A smaller board connects four cameras and multiple sensors over Ethernet, making it easier to build compact edge AI systems.
Microchip Technology has released Revision 2.0 of its PolarFire FPGA Ethernet Sensor Bridge, a smaller board designed for standardized sensor integration using NVIDIA Holoscan Sensor Bridge (HSB) technology.
The new board is 60% smaller than the first-generation version, supports twice as many cameras, uses USB-C power for easier rack deployment, and is available at a lower price. It replaces multiple sensor interfaces with a 10Gb Ethernet-based connection, helping reduce power use, system complexity, and bill-of-materials costs.
The board is designed for AI applications in medical systems, industrial equipment, and humanoid robotics using NVIDIA edge platforms such as NVIDIA Jetson and IGX.
Based on PolarFire FPGA technology, the board supports up to four cameras and includes a camera connector compatible with NVIDIA Jetson. It also has on-board optical latency measurement circuitry to measure end-to-end latency from sensor capture to AI inference using NVIDIA’s Latency Display Analysis Tool.
For expansion, the board includes an FPGA Mezzanine Card (FMC) connector and supports MIPI CSI-2, I²C, UART, and GPIO interfaces. It can also support sensor and video interfaces such as SLVS-EC 2.0, 12G-SDI, HDMI, and DisplayPort without changing the core platform design. A standard PMOD connector provides additional expansion options.
“Developers want to spend their time building high-value edge AI applications, not stitching together proprietary sensor interfaces,” said Shakeel Peera, vice president of Microchip’s FPGA business unit. “With low power PolarFire FPGA technology at its core, this second-generation Ethernet sensor bridge delivers a power-efficient, secure foundation in a significantly reduced form factor to help teams move faster from development to deployment in edge AI systems.”
Based on PolarFire FPGA technology, the HSB-enabled board supports real-time processing of data from multiple sensors over Ethernet in compact, power-constrained edge systems. Built-in security and safety features help protect edge AI systems and support long-term operation.
Click here for the original announcement.
