tech industry here in Silicon Valley. He has over 15 years of automotive experience and a bachelors degree in computer science. These skills, combined with technical writing and news reporting, allows him to fully understand and identify new and innovative technologies in the auto industry and beyond. He has worked at Uber on self-driving cars and as a technical writer, helping people to understand and work with technology.