Hand Gesture Detection

Lattice sensAI Reference Design

Our system is going under maintenance on August 13th between 2:00 pm to 10:00 pm Pacific. During this window, the website may not be reachable. For immediate assistance, please contact techsupport@latticesemi.com.

Customizable to detect hand gestures: This design implements a low power AI based system to detect hand gestures using an IR image sensor.

Optimized Power and Performance – iCE40 UltraPlus low power FPGA running the CNN compact accelerator engine is used for processing the images consuming few milli-watts of power.

Complete Reference Design - Training dataset, scripts for training using common Neural Network training tools and NN model are provided to enable modification.


  • AI based on-device gesture detection processing
  • VGG like 8-bits CNN used inside of iCE40 UltraPlus at up to 10 frames per second
  • Adjustable Frame-rate. Can be optimized between power and response time depending on system needs
  • Gestures can be customized based on system needs
Lattice sensAI

Jump to

Block Diagram


Quick Reference
Technical Resources
Select All
iCE40 UltraPlus Hand Gesture Recognition Demo
FPGA-UG-02119 1.0 12/16/2020 PDF 993.2 KB
Select All
iCE40 UltraPlus Hand Gesture Detection - Documentation
FPGA-RD-02206 1.0 12/16/2020 PDF 4 MB
iCE40 UltraPlus Hand Gesture Detection - Project Files
1.0 12/16/2020 ZIP 16.4 MB

*By clicking on the "Notify Me of Changes" button, you agree to receive notifications on changes to the document(s) you selected.

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.