User Tracking and Onlooker Detection Demonstration

CNN accelerated user detection and tracking using Low Power Lattice FPGAs

The Lattice sensAI smart vision sensing technology tracks device user's attention and intent to use making edge devices smarter and more aware of their surroundings than ever before.

Protecting User Privacy by tracking onlookers and their intent to look onto the user screen content, Lattice vision sensing technology safeguards the user data against visual hacking.

User Tracking and Onlooker Detection - Vision sensing technology safeguards the user data against visual hacking by tracking onlookers and their intent to look onto the user screen content.

Mobilenet Human Identification - Demonstration uses machine learning to identify different human faces. A CNN acceleration engine is trained to deliver accurate identification by extracting 256 16-bit characteristics from each registered face.

3D Head Pose Demonstration - The 3D head pose solution aims to revolutionize human face detection by not only identifying facial features but also providing detailed parameters essential for a comprehensive understanding of facial orientation. To learn more about this product design and request the complete source code, click here to contact us.

Features

  • Based on Mobilenet v1 network
  • Accelerated, low-power object detection demo
  • Processing at up to 60 FPS and 160x160 resolution
  • Detect the main user and onlooker and their focus on the user screen
  • Total application power consumption of CrossLink-NX FPGA is less than 80 mW

Block Diagram

Object Classification demo BD

Documentation

Quick Reference
Downloads
TITLE NUMBER VERSION DATE FORMAT SIZE
Select All
CrossLink-NX QVGA Mobilenet Human Identification on VVML Board Demonstration - User Guide
FPGA-UG-02141 1.0 11/10/2021 PDF 1.6 MB
CrossLink-NX User Tracking and Onlooker Detection on VVML Board Demonstration - User Guide
FPGA-UG-02140 1.1 8/2/2024 PDF 1.7 MB
CrossLink-NX 3D Head Pose on VVML Board Demonstration - User Guide
FPGA-UG-02199 1.0 12/5/2023 PDF 1.2 MB
CrossLink-NX ROI User Tracking Using VVML Board Demonstration - User Guide
FPGA-UG-02158 1.0 6/7/2022 PDF 657.7 KB
CrossLink-NX ROI Face ID Using VVML Board Demonstration - User Guide
FPGA-UG-02159 1.0 6/7/2022 PDF 741.8 KB
TITLE NUMBER VERSION DATE FORMAT SIZE
Select All
CrossLink-NX 3D Head Pose on VVML Board Demonstration - Bitstream
12/5/2023 ZIP 93.1 MB
CrossLink-NX User Tracking and Onlooker Detection on VVML Board Demonstration - Bitstream
11/10/2021 ZIP 375 KB
CrossLink-NX ROI User Tracking Using VVML Board Demonstration - Bitstream
6/7/2022 ZIP 372.8 KB

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