Lattice Semiconductor demonstrates how the CertusPro-NX FPGA bridges an image sensor to a Raspberry Pi, performing on-device pre-processing and object detection before passing data to the host CPU. Sensor frames at 30 fps are fed into the FPGA, where an object detection model — trained on eight automotive object classes — runs locally and outputs bounding boxes alongside the video stream. By offloading inference to the FPGA, the design reduces the volume of data transferred between sensor and compute, lowering both power consumption and latency. The object detection model is available on Lattice’s GitHub and can be further trained for custom use cases. Learn more about the Lattice sensAI™ solution stack at latticesemi.com.
