Skip to content

naoppy/tjsif

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

82 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Surveillance Camera to Track People

Demo

Overview

Detects only people with AI and records while tracking people with a camera.

Description

System specification

The specification of this system is written here.

How to extract image changes

The method of extracting image changes uses weighted accumulation on the image. Then binarize. Judgment is made based on whether the area extracted by contour extraction exceeds a certain level.

How to speed up human detection

Use Edge TPU and connect to the USB3.0 terminal on the RaspberyPi. Then use TensorFlow Lite Interpreter. The model is this one

How to control Powerful Motor

Unlike a DC motor, a large current flows through the bipolar motor and its control circuit.

So I used a transistor that can withstand a large current and soldered a circuit like an H-bridge circuit.

The circuit is this.

moving motor demo movie

Requirements

  • RaspberryPi4
  • Coral USB Accelerator(Edge TPU)
  • Bipolar Motor
  • WebCamera(Anything is OK)

Requirement Packages

  • OpenCV4.0
  • numpy
  • PIL(Pillow)
  • Tensorflow Lite Library(runtime only)
  • RPi.GPIO

Usage

$ git clone https://github.com/naoppy/tjsif.git
$ python3 products/main.py

Author

About

The surveillance camera system using edge TPU

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages