GithubHelp home page GithubHelp logo

jge162 / 471-seniordesign Goto Github PK

View Code? Open in Web Editor NEW
8.0 3.0 1.0 12.44 MB

Team of four CSUF seniors creating an innovative 'Automatic Waste Sorter' that utilizes advanced technology to sort waste accurately and efficiently. The system's core is driven by a Google Coral Dev Board, with additional peripherals such as an Arduino, stepper motors, proximity sensors, a webcam, and object detection (machine learning).

License: MIT License

Python 56.29% C++ 42.46% HTML 1.26%
python git capstone-project computer-engineering gpio html machine-learning object-detection google-coral-dev-board

471-seniordesign's Introduction

Computer Engineering Capstone Project!

Important

Below is a demonstration of the proof of concept:
Recycling, Composting, and Waste using Object Detection.

IMG_9676_compressed.mp4

Poster for project expos


Coral commands

  • use mdt shell to connect to coral via USB
  • use ssh [email protected] to connect via SSH, then use password to connect.
  • connect board to wifi nmtui
  • check wifi connection hostname -I shows IP address of Coral
  • can also pin ping google.com verifies your are connected to WIFI
  • load file to board mdt push PycharmProjects/InferenceCoral/main.py
  • run Python script on Coral python3 main.py
  • sudo apt-get update && sudo apt-get dist-upgrade
  • sudo reboot now
  • sudo shutdown now
  • Connect to dev board serially with mac

Git commands.

  • git config --global user.name "Your username" setup username for Repo
  • git config --global user.email "Your email address" setup account email
  • `git remote set-url origin

After above has been completed does not need to be done again.

  • git pull origin main
  • git add .
  • git commit -m "message you want to describe commit"

Update index.html on Google Coral dev board.

  • cd templates
  • nano index.html makes changes then do the following commands
  • using control k will delete line by line code in index.html file
  • then use control o to save file, then press enter to make changes
  • lastly, use control x to exit nano editor (used with bin/bash normally)



471-seniordesign's People

Contributors

5pencerw avatar andrewtakayama avatar duy301199 avatar jge162 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

Forkers

duy301199

471-seniordesign's Issues

EGCP 471 -> Meeting on 3/17/23 8 out of 15

Long Term Goals:
Spencer is going to work on getting the voltage/current from battery to get charge level
Duy is going to work on IR sensors
Jeremy can work on the website/ virtual control
We'll figure out something for Andrew to do

Painted the prototype today and ran test code for object detection. Good to go. Will work
on streaming at home now.

EGCP 471 -> Meeting on 1/27/23 15 out of 15

  • Spence completed Python script to activate Arduino's with Google Coral dev board.
  • Andrew and I worked to train the model for Machine Learning of 5 objects today also.
  • Lastly, me and Spencer Loaded trained model to Google Coral board via Shell/on Linux.

EGCP 471 -> Meeting on 5/12/23 1 out of 15

Working on PowerPoint in class tomorrow and will update the index.html on coral to latest website build. Then do a practice run in front of class to test project and then final presentation on 5/19 and done.

EGCP 471 -> Meeting on 3/3/23 10 out of 15

Goals are to create a method to remote into our Google coral to control it via ssh instead of using laptop.

  • Also button up all the. wiring
  • Setup a way to view webcam vie internet
  • and more details to follow....

EGCP 471 -> Meeting on 3/24/23 7 out of 15

Worked on testing wireless automation of waste sorter. Duy finished getting ultrasonic sensors working to notify us when the trash bins are full or empty. Spencer updated the model to run more items.

Next class will work with Andrew to update index.html file to improve web appearance.

EGCP 471 -> Meeting on 2/17/23 12 out of 15

Update:

Today only Andrew, Jeremy and Spencer made it to calss.

  • In class Andrew built a newmodel (but after testing it did not operate as expected).
    Need to train a new model next class.
  • Next me and Spencer stayed until about 6:25 pm and tried to get the model to
    work on coral but it did not.
  • Once I got home i used the Coral.ai website to test a still image with Andrews, previoulst mentioned
    trained model and it worked. it noticed a soda can
    -Then once I got home i was able to get the code working and seeing the soda can which gave a confidence
    score of 0.99+ so we are good there.
  • Next class we need to work on connecting to GPIO pins to control Stepper motors.

EGCP 471 -> Meeting on 2/10/23 13 out of 15

Today we reassembled the prototype and did test runs on the railing system.

No progress on coding today, but we did find good examples of Python
that can run Tensor-flow model on Google Coral Dev Board

We will expand the libraries on Python, since PyCoral is not working in Linux
environment.

IMG_8738.mov

EGCP 471 -> Meeting on 4/21/23 4 out of 15

Duy finalized the 3 sensors needed to display level of trash cans content (full or empty). I was able to test Duys code for sensors at home and it works. Spencer took apart and rebuilt streets wiring and drivers. They worked successfully at the end of the class. We left at 6:00 pm.

EGCP 471 -> Meeting on 2/24/23 11 out of 15

Goal, setup

Work on testing GPIO pins functionality with Google Coral dev board.
Work with Duy to implement, sensors.
Work with Andrew on a new trained Model
Work with Spencer on programming.

EGCP 471 -> Meeting on 2/3/23 14 out of 15

Updated checklist ->

  • Get the position of box and camera setup finalized.
  • Paint the box, and get 4 wheels to install, possibly cut the aluminum rails to make it look better?
  • Install plexi glass for sliding doors.
  • Resize the bottom tray. Lid
  • Height - 10 inches
  • Plexi glass size - height -> 15 inches, width -> 1 foot
  • Back cover - Camera height - 20 inches
  • we also disassembly the prototype today. I will be updating rail sizes and adding top, JE.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.