CES 2020: StradVision to showcase breakthroughs in AV vision processing technology

Posted On Monday, 06 January 2020 23:39 Written by
Rate this item
(0 votes)
StradVision's deep-learning based vision processing technology for self-driving vehicles will be demonstrated at CES 2020 StradVision's deep-learning based vision processing technology for self-driving vehicles will be demonstrated at CES 2020 Photo courtesy of StradVision

When CES 2020 opens on Jan. 7 in Las Vegas for its four-day run, one major theme will be the visions of the technological future being presented by its many participants. StradVision, an industry leader in vision processing and perception technology for Autonomous Vehicles, will be on site at CES showcasing their vision literally — demonstrating up-close how their SVNet softwarewill provide the eyes that guide the Autonomous Vehicles (AVs) and ADAS systems of the future, including vehicles headed to roadways in 2020.

StradVision CEO Junhwan Kim said the company’s vision processing software will be a central component of AVs becoming a reality for the masses.

“The deep-learning based vision processing technology we are developing at StradVision will be a cornerstone of AV success,” Kim said. “We are excited to have an opportunity at CES 2020, one of the biggest events in the world, to show both the world and other technological pioneers the critical components that StradVision will be contributing as Autonomous Vehicles become the norm in years to come.”

Home base for StradVision at CES 2020 will be the Westgate Las Vegas Resort and Casino, which is adjacent to the Smart Cities and IoT Infrastructure display areas at CES. In the Suite, StradVision’s leadership and technical teams will offer demonstrations of multiple perception-based safety technologies related to their SVNet software, including:

  • Renesas V3M (Tiny SVNet: the smallest deep-learning algorithm for ADAS)
  • Renesas V3H (robust, deep learning-based front camera ADAS system)
  • Ambarella CV22 (running ADAS & Driver Monitoring on one platform)
  • Texas Instruments TDA2x (Surround View Monitoring)
  • New Feature - Animal Detection
  • New Feature - Road Mark Detection
  • New Feature - License Plate Detection

On-site media can contact the StradVision team directly at This email address is being protected from spambots. You need JavaScript enabled to view it..
The team on-site for StradVision will include: Junhwan Kim, CEO; Hongmo Je, CTO; Sunny Lee, COO; Jaewon Sung, VP Engineering; Dean Kim, BD Director; Jinseok Lee, Optimization Engineer; John Oh, Marketing Manager; and Helena Koo, PR Manager.

In addition to its offerings in the suite, StradVision has multiple partnerships on site at CES.

  • A fully optimized SVNet will be ported on Ambarella’s CV22 system on chip (SoC), showing the flexible nature of the software, as well as Ambarella’s ability to accommodate sophisticated deep learning-based algorithms to execute complex functions necessary to operate AVs.
  • StradVision’s SVNet softwarewill leverage resource protection architecture of the Green Hills INTEGRITY® real-time operating system to safely and reliably executeits deep learning-based embedded perception algorithms. The CES demonstration showcases the collaboration between the two software companies on systems for Autonomous Vehicles currently in development, including a front-camera project with a leading global OEM and Tier 1 supplier for vehicles on the road in late 2020.
  • StradVision and AISIN are collaborating to showcase NVIDIA-based perception demonstrations.

The deep-learning expertise of StradVision, which recently was honored with a 2020 AVT ACES Award, has helped the company lead the way in Object Detection (OD) and Free Space Detection (FSD), and its SVNet External software enables vehicles to execute ADAS and self-driving functions, including: Automatic Emergency Braking, Adaptive Cruise Control, Lane Departure Warning and Blind Spot Detection.

StradVision,which recently announced $27 million in Series B funding, offers a wide range of abilities in the autonomous realm due to the leaner structure of the SVNet network, as well as its flexibility. There are multiple types and iterations of SVNet, increasing its versatility for ADAS systems and autonomous vehicles.

By 2021, StradVision will have millions of vehicles on the world’s roadways using SVNet, which is already compliant with strict standards such as Guobiao (GB) in China. StradVision is continuously expanding in China, and already deploying ADAS vehicles on Chinese roads. StradVision currently has multiple production projects in Europe and China, including work on a Level 4 autonomous bus project in Europe.

— Press release courtesy of StradVision


Matt M. Myftiu

Matt Myftiu has been a journalist for two decades with a focus on technology, NASCAR and autos.

This email address is being protected from spambots. You need JavaScript enabled to view it.

Leave a comment

Make sure you enter all the required information, indicated by an asterisk (*). HTML code is not allowed.

Search Reviews by Make

AutoTechReviews  is your home for In-depth reviews of the latest cars, trucks, and SUVs; information on all the emerging vehicle technology; and breaking news from the world of NASCAR and other motorsports.