Face Tracking

Lattice sensAI Reference Design

This reference design provides an example of how to implement a face/object tracking application based on the Lattice sensAI stack. It includes a SPI, DDR memory interface IP blocks, an image signal processing engine, 8 CNN acceleration engines and an overlay engine to indicate the face in the image.

The reference design is optimized for the ECP5-85K FPGA. While the FPGA logic will be loaded from the external flash memory, the weights and biases are loaded from a SD card, connected to SPI interface.

Features

  • Green box indicates location of face in image
  • Runs @ 14fps with 90 x 90 RGB input
  • Consumes 0.85W of power consumption on ECP5 FPGA
  • Applications include selfie drones, surveillance cameras, smart cameras etc
Lattice sensAI

Jump To

Video

Face Tracking Using ECP5 and CNNsExpand Image

Face Tracking Using ECP5 and CNNs

  • This demonstration identifies and tracks a human face
  • The inferencing is done using Convolutional Neural Networks implemented in the Embedded Vision Development Kit’s ECP5 FPGA
  • Power consumption is less than 1W

Block Diagram

Documentation

Technical Resources
TITLE NUMBER VERSION DATE FORMAT SIZE
Face Tracking Using CNN Accelerator IP - Documentation
FPGA-RD-02037 1.0 5/22/2018 PDF 705.3 KB
Face Tracking Using CNN Accelerator IP Code
1.1 9/25/2018 ZIP 146.4 MB


Like most websites, we use cookies and similar technologies to enhance your user experience. We also allow third parties to place cookies on our website. By continuing to use this website you consent to the use of cookies as described in our Cookie Policy.