Edge AI Using Cameras, 3D Time-of-Flight, and NVIDIA Jetson
Key Document
Download D3 Engineering Brings AI to Life White PaperComplete this form to access: “D3 Engineering Brings AI to Life White Paper”
"*" indicates required fields
Artificial Intelligence System Using 2D/3D MIPI CSI-2 Cameras and NVIDIA Jetson Modules
Visual input is driving Edge AI and the need for multi-sensors processing in low power, high performance compute systems. An AI system which allows you to run demanding AI algorithms at video rates can be created by combining MIPI CSI-2 cameras with the NVIDIA Jetson Platform. The MIPI CSI-2 image sensors output raw data directly from the image sensor with no need for conversion or compression, and without as much protocol overhead as an Ethernet or USB data link. The MIPI CSI-2 camera’s full-resolution and uncompressed video feed provides high-quality data, and these cameras can be placed exactly where they need to be via SerDes link. The Jetson’s ISP and GPU, and other accelerators, enables the processing of data at high frame rates.
Features
- Configurable starter kit hardware
- Compatible with Jetson AGX Xavier, Xavier NX, TX2 NX, and TX2
- Up to 16x cameras supported per Jetson module by the hardware
- Hardware-level synchronization options
- 2D RGB Cameras
- 1-8 megapixel resolution
- Global or rolling shutter options
- 3D Time-of-Flight Camera
- VGA resolution, 30 fps
- Up to 6m range
- 940 nm illumination
- FPD-Link III or GMSL2 interface
- Allows remote camera mounting up to 15m
- Power and data over a single coaxial cable
Applications
- Autonomous Robots
- Smart City – Monitoring/Tracking
- AI-based Inspection Systems – Agriculture, Industrial, Etc.
- Factory Automation and Safety
Technical Documents
Tools & Software
Additional Information
Ready to Get Started On Your 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.