User Background Blurring Demonstration

AI/ML Accelerated User Privacy Solution

As edge devices become more and more aware of users and context of usage, devices such as PC, peripherals and personal assistance devices with video calling capability can implement intelligent user segmentation and background bluring for more private and collaborative experiences.

Low Power Accelerated Scene Segmentation – This demonstration provides an implementation of scene segmentation on low power high performance Lattice FPGA.

Highly Customizable - This demo is based on the Scene Segmentation Reference Design and provided with end to end components to allow for modification of the object being detected.

Rapid Implementation - The demo utilizes popular Lattice’s Development Kit, which provide all components from image sensor to output to host system.

Features

  • Accelerated, low-power user background segmentation using CNN based model
  • Total power consumption of the CrossLink-NX 40K is less than 200mW
  • The entire end to end application implemented on FPGA resources including preprocessing of the video stream, scene segmentation using CNN based NN model and the background blurring

Block Diagram

Object Classification demo BD

Documentation

Quick Reference
Downloads
TITLE NUMBER VERSION DATE FORMAT SIZE
Select All
CrossLink-NX Background Segmentation Using VVML Board Demonstration
FPGA-UG-02161 1.0 6/7/2022 PDF 841.9 KB
TITLE NUMBER VERSION DATE FORMAT SIZE
Select All
CrossLink-NX Background Segmentation Using VVML Board Demonstration
6/7/2022 ZIP 517.9 KB

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