Human Counting

Lattice sensAI Demo

Scalable Solution - This human upper-body detection and counting demo utilizes Lattice’s ECP5 FPGA and a Convolutional Neural Network (CNN) acceleration engine. It utilizes 7 convolution layers implemented in 8 Neural Network (NN) engines on ECP5-85 FPGA.

Highly Customizable - This demo, based on the object counting reference design, is provided with end to end components to allow for modification of the object being detected.

Rapid Implementation - The demo utilizes Lattice’s award winning Embedded Vision Development Kit, which consists of three stackable boards incorporating CrossLink, ECP5 FPGA, and the SiI1136 HDMI transceiver device.

Features

  • Accelerated, low-power human presence detection at the network edge using neural network model
  • Configuration files provided for rapid implementation on ECP5 Embedded Vision Development Kit
  • VGG based neural network runs @ 6fps with 224 x 224 x 3 input resolution
  • Mobilenet based neural network runs @ 17 frames per second with 224 x 224 x 3 input resolution
  • Total ECP5 power consumption of 0.85 W
Lattice sensAI

Jump to

Block Diagram

Documentation

Quick Reference
Downloads
TITLE NUMBER VERSION DATE FORMAT SIZE
EVDK Human Counting Demonstration
FPGA-UG-02088 1.0 5/21/2019 PDF 770.3 KB
Human Counting using Mobilenet on EVDK Demonstration User Guide
FPGA-UG-02093 1.0 10/24/2019 PDF 1.1 MB
TITLE NUMBER VERSION DATE FORMAT SIZE
EVDK Based Human Counting Demostration Bitstream
1.0 5/21/2019 ZIP 1.6 MB
Human Counting using Mobilenet on EVDK Demonstration Bitstream
1.0 10/23/2019 ZIP 1.2 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.