• The newly launched computer vision development platform named XINK is both a platform-as-a-service and a hardware and software development kit.  
  • Things to note are its high-performance compute power, AI accelerator, input/output controls, and video capabilities.  

Artificial Intelligence (AI) startup eYs3D Microelectronics Co. is releasing a new development platform that offers computer vision-based image processing capabilities for autonomous robotic applications and smart city devices. 

XINK, the computer vision development platform by eYs3D, was announced at the Consumer Electronics Show in Las Vegas. It acts as both a hardware and software development kit and a platform-as-a-service. It aims to give a better cost-effective solution for programmers looking to help robots that are used in industrial, object recognition, retail and agricultural industries with field analysis, obstacle detection, and route planning capabilities. 

The startup states that the modular XINK platform comes with all that a developer requires to add such capabilities to their robots: an AI accelerator, flexible communications peripherals, high-performance compute power, input/output controls, smart power management capabilities, and machine vision subsystems. 

Also, it can be easily integrated with most robots and is designed to handle all the low-level programming tasks linked with computer vision. It allows developers to cut-and-paste programming for application-specific designs, thereby saving time consumed in writing codes. 

XINK’s processing power comes from eYs3D’s personalized new eCV1 AI chips which have a four-core Arm 64-bit central processing unit and a 4.6-teraflops neural processor that allows crunching its way through huge volumes of data. Also, there exists an additional Arm Cortex M4 processor that is used as a microcontroller. 

The video capabilities of the platform are also impressive, with XINK supporting H.264 compression for video streaming, additionally with Imaging Signal Processing. It can accept image data from both ISP software code and external ISPs integrated with XINK CPU. 

The company is expecting a lot of interest in its platform, citing data from Grand View Research that tells the global autonomous robot market will grow to USD 10.66 billion by 2030, with a yearly growth rate of 16.88% from 2022. 

Experts’ Say 

James Wong, Chief Strategy Officer of eYs3D, said, “New technologies have enabled surging market growth for mobile robotics. Mobile autonomy must be accompanied by advances in computer vision to enable new areas of robotic deployment, including accurate picking and packing; moving, sorting, and efficiently storing items; autonomous navigation; and other markets. Our XINK platform will allow rapid, one-stop development of vision capabilities for these applications, and we expect to host a community of developers who will both provide and benefit from contributed building blocks.”