Object Counting

Lattice sensAI Reference Design

Add Object Counting to any Device - This reference design provides an example of how to implement an object counting 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 a counting and overlay engine to count and indicate how many fruit items were detected.

Optimized Performance with Low Power FPGAs - The reference design is optimized for the ECP5-85 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

  • Accelerated, low-power human presence detection at the network edge using neural network model
  • Input from 1080P image sensor, the FPGA handles downscaling and basic ISP functionality
  • 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 power consumption of 0.85 W
Lattice sensAI

Jump to

Block Diagram

Video

Object Counting Using ECP5 and CNNsExpand Image

Object Counting Using ECP5 and CNNs

  • This demonstration tallies apples and oranges to demonstrate object counting
  • The inferencing is done using eight Convolutional Neural Networks implemented in the Embedded Vision Development Kit’s ECP5 FPGA
  • Power consumption is less than 1W

Documentation

Quick Reference
Technical Resources
TITLE NUMBER VERSION DATE FORMAT SIZE
ECP5 Object Counting Mobilenet Quick Start Guide
FPGA-AN-02009 1.0 10/24/2019 PDF 1.3 MB
ECP5 Object Counting Quick Start Guide
FPGA-AN-02006 1.1 6/17/2019 PDF 1.5 MB
TITLE NUMBER VERSION DATE FORMAT SIZE
Object Counting Using CNN Accelerator IP
FPGA-RD-02058 1.0 5/21/2019 PDF 2.7 MB
Object Counting Using CNN Accelerator IP - Project Files
1.0 5/21/2019 ZIP 213.2 MB
Object Counting using Mobilenet CNN Accelerator IP - Documentation
FPGA-RD-02067 1.0 10/24/2019 PDF 3.3 MB
Object Counting using Mobilenet CNN Accelerator IP - Project Files
1.0 10/24/2019 ZIP 203.7 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.