Key Document

Download “Dual Camera Capture Using MIPI CSI-2 Cameras and the UP Squared Pro 7000 Application Note”

Dual Camera Capture Using MIPI CSI-2 Cameras, the UP Squared Pro 7000 Powered by the Intel Atom® x7000E Series, and the Hailo-8 AI Accelerator

Edge AI processing is driven by visual input and the need for multiple sensors running on low-power, high-performance computing systems. An AI system that runs demanding AI algorithms at video rates is possible by combining DesignCore® Velocity Series MIPI CSI-2 cameras with the UP Squared Pro 7000 Developer Board (powered by the Intel Atom® x7000E Series), and the Hailo-8 AI Accelerator. The MIPI CSI-2 image sensor outputs raw data directly from the sensor with no need for conversion or compression, and without as much protocol overhead as an Ethernet or USB data link. The cameras provide full resolution and uncompressed high quality video data. With SerDes options, the cameras can be placed exactly where they need to be. The on-board ISP and accelerated hardware enables the processing of data at high frame rates.  


  • Compact Computing Developer Kit
    • Intel Atom® x7000E Series
    • MIPI CSI camera support
    • Intel® UHD Graphics for three simultaneous 4K displays
  • 2 Full-HD MIPI Cameras
    • Global shutter
    • High-speed frame rates
    • High-performance lenses
  • Image Signal Processing (ISP) Tuning for Camera Sensor and Lens
    • Produce high-quality Yuv video and output with excellent image quality
  • Edge AI Processor
    • Enables real-time, low latency & high-efficiency AI inferencing on edge devices
    • AI compute power of 26 Tera-Operations Per Second (TOPS)


  • Robotics
  • Autonomous Vehicles
  • Machine Vision
  • Industrial IoT
  • Drones
  • UAVs

Want to Customize This Solution?

Contact Our Design Services Team

Our design services include full-cycle embedded product development engagements, where you own the resulting IP. We work as part of your development team and follow our proven Define, Design, Deploy development methodology.