NewsSTMicroelectronics and eYs3D Microelectronics to showcase collaboration on high-quality 3D stereo-vision camera...

STMicroelectronics and eYs3D Microelectronics to showcase collaboration on high-quality 3D stereo-vision camera for machine vision and robotics at CES 2023

Category articles

STMicroelectronics (NYSE STM) is a global semiconductor company that serves customers across the full spectrum of electronics including eYs3D Microelectronics, the fabless semiconductor design house which concentrates on the complete system software and hardware that support computer vision, including advanced vision-processing Systems-on-Chip (SoC) devices. They will unveil the outcomes from their partnership on superior machine vision during CES 2023, which will be held in Las Vegas on January 5-8.

With live demonstrations, companies will demonstrate how stereo videos and a depth camera that is based on the latest active-coded infrared technology can improve capabilities like feature recognition as well as autonomous guidance within the mid-to-long range. “STMicroelectronics’ advanced image sensors, using proprietary process technologies, offer class-leading pixel size while offering both high sensitivity and low crosstalk,” said James Wang, Chief Strategy and Sales Officer of eYs3D Microelectronics. “Such advanced image sensors with a price that is competitive, let us achieve a small size systems while still delivering superior machine-vision performance.

The close relationship we’ve established with ST makes us more confident in developing new products that can lead the market for machine vision.” “The partnership with eYs3D Microelectronics through their experience in the field of capture, perception understanding and 3D-fusion, provides ST further possibilities for business, usage cases and ecosystems to meet the demand to use stereo vision for the field of applications like robots, home automation appliances for homes and many more,” said David Maucotel Business Line Manager for the ST Imaging Sub-Group.

“While the reference designs showcased at CES are using monochromatic sensors, we can already foresee exciting enhancements and further use-cases using the RGB and RGB-IR versions of our sensors.” The CES demonstrations feature two reference designs that were jointly developed The Ref-B6 and the Ref B3 ASV (Active Stereo Vision) depth and video cameras. They each incorporate the eYs3DCV processor as well as the eSP876 stereo 3D Depth-Map chip together with ST’s global shutter sensors that offer increased near-infrared (NIR) sensitivities. Its embedded eYs3D chipset boosts edge detection, enhances noise reduction in depth, and produces HD-quality 3D depth data , up to 60 frames per second. ST’s image sensors permit cameras to produce streams of data with various combinations of depth resolution, video and frame rates to ensure the highest quality depth sensing as well as point-cloud creation. Furthermore, optimized lenses filters, filters and a VCSEL active IR projector source maximize the infrared optic path, and increase the ability to block background light sources. A specially designed control algorithm is used to turn on and off the IR projection source on at random intervals to enable the capture of non-artifact gray-scale images.

By leveraging this sophisticated technology, the RefB6 stereo-video camera can achieve an 8-centimeter baseline and 85deg(H) in 70deg(V) the depth of field. Both eYs3D reference designs come with an SDK (Software Development Kit) which supports Windows(r), Linux and Android OS environments with multiple different programming languages as well as wrapper APIs. eYs3D will exhibit the Ref-B6 development joint Camera at two booths: LVCC, Booth #15769, Central Hall and Venetian, Eureka Park, Booth #62500 AT1, Hall G. Please contact your local sales representative or example@gmail.com to set up appointments or customer presentations. Note to editors: Artificial Intelligence of Things (AIoT) is the result of the combination with Artificial Intelligence (AI) technologies with technology and the Internet of Things (IoT) infrastructure. Point clouds are an unidirectional set of points scattered across space. These points can be an 3D shape or an object.

Michal Pukala
Electronics and Telecommunications engineer with Electro-energetics Master degree graduation. Lightning designer experienced engineer. Currently working in IT industry.

News