AI edge computing and automotive computing solutions provider Blaize has teamed up with eYs3D Microelectronics, an image processor solution provider enabling enhanced 3D computer vision for edge AI.
The companies have announced a reference design for the Blaize Pathfinder P1600 SoM, which is integrated with the eYs3D Depth Camera product line of 3D cameras. The camera line has unique stereo vision capabilities, delivering an extremely high level of accuracy of depth and optimal range. They are utilized in both indoor and outdoor AI-based autonomous operation, including robotics, security, touchless control, autonomous vehicles, and smart retail.
Lessening Reliance on LIDAR
These advanced capabilities could enable less reliance on Lidar implementations for robotics and other services, which come at a high cost.
Rajesh Anantharaman is Sr. Director of Products at Blaize.
“The Blaize and eYs3D collaboration showcases the power of the Blaize fully programmable GSP architecture and software productivity suite to process both RGB camera data and depth data in a highly efficient manner to provide both high accuracy and high performance for 3D sensor fusion applications at the edge.” said Anantharaman. “The Blaize and eYs3D integration enables faster time-to-market for systems incorporating visual simultaneous location and mapping (VSLAM), facial feature depth recognition, and gesture-based commands.”
The combined design takes advantage of the Blaize Graph Streaming Processor (GSP) architecture, and it offers better depth and distance sensing through the camera’s 3D sensor application. The 3D sensor application includes a sensor fusion function that enables a combination of two sets of data – RGB camera data and Depth data.
“Performance per watt” system metrics can be reduced through processing efficiency and user-friendly programmability for the entire end-to-end application. The Blaize P1600 can also convert the depth camera’s USB output to high-speed Ethernet connectivity, which enables enhanced video processing.
There are also software development kits for the reference design, and they can be used with various operating systems, programming languages, and development tools.
James Wang is eYs3D’s Chief Strategy Officer.
“We are excited to partner with Blaize to bring advanced computer vision capability to market, such as filtering, depth-sensing fusion, real-time 3D point cloud compression and streaming, that further enhance edge AI capability,” said Wang. “Depth-sensing technology has been widely adopted commercially in consumer and industrial applications in the last few years. eYs3D is a leader in 3D-stereo vision and its technology has already been used in popular VR headsets, robot arm visual systems and facial recognition kiosks. We are now seeing growing applications in robotics, 3D scene learning, drones, smart retail and other markets.”
The Blaize embedded and accelerator platforms are built on the Blaize Graph Streaming Processor (GSP) architecture, which is designed for edge computing. The Blaize AI Software Suit is made up of Blaize Picasso and AI Studio, and it leads the industry with open standards and ease of accessibility, which helps reduce the time it takes for edge applications to make it into production. With the new software, the time frame is reduced from months to days.
The Blaize Pathfinder P1600 embedded Systems on Module (SOM) improves the embedded AI applications deployed at the sensor or network edge by bringing the programmability and efficiency benefits of the GSP.
- Vianai’s New Open-Source Solution Tackles AI’s Hallucination Problem
- AI & AR are Driving Data Demand – Open Source Hardware is Meeting the Challenge
- What is a ChatGPT Persona?
- PyCharm vs. Spyder: Choosing the Right Python IDE
- “Brainless” Soft Robot Navigates Complex Environments in Robotics Breakthrough